WACV 2025 Open Access Repository

Papers

Feature Augmentation Based Test-Time Adaptation: Younggeol Cho,

Youngrae Kim,

Junho Yoon,

Seunghoon Hong,

Dongman Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cho_2025_WACV, author = {Cho, Younggeol and Kim, Youngrae and Yoon, Junho and Hong, Seunghoon and Lee, Dongman}, title = {Feature Augmentation Based Test-Time Adaptation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6838-6847} }
Agtech Framework for Cranberry-Ripening Analysis using Vision Foundation Models: Faith Johnson,

Ryan Meegan,

Jack Lowry,

Peter Oudemans,

Kristin Dana; [pdf] [arXiv]
[bibtex]
@InProceedings{Johnson_2025_WACV, author = {Johnson, Faith and Meegan, Ryan and Lowry, Jack and Oudemans, Peter and Dana, Kristin}, title = {Agtech Framework for Cranberry-Ripening Analysis using Vision Foundation Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1207-1216} }
Test-Time Adaptation in Point Clouds: Leveraging Sampling Variation with Weight Averaging: Ali Bahri,

Moslem Yazdanpanah,

Mehrdad Noori,

Sahar Dastani Oghani,

Milad Cheraghalikhani,

David Osowiechi,

Farzad Beizaee,

Gustavo A. Vargas Hakim,

Ismail Ben Ayed,

Christian Desrosiers; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bahri_2025_WACV, author = {Bahri, Ali and Yazdanpanah, Moslem and Noori, Mehrdad and Oghani, Sahar Dastani and Cheraghalikhani, Milad and Osowiechi, David and Beizaee, Farzad and Hakim, Gustavo A. Vargas and Ben Ayed, Ismail and Desrosiers, Christian}, title = {Test-Time Adaptation in Point Clouds: Leveraging Sampling Variation with Weight Averaging}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {266-275} }
Self-Supervised Anomaly Segmentation via Diffusion Models with Dynamic Transformer UNet: Komal Kumar,

Snehashis Chakraborty,

Dwarikanath Mahapatra,

Behzad Bozorgtabar,

Sudipta Roy; [pdf] [supp]
[bibtex]
@InProceedings{Kumar_2025_WACV, author = {Kumar, Komal and Chakraborty, Snehashis and Mahapatra, Dwarikanath and Bozorgtabar, Behzad and Roy, Sudipta}, title = {Self-Supervised Anomaly Segmentation via Diffusion Models with Dynamic Transformer UNet}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7917-7927} }
RGB2Point: 3D Point Cloud Generation from Single RGB Images: Jae Joong Lee,

Bedrich Benes; [pdf] [arXiv]
[bibtex]
@InProceedings{Lee_2025_WACV, author = {Lee, Jae Joong and Benes, Bedrich}, title = {RGB2Point: 3D Point Cloud Generation from Single RGB Images}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2952-2962} }
Shadow Removal Refinement via Material-Consistent Shadow Edges: Shilin Hu,

Hieu Le,

ShahRukh Athar,

Sagnik Das,

Dimitris Samaras; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hu_2025_WACV, author = {Hu, Shilin and Le, Hieu and Athar, ShahRukh and Das, Sagnik and Samaras, Dimitris}, title = {Shadow Removal Refinement via Material-Consistent Shadow Edges}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2631-2641} }
ChromaDistill : Colorizing Monochrome Radiance Fields with Knowledge Distillation: Ankit Dhiman,

Srinath R,

Srinjay Sarkar,

Lokesh Boregowda,

Venkatesh Babu Radhakrishnan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dhiman_2025_WACV, author = {Dhiman, Ankit and R, Srinath and Sarkar, Srinjay and Boregowda, Lokesh and Radhakrishnan, Venkatesh Babu}, title = {ChromaDistill : Colorizing Monochrome Radiance Fields with Knowledge Distillation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2400-2410} }
CT to PET Translation: A Large-Scale Dataset and Domain-Knowledge-Guided Diffusion Approach: Dac Thai Nguyen,

Trung Thanh Nguyen,

Huu Tien Nguyen,

Thanh Trung Nguyen,

Huy Hieu Pham,

Thanh Hung Nguyen,

Thao Nguyen Truong,

Phi Le Nguyen; [pdf] [arXiv]
[bibtex]
@InProceedings{Nguyen_2025_WACV, author = {Nguyen, Dac Thai and Nguyen, Trung Thanh and Nguyen, Huu Tien and Nguyen, Thanh Trung and Pham, Huy Hieu and Nguyen, Thanh Hung and Truong, Thao Nguyen and Le Nguyen, Phi}, title = {CT to PET Translation: A Large-Scale Dataset and Domain-Knowledge-Guided Diffusion Approach}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1498-1507} }
GTA-HDR: A Large-Scale Synthetic Dataset for HDR Image Reconstruction: Hrishav Bakul Barua,

Kalin Stefanov,

KokSheik Wong,

Abhinav Dhall,

Ganesh Krishnasamy; [pdf] [supp]
[bibtex]
@InProceedings{Barua_2025_WACV, author = {Barua, Hrishav Bakul and Stefanov, Kalin and Wong, KokSheik and Dhall, Abhinav and Krishnasamy, Ganesh}, title = {GTA-HDR: A Large-Scale Synthetic Dataset for HDR Image Reconstruction}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7865-7875} }
HOPE: A Memory-Based and Composition-Aware Framework for Zero-Shot Learning with Hopfield Network and Soft Mixture of Experts: Do Huu Dat,

Po-Yuan Mao,

Tien Hoang Nguyen,

Wray Buntine,

Mohammed Bennamoun; [pdf] [supp]
[bibtex]
@InProceedings{Dat_2025_WACV, author = {Dat, Do Huu and Mao, Po-Yuan and Nguyen, Tien Hoang and Buntine, Wray and Bennamoun, Mohammed}, title = {HOPE: A Memory-Based and Composition-Aware Framework for Zero-Shot Learning with Hopfield Network and Soft Mixture of Experts}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1101-1110} }
IRIS-VIS: A New Dataset for Visibility Estimation in an Industrial Environment: Flavien Armangeon,

Thibaud Ehret,

Enric Meinhardt-Llopis,

Rafael Grompone von Gioi,

Guillaume Thibault,

Marc Petit,

Gabriele Facciolo; [pdf] [supp]
[bibtex]
@InProceedings{Armangeon_2025_WACV, author = {Armangeon, Flavien and Ehret, Thibaud and Meinhardt-Llopis, Enric and von Gioi, Rafael Grompone and Thibault, Guillaume and Petit, Marc and Facciolo, Gabriele}, title = {IRIS-VIS: A New Dataset for Visibility Estimation in an Industrial Environment}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7235-7243} }
PivotAlign: Improve Semi-Supervised Learning by Learning Intra-Class Heterogeneity and Aligning with Pivots: Lingjie Yi,

Tao Sun,

Yikai Zhang,

Songzhu Zheng,

Weimin Lyu,

Haibin Ling,

Chao Chen; [pdf] [supp]
[bibtex]
@InProceedings{Yi_2025_WACV, author = {Yi, Lingjie and Sun, Tao and Zhang, Yikai and Zheng, Songzhu and Lyu, Weimin and Ling, Haibin and Chen, Chao}, title = {PivotAlign: Improve Semi-Supervised Learning by Learning Intra-Class Heterogeneity and Aligning with Pivots}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7907-7916} }
SpectFormer: Frequency and Attention is What You Need in a Vision Transformer: Badri N. Patro,

Vinay P. Namboodiri,

Vijay S. Agneeswaran; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Patro_2025_WACV, author = {Patro, Badri N. and Namboodiri, Vinay P. and Agneeswaran, Vijay S.}, title = {SpectFormer: Frequency and Attention is What You Need in a Vision Transformer}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9525-9536} }
EgoCast: Forecasting Egocentric Human Pose in the Wild: Maria Escobar,

Juanita Puentes,

Cristhian Forigua,

Jordi Pont-Tuset,

Kevis-Kokitsi Maninis,

Pablo Arbelaez; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Escobar_2025_WACV, author = {Escobar, Maria and Puentes, Juanita and Forigua, Cristhian and Pont-Tuset, Jordi and Maninis, Kevis-Kokitsi and Arbelaez, Pablo}, title = {EgoCast: Forecasting Egocentric Human Pose in the Wild}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5831-5841} }
ReEdit: Multimodal Exemplar-Based Image Editing: Ashutosh Srivastava,

Tarun Ram Menta,

Abhinav Java,

Avadhoot Gorakh Jadhav,

Silky Singh,

Surgan Jandial,

Balaji Krishnamurthy; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Srivastava_2025_WACV, author = {Srivastava, Ashutosh and Menta, Tarun Ram and Java, Abhinav and Jadhav, Avadhoot Gorakh and Singh, Silky and Jandial, Surgan and Krishnamurthy, Balaji}, title = {ReEdit: Multimodal Exemplar-Based Image Editing}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {929-939} }
PGRID: Power Grid Reconstruction in Informal Developments using High-Resolution Aerial Imagery: Simone Fobi Nsutezo,

Amrita Gupta,

Duncan Kebut,

Seema Iyer,

Luana Marotti,

Rahul Dodhia,

Juan M. Lavista Ferres,

Anthony Ortiz; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nsutezo_2025_WACV, author = {Nsutezo, Simone Fobi and Gupta, Amrita and Kebut, Duncan and Iyer, Seema and Marotti, Luana and Dodhia, Rahul and Ferres, Juan M. Lavista and Ortiz, Anthony}, title = {PGRID: Power Grid Reconstruction in Informal Developments using High-Resolution Aerial Imagery}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6311-6319} }
Enhancing Predictive Imaging Biomarker Discovery through Treatment Effect Analysis: Shuhan Xiao,

Lukas Klein,

Jens Petersen,

Philipp Vollmuth,

Paul F. Jaeger,

Klaus H. Maier-Hein; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xiao_2025_WACV, author = {Xiao, Shuhan and Klein, Lukas and Petersen, Jens and Vollmuth, Philipp and Jaeger, Paul F. and Maier-Hein, Klaus H.}, title = {Enhancing Predictive Imaging Biomarker Discovery through Treatment Effect Analysis}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4512-4522} }
DeepCA: Deep Learning-Based 3D Coronary Artery Tree Reconstruction from Two 2D Non-Simultaneous X-ray Angiography Projections: Yiying Wang,

Abhirup Banerjee,

Robin P. Choudhury,

Vicente Grau; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2025_WACV, author = {Wang, Yiying and Banerjee, Abhirup and Choudhury, Robin P. and Grau, Vicente}, title = {DeepCA: Deep Learning-Based 3D Coronary Artery Tree Reconstruction from Two 2D Non-Simultaneous X-ray Angiography Projections}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {337-346} }
Precise Integral in NeRFs: Overcoming the Approximation Errors of Numerical Quadrature: Boyuan Zhang,

Zhenliang He,

Meina Kan,

Shiguang Shan; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2025_WACV, author = {Zhang, Boyuan and He, Zhenliang and Kan, Meina and Shan, Shiguang}, title = {Precise Integral in NeRFs: Overcoming the Approximation Errors of Numerical Quadrature}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {317-326} }
FitDiff: Robust Monocular 3D Facial Shape and Reflectance Estimation using Diffusion Models: Stathis Galanakis,

Alexandros Lattas,

Stylianos Moschoglou,

Stefanos Zafeiriou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Galanakis_2025_WACV, author = {Galanakis, Stathis and Lattas, Alexandros and Moschoglou, Stylianos and Zafeiriou, Stefanos}, title = {FitDiff: Robust Monocular 3D Facial Shape and Reflectance Estimation using Diffusion Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {992-1004} }
Differential Privacy Mechanisms in Neural Tangent Kernel Regression: Jiuxiang Gu,

Yingyu Liang,

Zhizhou Sha,

Zhenmei Shi,

Zhao Song; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gu_2025_WACV, author = {Gu, Jiuxiang and Liang, Yingyu and Sha, Zhizhou and Shi, Zhenmei and Song, Zhao}, title = {Differential Privacy Mechanisms in Neural Tangent Kernel Regression}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2342-2356} }
DiL: An Explainable and Practical Metric for Abnormal Uncertainty in Object Detection: Amit Giloni,

Omer Hofman,

Ikuya Morikawa,

Toshiya Shimizu,

Yuval Elovici,

Asaf Shabtai; [pdf] [supp]
[bibtex]
@InProceedings{Giloni_2025_WACV, author = {Giloni, Amit and Hofman, Omer and Morikawa, Ikuya and Shimizu, Toshiya and Elovici, Yuval and Shabtai, Asaf}, title = {DiL: An Explainable and Practical Metric for Abnormal Uncertainty in Object Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2507-2516} }
SoundLoc3D: Invisible 3D Sound Source Localization and Classification using a Multimodal RGB-D Acoustic Camera: Yuhang He,

Sangyun Shin,

Anoop Cherian,

Niki Trigoni,

Andrew Markham; [pdf] [supp]
[bibtex]
@InProceedings{He_2025_WACV, author = {He, Yuhang and Shin, Sangyun and Cherian, Anoop and Trigoni, Niki and Markham, Andrew}, title = {SoundLoc3D: Invisible 3D Sound Source Localization and Classification using a Multimodal RGB-D Acoustic Camera}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5408-5418} }
Enhancing Monocular Depth Estimation with Multi-Source Auxiliary Tasks: Alessio Quercia,

Erenus Yildiz,

Zhuo Cao,

Kai Krajsek,

Abigail Morrison,

Ira Assent,

Hanno Scharr; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Quercia_2025_WACV, author = {Quercia, Alessio and Yildiz, Erenus and Cao, Zhuo and Krajsek, Kai and Morrison, Abigail and Assent, Ira and Scharr, Hanno}, title = {Enhancing Monocular Depth Estimation with Multi-Source Auxiliary Tasks}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6435-6445} }
Neural SDF for Shadow-Aware Unsupervised Structured Light: Kazuto Ichimaru,

Diego Thomas,

Takafumi Iwaguchi,

Hiroshi Kawasaki; [pdf] [supp]
[bibtex]
@InProceedings{Ichimaru_2025_WACV, author = {Ichimaru, Kazuto and Thomas, Diego and Iwaguchi, Takafumi and Kawasaki, Hiroshi}, title = {Neural SDF for Shadow-Aware Unsupervised Structured Light}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {287-296} }
Can Multimodal Large Language Models Truly Perform Multimodal In-Context Learning?: Shuo Chen,

Zhen Han,

Bailan He,

Jianzhe Liu,

Mark Buckley,

Yao Qin,

Philip Torr,

Volker Tresp,

Jindong Gu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2025_WACV, author = {Chen, Shuo and Han, Zhen and He, Bailan and Liu, Jianzhe and Buckley, Mark and Qin, Yao and Torr, Philip and Tresp, Volker and Gu, Jindong}, title = {Can Multimodal Large Language Models Truly Perform Multimodal In-Context Learning?}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6000-6010} }
I Spy with My Little Eye A Minimum Cost Multicut Investigation of Dataset Frames: Katharina Prasse,

Isaac Bravo,

Stefanie Walter,

Margret Keuper; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Prasse_2025_WACV, author = {Prasse, Katharina and Bravo, Isaac and Walter, Stefanie and Keuper, Margret}, title = {I Spy with My Little Eye A Minimum Cost Multicut Investigation of Dataset Frames}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2134-2143} }
A Semantically Impactful Image Manipulation Dataset: Characterizing Image Manipulations using Semantic Significance: Yuwei Chen,

Ming-Ching Chang,

Mattias Kirchner,

Zhenfei Zhang,

Xin Li,

Arslan Basharat,

Anthony Hoogs; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2025_WACV, author = {Chen, Yuwei and Chang, Ming-Ching and Kirchner, Mattias and Zhang, Zhenfei and Li, Xin and Basharat, Arslan and Hoogs, Anthony}, title = {A Semantically Impactful Image Manipulation Dataset: Characterizing Image Manipulations using Semantic Significance}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7648-7657} }
Which Transformer to Favor: A Comparative Analysis of Efficiency in Vision Transformers: Tobias Christian Nauen,

Sebastian Palacio,

Federico Raue,

Andreas Dengel; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nauen_2025_WACV, author = {Nauen, Tobias Christian and Palacio, Sebastian and Raue, Federico and Dengel, Andreas}, title = {Which Transformer to Favor: A Comparative Analysis of Efficiency in Vision Transformers}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6955-6966} }
MixDiff: Mixing Natural and Synthetic Images for Robust Self-Supervised Representations: Reza Akbarian Bafghi,

Nidhin Harilal,

Maziar Raissi,

Claire Monteleoni; [pdf] [arXiv]
[bibtex]
@InProceedings{Bafghi_2025_WACV, author = {Bafghi, Reza Akbarian and Harilal, Nidhin and Raissi, Maziar and Monteleoni, Claire}, title = {MixDiff: Mixing Natural and Synthetic Images for Robust Self-Supervised Representations}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7500-7500} }
Covariance-Based Space Regularization for Few-Shot Class Incremental Learning: Yijie Hu,

Guanyu Yang,

Zhaorui Tan,

Xiaowei Wang,

Kaizhu Huang,

Qiu-Feng Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hu_2025_WACV, author = {Hu, Yijie and Yang, Guanyu and Tan, Zhaorui and Wang, Xiaowei and Huang, Kaizhu and Wang, Qiu-Feng}, title = {Covariance-Based Space Regularization for Few-Shot Class Incremental Learning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9548-9558} }
Structured Human Assessment of Text-to-Image Generative Models: Ciprian A. Corneanu,

Qianli Feng,

Aleix M. Martinez; [pdf]
[bibtex]
@InProceedings{Corneanu_2025_WACV, author = {Corneanu, Ciprian A. and Feng, Qianli and Martinez, Aleix M.}, title = {Structured Human Assessment of Text-to-Image Generative Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4481-4490} }
Unsupervised Single-Image Intrinsic Image Decomposition with LiDAR Intensity Enhanced Training: Shogo Sato,

Takuhiro Kaneko,

Kazuhiko Murasaki,

Taiga Yoshida,

Ryuichi Tanida,

Akisato Kimura; [pdf] [supp]
[bibtex]
@InProceedings{Sato_2025_WACV, author = {Sato, Shogo and Kaneko, Takuhiro and Murasaki, Kazuhiko and Yoshida, Taiga and Tanida, Ryuichi and Kimura, Akisato}, title = {Unsupervised Single-Image Intrinsic Image Decomposition with LiDAR Intensity Enhanced Training}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2368-2378} }
3D Synthesis for Architectural Design: I-Ting Tsai,

Bharath Hariharan; [pdf] [supp]
[bibtex]
@InProceedings{Tsai_2025_WACV, author = {Tsai, I-Ting and Hariharan, Bharath}, title = {3D Synthesis for Architectural Design}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4799-4809} }
Assessing Visually-Continuous Corruption Robustness of Neural Networks Relative to Human Performance: Huakun Shen,

Boyue Hu,

Krzysztof Czarnecki,

Lina Marsso,

Marsha Chechik; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shen_2025_WACV, author = {Shen, Huakun and Hu, Boyue and Czarnecki, Krzysztof and Marsso, Lina and Chechik, Marsha}, title = {Assessing Visually-Continuous Corruption Robustness of Neural Networks Relative to Human Performance}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6300-6310} }
SMDAF: A Scalable Sidewalk Material Data Acquisition Framework with Bidirectional Cross-Modal Knowledge Distillation: Jiawei Liu,

Wayne Lam,

Zhigang Zhu,

Hao Tang; [pdf]
[bibtex]
@InProceedings{Liu_2025_WACV, author = {Liu, Jiawei and Lam, Wayne and Zhu, Zhigang and Tang, Hao}, title = {SMDAF: A Scalable Sidewalk Material Data Acquisition Framework with Bidirectional Cross-Modal Knowledge Distillation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2983-2992} }
Epipolar Attention Field Transformers for Bird's Eye View Semantic Segmentation: Christian Witte,

Jens Behley,

Cyrill Stachniss,

Marvin Raaijmakers; [pdf] [supp]
[bibtex]
@InProceedings{Witte_2025_WACV, author = {Witte, Christian and Behley, Jens and Stachniss, Cyrill and Raaijmakers, Marvin}, title = {Epipolar Attention Field Transformers for Bird's Eye View Semantic Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8649-8658} }
Segment Anything Meets Point Tracking: Frano Rajič,

Lei Ke,

Yu-Wing Tai,

Chi-Keung Tang,

Martin Danelljan,

Fisher Yu; [pdf]
[bibtex]
@InProceedings{Rajic_2025_WACV, author = {Raji\v{c}, Frano and Ke, Lei and Tai, Yu-Wing and Tang, Chi-Keung and Danelljan, Martin and Yu, Fisher}, title = {Segment Anything Meets Point Tracking}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9284-9293} }
Cross-Domain and Cross-Dimension Learning for Image-to-Graph Transformers: Alexander H. Berger,

Laurin Lux,

Suprosanna Shit,

Ivan Ezhof,

Georgios Kaissis,

Martin J. Menten,

Daniel Rueckert,

Johannes C. Paetzold; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Berger_2025_WACV, author = {Berger, Alexander H. and Lux, Laurin and Shit, Suprosanna and Ezhof, Ivan and Kaissis, Georgios and Menten, Martin J. and Rueckert, Daniel and Paetzold, Johannes C.}, title = {Cross-Domain and Cross-Dimension Learning for Image-to-Graph Transformers}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {64-74} }
Beyond Boxes: Mask-Guided Spatio-Temporal Feature Aggregation for Video Object Detection: Khurram Azeem Hashmi,

Talha Uddin Sheikh,

Didier Stricker,

Muhammad Zeshan Afzal; [pdf] [arXiv]
[bibtex]
@InProceedings{Hashmi_2025_WACV, author = {Hashmi, Khurram Azeem and Sheikh, Talha Uddin and Stricker, Didier and Afzal, Muhammad Zeshan}, title = {Beyond Boxes: Mask-Guided Spatio-Temporal Feature Aggregation for Video Object Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8111-8122} }
SpiralMLP: A Lightweight Vision MLP Architecture: Haojie Mu,

Burhan Ul Tayyab,

Nicholas Chua; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mu_2025_WACV, author = {Mu, Haojie and Tayyab, Burhan Ul and Chua, Nicholas}, title = {SpiralMLP: A Lightweight Vision MLP Architecture}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8616-8626} }
On-the-Fly Object-aware Representative Point Selection in Point Cloud: Xiaoyu Zhang,

Ziwei Wang,

Hai Dong,

Zhifeng Bao,

Jiajun Liu; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2025_WACV, author = {Zhang, Xiaoyu and Wang, Ziwei and Dong, Hai and Bao, Zhifeng and Liu, Jiajun}, title = {On-the-Fly Object-aware Representative Point Selection in Point Cloud}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1713-1722} }
Socially-Informed Reconstruction for Pedestrian Trajectory Forecasting: Haleh Damirchi,

Ali Etemad,

Michael Greenspan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Damirchi_2025_WACV, author = {Damirchi, Haleh and Etemad, Ali and Greenspan, Michael}, title = {Socially-Informed Reconstruction for Pedestrian Trajectory Forecasting}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7460-7469} }
Continuous Spatio-Temporal Memory Networks for 4D Cardiac Cine MRI Segmentation: Meng Ye,

Bingyu Xin,

Leon Axel,

Dimitris Metaxas; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ye_2025_WACV, author = {Ye, Meng and Xin, Bingyu and Axel, Leon and Metaxas, Dimitris}, title = {Continuous Spatio-Temporal Memory Networks for 4D Cardiac Cine MRI Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9514-9524} }
Foundation X: Integrating Classification Localization and Segmentation through Lock-Release Pretraining Strategy for Chest X-ray Analysis: Nahid Ul Islam,

DongAo Ma,

Jiaxuan Pang,

Shivasakthi Senthil Velan,

Michael Gotway,

Jianming Liang; [pdf] [supp]
[bibtex]
@InProceedings{Islam_2025_WACV, author = {Islam, Nahid Ul and Ma, DongAo and Pang, Jiaxuan and Velan, Shivasakthi Senthil and Gotway, Michael and Liang, Jianming}, title = {Foundation X: Integrating Classification Localization and Segmentation through Lock-Release Pretraining Strategy for Chest X-ray Analysis}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3647-3656} }
MVMD: A Multi-View Approach for Enhanced Mirror Detection: Yidan Shen,

Yu Wen,

Chen Zhang,

Xin Fu,

Renjie Hu; [pdf] [supp]
[bibtex]
@InProceedings{Shen_2025_WACV, author = {Shen, Yidan and Wen, Yu and Zhang, Chen and Fu, Xin and Hu, Renjie}, title = {MVMD: A Multi-View Approach for Enhanced Mirror Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9314-9323} }
Mind the Map! Accounting for Existing Maps When Estimating Online HDMaps from Sensors: Rémy Sun,

Li Yang,

Diane Lingrand,

Frederic Precioso; [pdf] [supp]
[bibtex]
@InProceedings{Sun_2025_WACV, author = {Sun, R\'emy and Yang, Li and Lingrand, Diane and Precioso, Frederic}, title = {Mind the Map! Accounting for Existing Maps When Estimating Online HDMaps from Sensors}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1671-1681} }
Treading Towards Privacy-Preserving Table Structure Recognition: Sachin Raja,

Ajoy Mondal,

C.V. Jawahar; [pdf] [supp]
[bibtex]
@InProceedings{Raja_2025_WACV, author = {Raja, Sachin and Mondal, Ajoy and Jawahar, C.V.}, title = {Treading Towards Privacy-Preserving Table Structure Recognition}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2311-2321} }
TreeFormer: Single-View Plant Skeleton Estimation via Tree-Constrained Graph Generation: Xinpeng Liu,

Hiroaki Santo,

Yosuke Toda,

Fumio Okura; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2025_WACV, author = {Liu, Xinpeng and Santo, Hiroaki and Toda, Yosuke and Okura, Fumio}, title = {TreeFormer: Single-View Plant Skeleton Estimation via Tree-Constrained Graph Generation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8154-8164} }
Rethinking Cluster-Conditioned Diffusion Models for Label-Free Image Synthesis: Nikolaos Adaloglou,

Tim Kaiser,

Felix Michels,

Markus Kollmann; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Adaloglou_2025_WACV, author = {Adaloglou, Nikolaos and Kaiser, Tim and Michels, Felix and Kollmann, Markus}, title = {Rethinking Cluster-Conditioned Diffusion Models for Label-Free Image Synthesis}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3603-3613} }
Robust Portrait Image Matting and Depth-of-Field Synthesis via Multiplane Images: Zhefan Rao,

Tianjia Zhang,

Yuen Fui Lau,

Qifeng Chen; [pdf]
[bibtex]
@InProceedings{Rao_2025_WACV, author = {Rao, Zhefan and Zhang, Tianjia and Lau, Yuen Fui and Chen, Qifeng}, title = {Robust Portrait Image Matting and Depth-of-Field Synthesis via Multiplane Images}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9589-9599} }
Context-Aware Outlier Rejection for Robust Multi-View 3D Tracking of Similar Small Birds in An Outdoor Aviary: Keon Moradi,

Ethan Haque,

Jasmeen Kaur,

Alexandra B. Bentz,

Eli S. Bridge,

Golnaz Habibi; [pdf] [arXiv]
[bibtex]
@InProceedings{Moradi_2025_WACV, author = {Moradi, Keon and Haque, Ethan and Kaur, Jasmeen and Bentz, Alexandra B. and Bridge, Eli S. and Habibi, Golnaz}, title = {Context-Aware Outlier Rejection for Robust Multi-View 3D Tracking of Similar Small Birds in An Outdoor Aviary}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {983-991} }
MLLM-LLaVA-FL: Multimodal Large Language Model Assisted Federated Learning: Jianyi Zhang,

Hao Yang,

Ang Li,

Xin Guo,

Pu Wang,

Haiming Wang,

Yiran Chen,

Hai Li; [pdf]
[bibtex]
@InProceedings{Zhang_2025_WACV, author = {Zhang, Jianyi and Yang, Hao and Li, Ang and Guo, Xin and Wang, Pu and Wang, Haiming and Chen, Yiran and Li, Hai}, title = {MLLM-LLaVA-FL: Multimodal Large Language Model Assisted Federated Learning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4066-4076} }
Face Anonymization Made Simple: Han-Wei Kung,

Tuomas Varanka,

Sanjay Saha,

Terence Sim,

Nicu Sebe; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kung_2025_WACV, author = {Kung, Han-Wei and Varanka, Tuomas and Saha, Sanjay and Sim, Terence and Sebe, Nicu}, title = {Face Anonymization Made Simple}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1040-1050} }
Diffusion Model Guided Sampling with Pixel-Wise Aleatoric Uncertainty Estimation: Michele De Vita,

Vasileios Belagiannis; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{De_Vita_2025_WACV, author = {De Vita, Michele and Belagiannis, Vasileios}, title = {Diffusion Model Guided Sampling with Pixel-Wise Aleatoric Uncertainty Estimation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3844-3854} }
SIGNN - Star Identification using Graph Neural Networks: Floyd Hepburn-Dickins,

Mark W. Jones,

Mike Edwards,

Jay Paul Morgan,

Steve Bell; [pdf] [supp]
[bibtex]
@InProceedings{Hepburn-Dickins_2025_WACV, author = {Hepburn-Dickins, Floyd and Jones, Mark W. and Edwards, Mike and Morgan, Jay Paul and Bell, Steve}, title = {SIGNN - Star Identification using Graph Neural Networks}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9045-9054} }
Controlling Human Shape and Pose in Text-to-Image Diffusion Models via Domain Adaptation: Benito Buchheim,

Max Reimann,

Jürgen Döllner; [pdf] [supp]
[bibtex]
@InProceedings{Buchheim_2025_WACV, author = {Buchheim, Benito and Reimann, Max and D\"ollner, J\"urgen}, title = {Controlling Human Shape and Pose in Text-to-Image Diffusion Models via Domain Adaptation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3688-3697} }
Zero-Shot Class Unlearning in CLIP with Synthetic Samples: Alexey Kravets,

Vinay Namboodiri; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kravets_2025_WACV, author = {Kravets, Alexey and Namboodiri, Vinay}, title = {Zero-Shot Class Unlearning in CLIP with Synthetic Samples}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6456-6464} }
XPose: Towards Extreme Low Light Hand Pose Estimation: Green Rosh,

Meghana Shankar,

Prateek Kukreja,

Anmol Namdev,

Pawan Prasad B H; [pdf]
[bibtex]
@InProceedings{Rosh_2025_WACV, author = {Rosh, Green and Shankar, Meghana and Kukreja, Prateek and Namdev, Anmol and H, Pawan Prasad B}, title = {XPose: Towards Extreme Low Light Hand Pose Estimation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2838-2848} }
HDPNet: Hourglass Vision Transformer with Dual-Path Feature Pyramid for Camouflaged Object Detection: Jinpeng He,

Biyuan Liu,

Huaixin Chen; [pdf] [supp]
[bibtex]
@InProceedings{He_2025_WACV, author = {He, Jinpeng and Liu, Biyuan and Chen, Huaixin}, title = {HDPNet: Hourglass Vision Transformer with Dual-Path Feature Pyramid for Camouflaged Object Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8627-8636} }
SEM-Net: Efficient Pixel Modelling for Image Inpainting with Spatially Enhanced SSM: Shuang Chen,

Haozheng Zhang,

Amir Atapour-Abarghouei,

Hubert P. H. Shum; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2025_WACV, author = {Chen, Shuang and Zhang, Haozheng and Atapour-Abarghouei, Amir and Shum, Hubert P. H.}, title = {SEM-Net: Efficient Pixel Modelling for Image Inpainting with Spatially Enhanced SSM}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {461-471} }
LLS: Local Learning Rule for Deep Neural Networks Inspired by Neural Activity Synchronization: Marco P. E. Apolinario,

Arani Roy,

Kaushik Roy; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Apolinario_2025_WACV, author = {Apolinario, Marco P. E. and Roy, Arani and Roy, Kaushik}, title = {LLS: Local Learning Rule for Deep Neural Networks Inspired by Neural Activity Synchronization}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7796-7805} }
A Multi-Task Supervised Compression Model for Split Computing: Yoshitomo Matsubara,

Matteo Mendula,

Marco Levorato; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Matsubara_2025_WACV, author = {Matsubara, Yoshitomo and Mendula, Matteo and Levorato, Marco}, title = {A Multi-Task Supervised Compression Model for Split Computing}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4913-4922} }
Advancing Chart Question Answering with Robust Chart Component Recognition: Hanwen Zheng,

Sijia Wang,

Chris Thomas,

Lifu Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zheng_2025_WACV, author = {Zheng, Hanwen and Wang, Sijia and Thomas, Chris and Huang, Lifu}, title = {Advancing Chart Question Answering with Robust Chart Component Recognition}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5741-5750} }
Towards Accurate Unified Anomaly Segmentation: Wenxin Ma,

Qingsong Yao,

Xiang Zhang,

Zhelong Huang,

Zihang Jiang,

S.Kevin Zhou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ma_2025_WACV, author = {Ma, Wenxin and Yao, Qingsong and Zhang, Xiang and Huang, Zhelong and Jiang, Zihang and Zhou, S.Kevin}, title = {Towards Accurate Unified Anomaly Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1342-1352} }
TRUST: Time-Domain Residual Unsupervised Stability Technique for Improved Heart Rate Estimation: Shahzad Ahmad,

Sania Bano,

Sukalpa Chanda,

Santosh Kumar Vipparthi,

Subrahmanyam Murala; [pdf] [supp]
[bibtex]
@InProceedings{Ahmad_2025_WACV, author = {Ahmad, Shahzad and Bano, Sania and Chanda, Sukalpa and Vipparthi, Santosh Kumar and Murala, Subrahmanyam}, title = {TRUST: Time-Domain Residual Unsupervised Stability Technique for Improved Heart Rate Estimation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4046-4055} }
Attention-Guided Masked Autoencoders for Learning Image Representations: Leon Sick,

Dominik Engel,

Pedro Hermosilla,

Timo Ropinski; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sick_2025_WACV, author = {Sick, Leon and Engel, Dominik and Hermosilla, Pedro and Ropinski, Timo}, title = {Attention-Guided Masked Autoencoders for Learning Image Representations}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {836-846} }
Enhancing Vision-Language Few-Shot Adaptation with Negative Learning: Ce Zhang,

Simon Stepputtis,

Katia Sycara,

Yaqi Xie; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2025_WACV, author = {Zhang, Ce and Stepputtis, Simon and Sycara, Katia and Xie, Yaqi}, title = {Enhancing Vision-Language Few-Shot Adaptation with Negative Learning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5905-5915} }
MVAD: A Multiple Visual Artifact Detector for Video Streaming: Chen Feng,

Duolikun Danier,

Fan Zhang,

Alex Mackin,

Andrew Collins,

David Bull; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Feng_2025_WACV, author = {Feng, Chen and Danier, Duolikun and Zhang, Fan and Mackin, Alex and Collins, Andrew and Bull, David}, title = {MVAD: A Multiple Visual Artifact Detector for Video Streaming}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3148-3158} }
Physiology-Aware PolySnake for Coronary Vessel Segmentation: Yizhe Ruan,

Lin Gu,

Yusuke Kurose,

Junichi Iho,

Youji Tokunaga,

Makoto Horie,

Yusaku Hayashi,

Keisuke Nishizawa,

Yasushi Koyama,

Tatsuya Harada; [pdf] [supp]
[bibtex]
@InProceedings{Ruan_2025_WACV, author = {Ruan, Yizhe and Gu, Lin and Kurose, Yusuke and Iho, Junichi and Tokunaga, Youji and Horie, Makoto and Hayashi, Yusaku and Nishizawa, Keisuke and Koyama, Yasushi and Harada, Tatsuya}, title = {Physiology-Aware PolySnake for Coronary Vessel Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8855-8864} }
MOOSS: Mask-Enhanced Temporal Contrastive Learning for Smooth State Evolution in Visual Reinforcement Learning: Jiarui Sun,

M. Ugur Akcal,

Girish Chowdhary,

Wei Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sun_2025_WACV, author = {Sun, Jiarui and Akcal, M. Ugur and Chowdhary, Girish and Zhang, Wei}, title = {MOOSS: Mask-Enhanced Temporal Contrastive Learning for Smooth State Evolution in Visual Reinforcement Learning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6719-6729} }
Removing Geometric Bias in One-Class Anomaly Detection with Adaptive Feature Perturbation: Romain Hermary,

Vincent Gaudilliere,

Abd El Rahman Shabayek,

Djamila Aouada; [pdf]
[bibtex]
@InProceedings{Hermary_2025_WACV, author = {Hermary, Romain and Gaudilliere, Vincent and El Rahman Shabayek, Abd and Aouada, Djamila}, title = {Removing Geometric Bias in One-Class Anomaly Detection with Adaptive Feature Perturbation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6612-6622} }
CryoMAE: Few-Shot Cryo-EM Particle Picking with Masked Autoencoders: Chentianye Xu,

Xueying Zhan,

Min Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2025_WACV, author = {Xu, Chentianye and Zhan, Xueying and Xu, Min}, title = {CryoMAE: Few-Shot Cryo-EM Particle Picking with Masked Autoencoders}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3876-3885} }
BroadTrack: Broadcast Camera Tracking for Soccer: Floriane Magera,

Thomas Hoyoux,

Olivier Barnich,

Marc Van Droogenbroeck; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Magera_2025_WACV, author = {Magera, Floriane and Hoyoux, Thomas and Barnich, Olivier and Van Droogenbroeck, Marc}, title = {BroadTrack: Broadcast Camera Tracking for Soccer}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6177-6187} }
Negative-Prompt Inversion: Fast Image Inversion for Editing with Text-Guided Diffusion Models: Daiki Miyake,

Akihiro Iohara,

Yu Saito,

Toshiyuki Tanaka; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Miyake_2025_WACV, author = {Miyake, Daiki and Iohara, Akihiro and Saito, Yu and Tanaka, Toshiyuki}, title = {Negative-Prompt Inversion: Fast Image Inversion for Editing with Text-Guided Diffusion Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2063-2072} }
EvoCL: Continual Learning over Evolving Domains: Vishnuprasadh Kumaravelu,

P.K. Srijith,

Sunil Gupta; [pdf] [supp]
[bibtex]
@InProceedings{Kumaravelu_2025_WACV, author = {Kumaravelu, Vishnuprasadh and Srijith, P.K. and Gupta, Sunil}, title = {EvoCL: Continual Learning over Evolving Domains}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7522-7530} }
Adaptive and Temporally Consistent Gaussian Surfels for Multi-View Dynamic Reconstruction: Decai Chen,

Brianne Oberson,

Ingo Feldmann,

Oliver Schreer,

Anna Hilsmann,

Peter Eisert; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2025_WACV, author = {Chen, Decai and Oberson, Brianne and Feldmann, Ingo and Schreer, Oliver and Hilsmann, Anna and Eisert, Peter}, title = {Adaptive and Temporally Consistent Gaussian Surfels for Multi-View Dynamic Reconstruction}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {742-752} }
ZeroComp: Zero-Shot Object Compositing from Image Intrinsics via Diffusion: Zitian Zhang,

Frédéric Fortier-Chouinard,

Mathieu Garon,

Anand Bhattad,

Jean-François Lalonde; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2025_WACV, author = {Zhang, Zitian and Fortier-Chouinard, Fr\'ed\'eric and Garon, Mathieu and Bhattad, Anand and Lalonde, Jean-Fran\c{c}ois}, title = {ZeroComp: Zero-Shot Object Compositing from Image Intrinsics via Diffusion}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {483-494} }
Needles & Haystacks: Dataset and Benchmark for Domain-Agnostic Image-Based Rigid Slice-to-Volume Registration: Anton Frolov,

Florian Kleiner,

Christiane Rößler,

Volker Rodehorst; [pdf] [supp]
[bibtex]
@InProceedings{Frolov_2025_WACV, author = {Frolov, Anton and Kleiner, Florian and R\"o{\ss}ler, Christiane and Rodehorst, Volker}, title = {Needles \& Haystacks: Dataset and Benchmark for Domain-Agnostic Image-Based Rigid Slice-to-Volume Registration}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7081-7091} }
Retrieval Augmented Recipe Generation: Guoshan Liu,

Hailong Yin,

Bin Zhu,

Jingjing Chen,

Chong-Wah Ngo,

Yu-Gang Jiang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2025_WACV, author = {Liu, Guoshan and Yin, Hailong and Zhu, Bin and Chen, Jingjing and Ngo, Chong-Wah and Jiang, Yu-Gang}, title = {Retrieval Augmented Recipe Generation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2453-2463} }
Enriching Local Patterns with Multi-Token Attention for Broad-Sight Neural Networks: Hankyul Kang,

Jongbin Ryu; [pdf] [supp]
[bibtex]
@InProceedings{Kang_2025_WACV, author = {Kang, Hankyul and Ryu, Jongbin}, title = {Enriching Local Patterns with Multi-Token Attention for Broad-Sight Neural Networks}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8259-8268} }
Data-Efficient 3D Visual Grounding via Order-Aware Referring: Tung-Yu Wu,

Sheng-Yu Huang,

Yu-Chiang Frank Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2025_WACV, author = {Wu, Tung-Yu and Huang, Sheng-Yu and Wang, Yu-Chiang Frank}, title = {Data-Efficient 3D Visual Grounding via Order-Aware Referring}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3107-3117} }
Boosting Semi-Supervised Video Action Detection with Temporal Context: Donghyeon Kwon,

Inho Kim,

Suha Kwak; [pdf] [supp]
[bibtex]
@InProceedings{Kwon_2025_WACV, author = {Kwon, Donghyeon and Kim, Inho and Kwak, Suha}, title = {Boosting Semi-Supervised Video Action Detection with Temporal Context}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {847-858} }
CCASeg: Decoding Multi-Scale Context with Convolutional Cross-Attention for Semantic Segmentation: Jiwon Yoo,

Dami Ko,

Gyeonghwan Kim; [pdf]
[bibtex]
@InProceedings{Yoo_2025_WACV, author = {Yoo, Jiwon and Ko, Dami and Kim, Gyeonghwan}, title = {CCASeg: Decoding Multi-Scale Context with Convolutional Cross-Attention for Semantic Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9461-9470} }
STLight: A Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal Joint Processing: Andrea Alfarano,

Alberto Alfarano,

Linda Friso,

Andrea Bacciu,

Irene Amerini,

Fabrizio Silvestri; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Alfarano_2025_WACV, author = {Alfarano, Andrea and Alfarano, Alberto and Friso, Linda and Bacciu, Andrea and Amerini, Irene and Silvestri, Fabrizio}, title = {STLight: A Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal Joint Processing}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1090-1100} }
Active Learning for Image Segmentation with Binary User Feedback: Debanjan Goswami,

Shayok Chakraborty; [pdf]
[bibtex]
@InProceedings{Goswami_2025_WACV, author = {Goswami, Debanjan and Chakraborty, Shayok}, title = {Active Learning for Image Segmentation with Binary User Feedback}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9138-9147} }
FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding: Zhuo Cao,

Bingqing Zhang,

Heming Du,

Xin Yu,

Xue Li,

Sen Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Cao_2025_WACV, author = {Cao, Zhuo and Zhang, Bingqing and Du, Heming and Yu, Xin and Li, Xue and Wang, Sen}, title = {FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9208-9218} }
Fine-Grained Spatial and Verbal Losses for 3D Visual Grounding: Sombit Dey,

Ozan Unal,

Christos Sakaridis,

Luc Van Gool; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dey_2025_WACV, author = {Dey, Sombit and Unal, Ozan and Sakaridis, Christos and Van Gool, Luc}, title = {Fine-Grained Spatial and Verbal Losses for 3D Visual Grounding}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4852-4861} }
Towards On-the-Fly Novel Category Discovery in Dynamic Long-Tailed Distributions: Hoin Jung,

Xiaoqian Wang; [pdf] [supp]
[bibtex]
@InProceedings{Jung_2025_WACV, author = {Jung, Hoin and Wang, Xiaoqian}, title = {Towards On-the-Fly Novel Category Discovery in Dynamic Long-Tailed Distributions}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6795-6804} }
Survival Prediction in Lung Cancer through Multi-Modal Representation Learning: Aiman Farooq,

Deepak Mishra,

Santanu Chaudhury; [pdf] [arXiv]
[bibtex]
@InProceedings{Farooq_2025_WACV, author = {Farooq, Aiman and Mishra, Deepak and Chaudhury, Santanu}, title = {Survival Prediction in Lung Cancer through Multi-Modal Representation Learning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3907-3915} }
PALO: A Polyglot Large Multimodal Model for 5B People: Hanoona Rasheed,

Muhammad Maaz,

Abdelrahman Shaker,

Salman Khan,

Hisham Cholakkal,

Rao M. Anwer,

Tim Baldwin,

Michael Felsberg,

Fahad S. Khan; [pdf] [arXiv]
[bibtex]
@InProceedings{Rasheed_2025_WACV, author = {Rasheed, Hanoona and Maaz, Muhammad and Shaker, Abdelrahman and Khan, Salman and Cholakkal, Hisham and Anwer, Rao M. and Baldwin, Tim and Felsberg, Michael and Khan, Fahad S.}, title = {PALO: A Polyglot Large Multimodal Model for 5B People}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1745-1754} }
Uncertainty-Aware Regularization for Image-to-Image Translation: Anuja Vats,

Ivar Farup,

Marius Pedersen,

Kiran Raja; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Vats_2025_WACV, author = {Vats, Anuja and Farup, Ivar and Pedersen, Marius and Raja, Kiran}, title = {Uncertainty-Aware Regularization for Image-to-Image Translation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3965-3974} }
Revisiting Deep Archetypal Analysis for Phenotype Discovery in High Content Imaging: Mario Wieser,

Daniel Siegismund,

Stephan Steigele; [pdf] [supp]
[bibtex]
@InProceedings{Wieser_2025_WACV, author = {Wieser, Mario and Siegismund, Daniel and Steigele, Stephan}, title = {Revisiting Deep Archetypal Analysis for Phenotype Discovery in High Content Imaging}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3802-3811} }
GaussianBeV : 3D Gaussian Representation Meets Perception Models for BeV Segmentation: Florian Chabot,

Nicolas Granger,

Guillaume Lapouge; [pdf] [arXiv]
[bibtex]
@InProceedings{Chabot_2025_WACV, author = {Chabot, Florian and Granger, Nicolas and Lapouge, Guillaume}, title = {GaussianBeV : 3D Gaussian Representation Meets Perception Models for BeV Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2250-2259} }
PC-GZSL: Prior Correction for Generalized Zero Shot Learning: S Divakar Bhat,

Amit More,

Mudit Soni,

Bhuvan Aggarwal; [pdf] [supp]
[bibtex]
@InProceedings{Bhat_2025_WACV, author = {Bhat, S Divakar and More, Amit and Soni, Mudit and Aggarwal, Bhuvan}, title = {PC-GZSL: Prior Correction for Generalized Zero Shot Learning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7173-7183} }
Multi-Scale Grouped Prototypes for Interpretable Semantic Segmentation: Hugo Porta,

Emanuele Dalsasso,

Diego Marcos,

Devis Tuia; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Porta_2025_WACV, author = {Porta, Hugo and Dalsasso, Emanuele and Marcos, Diego and Tuia, Devis}, title = {Multi-Scale Grouped Prototypes for Interpretable Semantic Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2869-2880} }
Effective and Efficient Medical Image Segmentation with Hierarchical Context Interaction: Zehua Cheng,

Di Yuan,

Wenhu Zhang,

Thomas Lukasiewicz; [pdf]
[bibtex]
@InProceedings{Cheng_2025_WACV, author = {Cheng, Zehua and Yuan, Di and Zhang, Wenhu and Lukasiewicz, Thomas}, title = {Effective and Efficient Medical Image Segmentation with Hierarchical Context Interaction}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9378-9387} }
A 0-Shot Self-Attention Mechanism for Accelerated Diagonal Attention: Mario Viti,

Nadiya Shvai,

Arcadi Llanza,

Amir Nakib; [pdf]
[bibtex]
@InProceedings{Viti_2025_WACV, author = {Viti, Mario and Shvai, Nadiya and Llanza, Arcadi and Nakib, Amir}, title = {A 0-Shot Self-Attention Mechanism for Accelerated Diagonal Attention}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7308-7315} }
Temporal Dynamics in Visual Data: Analyzing the Impact of Time on Classification Accuracy: Tom Pégeot,

Eva Feillet,

Adrian Popescu,

Inna Kucher,

Bertrand Delezoide; [pdf] [supp]
[bibtex]
@InProceedings{Pegeot_2025_WACV, author = {P\'egeot, Tom and Feillet, Eva and Popescu, Adrian and Kucher, Inna and Delezoide, Bertrand}, title = {Temporal Dynamics in Visual Data: Analyzing the Impact of Time on Classification Accuracy}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6932-6943} }
Bidirectional Multi-Step Domain Generalization for Visible-Infrared Person Re-Identification: Mahdi Alehdaghi,

Pourya Shamsolmoali,

Rafael M. O. Cruz,

Eric Granger; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Alehdaghi_2025_WACV, author = {Alehdaghi, Mahdi and Shamsolmoali, Pourya and Cruz, Rafael M. O. and Granger, Eric}, title = {Bidirectional Multi-Step Domain Generalization for Visible-Infrared Person Re-Identification}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {763-773} }
Pre-Trained Multiple Latent Variable Generative Models are Good Defenders Against Adversarial Attacks: Dario Serez,

Marco Cristani,

Alessio Del Bue,

Vittorio Murino,

Pietro Morerio; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Serez_2025_WACV, author = {Serez, Dario and Cristani, Marco and Del Bue, Alessio and Murino, Vittorio and Morerio, Pietro}, title = {Pre-Trained Multiple Latent Variable Generative Models are Good Defenders Against Adversarial Attacks}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6506-6516} }
TPP-Gaze: Modelling Gaze Dynamics in Space and Time with Neural Temporal Point Processes: Alessandro D'Amelio,

Giuseppe Cartella,

Vittorio Cuculo,

Manuele Lucchi,

Marcella Cornia,

Rita Cucchiara,

Giuseppe Boccignone; [pdf] [supp]
[bibtex]
@InProceedings{D'Amelio_2025_WACV, author = {D'Amelio, Alessandro and Cartella, Giuseppe and Cuculo, Vittorio and Lucchi, Manuele and Cornia, Marcella and Cucchiara, Rita and Boccignone, Giuseppe}, title = {TPP-Gaze: Modelling Gaze Dynamics in Space and Time with Neural Temporal Point Processes}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8775-8784} }
Towards Unsupervised Blind Face Restoration using Diffusion Prior: Tianshu Kuai,

Sina Honari,

Igor Gilitschenski,

Alex Levinshtein; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kuai_2025_WACV, author = {Kuai, Tianshu and Honari, Sina and Gilitschenski, Igor and Levinshtein, Alex}, title = {Towards Unsupervised Blind Face Restoration using Diffusion Prior}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1839-1849} }
Long-Term Ad Memorability: Understanding & Generating Memorable Ads: Harini Si,

Somesh Singh,

Yaman Kumar Singla,

Aanisha Bhattacharyya,

Veeky Baths,

Changyou Chen,

Rajiv Ratn Shah,

Balaji Krishnamurthy; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Si_2025_WACV, author = {Si, Harini and Singh, Somesh and Singla, Yaman Kumar and Bhattacharyya, Aanisha and Baths, Veeky and Chen, Changyou and Shah, Rajiv Ratn and Krishnamurthy, Balaji}, title = {Long-Term Ad Memorability: Understanding \& Generating Memorable Ads}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5707-5718} }
Mamba-ST: State Space Model for Efficient Style Transfer: Filippo Botti,

Alex Ergasti,

Leonardo Rossi,

Tomaso Fontanini,

Claudio Ferrari,

Massimo Bertozzi,

Andrea Prati; [pdf] [supp]
[bibtex]
@InProceedings{Botti_2025_WACV, author = {Botti, Filippo and Ergasti, Alex and Rossi, Leonardo and Fontanini, Tomaso and Ferrari, Claudio and Bertozzi, Massimo and Prati, Andrea}, title = {Mamba-ST: State Space Model for Efficient Style Transfer}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7786-7795} }
Through the Curved Cover: Synthesizing Cover Aberrated Scenes with Refractive Field: Liuyue Xie,

Jiancong Guo,

László A. Jeni,

Zhiheng Jia,

Mingyang Li,

Yunwen Zhou,

Chao Guo; [pdf] [arXiv]
[bibtex]
@InProceedings{Xie_2025_WACV, author = {Xie, Liuyue and Guo, Jiancong and Jeni, L\'aszl\'o A. and Jia, Zhiheng and Li, Mingyang and Zhou, Yunwen and Guo, Chao}, title = {Through the Curved Cover: Synthesizing Cover Aberrated Scenes with Refractive Field}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9632-9641} }
Crossroads of Continents: Automated Artifact Extraction for Cultural Adaptation with Large Multimodal Models: Anjishnu Mukherjee,

Ziwei Zhu,

Antonios Anastasopoulos; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mukherjee_2025_WACV, author = {Mukherjee, Anjishnu and Zhu, Ziwei and Anastasopoulos, Antonios}, title = {Crossroads of Continents: Automated Artifact Extraction for Cultural Adaptation with Large Multimodal Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1755-1764} }
SoundSil-DS: Deep Denoising and Segmentation of Sound-Field Images with Silhouettes: Risako Tanigawa,

Kenji Ishikawa,

Noboru Harada,

Yasuhiro Oikawa; [pdf] [supp]
[bibtex]
@InProceedings{Tanigawa_2025_WACV, author = {Tanigawa, Risako and Ishikawa, Kenji and Harada, Noboru and Oikawa, Yasuhiro}, title = {SoundSil-DS: Deep Denoising and Segmentation of Sound-Field Images with Silhouettes}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4947-4956} }
OpenCapBench: A Benchmark to Bridge Pose Estimation and Biomechanics: Yoni Gozlan,

Antoine Falisse,

Scott Uhlrich,

Anthony Gatti,

Michael Black,

Jennifer Hicks,

Scott Delp,

Akshay Chaudhari; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gozlan_2025_WACV, author = {Gozlan, Yoni and Falisse, Antoine and Uhlrich, Scott and Gatti, Anthony and Black, Michael and Hicks, Jennifer and Delp, Scott and Chaudhari, Akshay}, title = {OpenCapBench: A Benchmark to Bridge Pose Estimation and Biomechanics}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4056-4065} }
Neural Graph Map: Dense Mapping with Efficient Loop Closure Integration: Leonard Bruns,

Jun Zhang,

Patric Jensfelt; [pdf] [supp]
[bibtex]
@InProceedings{Bruns_2025_WACV, author = {Bruns, Leonard and Zhang, Jun and Jensfelt, Patric}, title = {Neural Graph Map: Dense Mapping with Efficient Loop Closure Integration}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2900-2909} }
Label Convergence: Defining an Upper Performance Bound in Object Recognition through Contradictory Annotations: David Eike Tschirschwitz,

Volker Rodehorst; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tschirschwitz_2025_WACV, author = {Tschirschwitz, David Eike and Rodehorst, Volker}, title = {Label Convergence: Defining an Upper Performance Bound in Object Recognition through Contradictory Annotations}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6848-6857} }
A Two-Head Loss Function for Deep Average-K Classification: Camille Garcin,

Maximilien Servajean,

Alexis Joly,

Joseph Salmon; [pdf] [supp]
[bibtex]
@InProceedings{Garcin_2025_WACV, author = {Garcin, Camille and Servajean, Maximilien and Joly, Alexis and Salmon, Joseph}, title = {A Two-Head Loss Function for Deep Average-K Classification}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7358-7367} }
DyRoNet: Dynamic Routing and Low-Rank Adapters for Autonomous Driving Streaming Perception: Xiang Huang,

Zhi-Qi Cheng,

Jun-Yan He,

Chenyang Li,

Wangmeng Xiang,

Baigui Sun; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2025_WACV, author = {Huang, Xiang and Cheng, Zhi-Qi and He, Jun-Yan and Li, Chenyang and Xiang, Wangmeng and Sun, Baigui}, title = {DyRoNet: Dynamic Routing and Low-Rank Adapters for Autonomous Driving Streaming Perception}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5959-5968} }
PrivateEye: In-Sensor Privacy Preservation Through Optical Feature Separation: Adith Boloor,

Weikai Lin,

Tianrui Ma,

Yu Feng,

Yuhao Zhu,

Xuan Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Boloor_2025_WACV, author = {Boloor, Adith and Lin, Weikai and Ma, Tianrui and Feng, Yu and Zhu, Yuhao and Zhang, Xuan}, title = {PrivateEye: In-Sensor Privacy Preservation Through Optical Feature Separation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2357-2367} }
Learning under Noisy Labels Spurious Points and Diverse Structures: TS40K a 3D Point Cloud Dataset of Rural Terrain and Electrical Transmission Systems: Diogo Lavado,

Ricardo Santos,

André Coelho,

João Santos,

Alessandra Micheletti,

Cláudia Soares; [pdf]
[bibtex]
@InProceedings{Lavado_2025_WACV, author = {Lavado, Diogo and Santos, Ricardo and Coelho, Andr\'e and Santos, Jo\~ao and Micheletti, Alessandra and Soares, Cl\'audia}, title = {Learning under Noisy Labels Spurious Points and Diverse Structures: TS40K a 3D Point Cloud Dataset of Rural Terrain and Electrical Transmission Systems}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7326-7336} }
DT-LSD: Deformable Transformer-Based Line Segment Detection: Sebastian Janampa,

Marios Pattichis; [pdf]
[bibtex]
@InProceedings{Janampa_2025_WACV, author = {Janampa, Sebastian and Pattichis, Marios}, title = {DT-LSD: Deformable Transformer-Based Line Segment Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3477-3486} }
Unconstrained Open Vocabulary Image Classification: Zero-Shot Transfer from Text to Image via CLIP Inversion: Philipp Allgeuer,

Kyra Ahrens,

Stefan Wermter; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Allgeuer_2025_WACV, author = {Allgeuer, Philipp and Ahrens, Kyra and Wermter, Stefan}, title = {Unconstrained Open Vocabulary Image Classification: Zero-Shot Transfer from Text to Image via CLIP Inversion}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8206-8217} }
RapidNet: Multi-Level Dilated Convolution Based Mobile Backbone: Mustafa Munir,

Md Mostafijur Rahman,

Radu Marculescu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Munir_2025_WACV, author = {Munir, Mustafa and Rahman, Md Mostafijur and Marculescu, Radu}, title = {RapidNet: Multi-Level Dilated Convolution Based Mobile Backbone}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8291-8301} }
Uncertainty-Based Data-Wise Label Smoothing for Calibrating Multiple Instance Learning in Histopathology Image Classification: Hyeongmin Park,

Sungrae Hong,

Chanjae Song,

Jongwoo Kim,

Mun Yong Yi; [pdf] [supp]
[bibtex]
@InProceedings{Park_2025_WACV, author = {Park, Hyeongmin and Hong, Sungrae and Song, Chanjae and Kim, Jongwoo and Yi, Mun Yong}, title = {Uncertainty-Based Data-Wise Label Smoothing for Calibrating Multiple Instance Learning in Histopathology Image Classification}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {599-608} }
Active Event Alignment for Monocular Distance Estimation: Nan Cai,

Pia Bideau; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cai_2025_WACV, author = {Cai, Nan and Bideau, Pia}, title = {Active Event Alignment for Monocular Distance Estimation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2464-2473} }
ACE: Action Concept Enhancement of Video-Language Models in Procedural Videos: Reza Ghoddoosian,

Nakul Agarwal,

Isht Dwivedi,

Behzad Dariush; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ghoddoosian_2025_WACV, author = {Ghoddoosian, Reza and Agarwal, Nakul and Dwivedi, Isht and Dariush, Behzad}, title = {ACE: Action Concept Enhancement of Video-Language Models in Procedural Videos}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9503-9513} }
Psych-Occlusion: using Visual Psychophysics for Aerial Detection of Occluded Persons during Search and Rescue: Arturo Miguel Russell Bernal,

Jane Cleland-Huang,

Walter Scheirer; [pdf]
[bibtex]
@InProceedings{Russell_Bernal_2025_WACV, author = {Russell Bernal, Arturo Miguel and Cleland-Huang, Jane and Scheirer, Walter}, title = {Psych-Occlusion: using Visual Psychophysics for Aerial Detection of Occluded Persons during Search and Rescue}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3383-3395} }
Ordinal Multiple-Instance Learning for Ulcerative Colitis Severity Estimation with Selective Aggregated Transformer: Kaito Shiku,

Kazuya Nishimura,

Daiki Suehiro,

Kiyohito Tanaka,

Ryoma Bise; [pdf] [arXiv]
[bibtex]
@InProceedings{Shiku_2025_WACV, author = {Shiku, Kaito and Nishimura, Kazuya and Suehiro, Daiki and Tanaka, Kiyohito and Bise, Ryoma}, title = {Ordinal Multiple-Instance Learning for Ulcerative Colitis Severity Estimation with Selective Aggregated Transformer}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4290-4299} }
ConDiSR: Contrastive Disentanglement and Style Regularization for Single Domain Generalizatio: Aleksandr Matsun,

Numan Saeed,

Fadillah Adamsyah Maani,

Mohammad Yaqub; [pdf]
[bibtex]
@InProceedings{Matsun_2025_WACV, author = {Matsun, Aleksandr and Saeed, Numan and Maani, Fadillah Adamsyah and Yaqub, Mohammad}, title = {ConDiSR: Contrastive Disentanglement and Style Regularization for Single Domain Generalizatio}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2881-2889} }
MRI Reconstruction with Regularized 3D Diffusion Model (R3DM): Arya Bangun,

Zhuo Cao,

Alessio Quercia,

Hanno Scharr,

Elisabeth Pfaehler; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bangun_2025_WACV, author = {Bangun, Arya and Cao, Zhuo and Quercia, Alessio and Scharr, Hanno and Pfaehler, Elisabeth}, title = {MRI Reconstruction with Regularized 3D Diffusion Model (R3DM)}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {700-710} }
DreaMo: Articulated 3D Reconstruction from a Single Casual Video: Tao Tu,

Ming-Feng Li,

Chieh Hubert Lin,

Yen-Chi Cheng,

Min Sun,

Ming-Hsuan Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tu_2025_WACV, author = {Tu, Tao and Li, Ming-Feng and Lin, Chieh Hubert and Cheng, Yen-Chi and Sun, Min and Yang, Ming-Hsuan}, title = {DreaMo: Articulated 3D Reconstruction from a Single Casual Video}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2269-2279} }
A Regional-Level Resource-Saving Model for Winter Road Surface Snow Detection in Extreme Weathers: Xinhao Zhou,

Tong Wang,

Zhaodong Liu,

Hao Wei,

Guangyuan Pan; [pdf]
[bibtex]
@InProceedings{Zhou_2025_WACV, author = {Zhou, Xinhao and Wang, Tong and Liu, Zhaodong and Wei, Hao and Pan, Guangyuan}, title = {A Regional-Level Resource-Saving Model for Winter Road Surface Snow Detection in Extreme Weathers}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6063-6072} }
EDMB: Edge Detector with Mamba: Yachuan Li,

Xavier Soria Poma,

Yun Bai,

Qian Xiao,

Chaozhi Yang,

Guanlin Li,

Zongmin Li; [pdf] [arXiv]
[bibtex]
@InProceedings{Li_2025_WACV, author = {Li, Yachuan and Poma, Xavier Soria and Bai, Yun and Xiao, Qian and Yang, Chaozhi and Li, Guanlin and Li, Zongmin}, title = {EDMB: Edge Detector with Mamba}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7671-7680} }
USWformer: Efficient Sparse Wavelet Transformer for Underwater Image Enhancement: Priyanka Mishra,

Nancy Mehta,

Santosh Kumar Vipparthi,

Subrahmanyam Murala; [pdf] [supp]
[bibtex]
@InProceedings{Mishra_2025_WACV, author = {Mishra, Priyanka and Mehta, Nancy and Vipparthi, Santosh Kumar and Murala, Subrahmanyam}, title = {USWformer: Efficient Sparse Wavelet Transformer for Underwater Image Enhancement}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3372-3382} }
Data Augmentation for Surgical Scene Segmentation with Anatomy-Aware Diffusion Models: Danush Kumar Venkatesh,

Dominik Rivoir,

Micha Pfeiffer,

Fiona Kolbinger,

Stefanie Speidel; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Venkatesh_2025_WACV, author = {Venkatesh, Danush Kumar and Rivoir, Dominik and Pfeiffer, Micha and Kolbinger, Fiona and Speidel, Stefanie}, title = {Data Augmentation for Surgical Scene Segmentation with Anatomy-Aware Diffusion Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2280-2290} }
Identity Curvature Laplace Approximation for Improved Out-of-Distribution Detection: Maksim Zhdanov,

Stanislav Dereka,

Sergey Kolesnikov; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhdanov_2025_WACV, author = {Zhdanov, Maksim and Dereka, Stanislav and Kolesnikov, Sergey}, title = {Identity Curvature Laplace Approximation for Improved Out-of-Distribution Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7019-7028} }
CLIPScope: Enhancing Zero-Shot OOD Detection with Bayesian Scoring: Hao Fu,

Naman Patel,

Prashanth Krishnamurthy,

Farshad khorrami; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fu_2025_WACV, author = {Fu, Hao and Patel, Naman and Krishnamurthy, Prashanth and khorrami, Farshad}, title = {CLIPScope: Enhancing Zero-Shot OOD Detection with Bayesian Scoring}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5346-5355} }
Graph-Jigsaw Conditioned Diffusion Model for Skeleton-Based Video Anomaly Detection: Ali Karami,

Thi Kieu Khanh Ho,

Narges Armanfard; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Karami_2025_WACV, author = {Karami, Ali and Ho, Thi Kieu Khanh and Armanfard, Narges}, title = {Graph-Jigsaw Conditioned Diffusion Model for Skeleton-Based Video Anomaly Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4237-4247} }
Federated Source-Free Domain Adaptation for Classification: Weighted Cluster Aggregation for Unlabeled Data: Junki Mori,

Kosuke Kihara,

Taiki Miyagawa,

Akinori F. Ebihara,

Isamu Teranishi,

Hisashi Kashima; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mori_2025_WACV, author = {Mori, Junki and Kihara, Kosuke and Miyagawa, Taiki and Ebihara, Akinori F. and Teranishi, Isamu and Kashima, Hisashi}, title = {Federated Source-Free Domain Adaptation for Classification: Weighted Cluster Aggregation for Unlabeled Data}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6879-6889} }
Active Learning for Vision Language Models: Bardia Safaei,

Vishal M. Patel; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Safaei_2025_WACV, author = {Safaei, Bardia and Patel, Vishal M.}, title = {Active Learning for Vision Language Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4902-4912} }
Metric Compatible Training for Online Backfilling in Large-Scale Retrieval: Seonguk Seo,

Mustafa Gokhan Uzunbas,

Bohyung Han,

Sara Cao,

Ser-Nam Lim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Seo_2025_WACV, author = {Seo, Seonguk and Uzunbas, Mustafa Gokhan and Han, Bohyung and Cao, Sara and Lim, Ser-Nam}, title = {Metric Compatible Training for Online Backfilling in Large-Scale Retrieval}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1537-1545} }
GaitCloud: Leveraging Spatial-Temporal Information for LiDAR-Base Gait Recognition with A True-3D Gait Representation: Shaoxiong Zhang,

Hiromitsu Awano,

Takashi Sato; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2025_WACV, author = {Zhang, Shaoxiong and Awano, Hiromitsu and Sato, Takashi}, title = {GaitCloud: Leveraging Spatial-Temporal Information for LiDAR-Base Gait Recognition with A True-3D Gait Representation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2849-2858} }
Dequantization and Color Transfer with Diffusion Models: Vaibhav Vavilala,

Faaris Shaik,

David Forsyth; [pdf] [arXiv]
[bibtex]
@InProceedings{Vavilala_2025_WACV, author = {Vavilala, Vaibhav and Shaik, Faaris and Forsyth, David}, title = {Dequantization and Color Transfer with Diffusion Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9612-9621} }
Partial Filter-Sharing: Improved Parameter-Sharing Method for Single Image Super-Resolution Networks: Karam Park,

Nam Ik Cho; [pdf] [supp]
[bibtex]
@InProceedings{Park_2025_WACV, author = {Park, Karam and Cho, Nam Ik}, title = {Partial Filter-Sharing: Improved Parameter-Sharing Method for Single Image Super-Resolution Networks}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2653-2663} }
Identify Backdoored Model in Federated Learning via Individual Unlearning: Jiahao Xu,

Zikai Zhang,

Rui Hu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2025_WACV, author = {Xu, Jiahao and Zhang, Zikai and Hu, Rui}, title = {Identify Backdoored Model in Federated Learning via Individual Unlearning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7949-7958} }
Multispectral Object Detection Enhanced by Cross-Modal Information Complementary and Cosine Similarity Channel Resampling Modules: Junbo Jang,

Chanyeong Park,

Heegwang Kim,

Jiyoon Lee,

Joonki Paik; [pdf]
[bibtex]
@InProceedings{Jang_2025_WACV, author = {Jang, Junbo and Park, Chanyeong and Kim, Heegwang and Lee, Jiyoon and Paik, Joonki}, title = {Multispectral Object Detection Enhanced by Cross-Modal Information Complementary and Cosine Similarity Channel Resampling Modules}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9419-9428} }
Robust Long-Range Perception Against Sensor Misalignment in Autonomous Vehicles: Zi-Xiang Xia,

Sudeep Fadadu,

Yi Shi,

Louis Foucard; [pdf] [arXiv]
[bibtex]
@InProceedings{Xia_2025_WACV, author = {Xia, Zi-Xiang and Fadadu, Sudeep and Shi, Yi and Foucard, Louis}, title = {Robust Long-Range Perception Against Sensor Misalignment in Autonomous Vehicles}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5761-5770} }
Anomaly Detection for People with Visual Impairments using an Egocentric 360-Degree Camera: Inpyo Song,

Sanghyeon Lee,

Minjun Joo,

Jangwon Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Song_2025_WACV, author = {Song, Inpyo and Lee, Sanghyeon and Joo, Minjun and Lee, Jangwon}, title = {Anomaly Detection for People with Visual Impairments using an Egocentric 360-Degree Camera}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2828-2837} }
TRNeRF: Restoring Blurry Rolling Shutter and Noisy Thermal Images with Neural Radiance Fields: Spencer Carmichael,

Manohar Bhat,

Mani Ramanagopal,

Austin Buchan,

Ram Vasudevan,

Katherine A. Skinner; [pdf] [supp]
[bibtex]
@InProceedings{Carmichael_2025_WACV, author = {Carmichael, Spencer and Bhat, Manohar and Ramanagopal, Mani and Buchan, Austin and Vasudevan, Ram and Skinner, Katherine A.}, title = {TRNeRF: Restoring Blurry Rolling Shutter and Noisy Thermal Images with Neural Radiance Fields}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7969-7979} }
Unsupervised Domain Adaptive Visual Question Answering in the Era of Multi-Modal Large Language Models: Weixi Weng,

Rui Zhang,

Xiaojun Meng,

Jieming Zhu,

Qun Liu,

Chun Yuan; [pdf]
[bibtex]
@InProceedings{Weng_2025_WACV, author = {Weng, Weixi and Zhang, Rui and Meng, Xiaojun and Zhu, Jieming and Liu, Qun and Yuan, Chun}, title = {Unsupervised Domain Adaptive Visual Question Answering in the Era of Multi-Modal Large Language Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6248-6258} }
PULSE: Physiological Understanding with Liquid Signal Extraction: Shahzad Ahmad,

Sania Bano,

Sachin Verma,

Yogesh Singh Rawat,

Sukalpa Chanda,

Santosh Kumar Vipparthi,

Subrahmanyam Murala; [pdf] [supp]
[bibtex]
@InProceedings{Ahmad_2025_WACV, author = {Ahmad, Shahzad and Bano, Sania and Verma, Sachin and Rawat, Yogesh Singh and Chanda, Sukalpa and Vipparthi, Santosh Kumar and Murala, Subrahmanyam}, title = {PULSE: Physiological Understanding with Liquid Signal Extraction}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4574-4584} }
On Which Data Distribution (Synthetic or Real) We Should Rely for Soft Biometric Classification: Manju R. A,

Atul Kumar,

Akshay Agarwal; [pdf]
[bibtex]
@InProceedings{A_2025_WACV, author = {A, Manju R. and Kumar, Atul and Agarwal, Akshay}, title = {On Which Data Distribution (Synthetic or Real) We Should Rely for Soft Biometric Classification}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6238-6247} }
SimuScope: Realistic Endoscopic Synthetic Dataset Generation through Surgical Simulation and Diffusion Models: Sabina Martyniak,

Joanna Kaleta,

Diego Dall'Alba,

Michał Naskręt,

Szymon Płotka,

Przemysław Korzeniowski; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Martyniak_2025_WACV, author = {Martyniak, Sabina and Kaleta, Joanna and Dall'Alba, Diego and Naskr\k{e}t, Micha{\l} and P{\l}otka, Szymon and Korzeniowski, Przemys{\l}aw}, title = {SimuScope: Realistic Endoscopic Synthetic Dataset Generation through Surgical Simulation and Diffusion Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4268-4278} }
CAMEL: Confidence-Aware Multi-Task Ensemble Learning with Spatial Information for Retina OCT Image Classification and Segmentation: Juho Jung,

Migyeong Yang,

Hyunseon Won,

Jiwon Kim,

Jeong Mo Han,

Joon Seo Hwang,

Daniel Duck-Jin Hwang,

Jinyoung Han; [pdf] [supp]
[bibtex]
@InProceedings{Jung_2025_WACV, author = {Jung, Juho and Yang, Migyeong and Won, Hyunseon and Kim, Jiwon and Han, Jeong Mo and Hwang, Joon Seo and Hwang, Daniel Duck-Jin and Han, Jinyoung}, title = {CAMEL: Confidence-Aware Multi-Task Ensemble Learning with Spatial Information for Retina OCT Image Classification and Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8929-8939} }
ERM++: An Improved Baseline for Domain Generalization: Piotr Teterwak,

Kuniaki Saito,

Theodoros Tsiligkaridis,

Kate Saenko,

Bryan Plummer; [pdf] [supp]
[bibtex]
@InProceedings{Teterwak_2025_WACV, author = {Teterwak, Piotr and Saito, Kuniaki and Tsiligkaridis, Theodoros and Saenko, Kate and Plummer, Bryan}, title = {ERM++: An Improved Baseline for Domain Generalization}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8514-8524} }
WAFFLE: Multimodal Floorplan Understanding in the Wild: Keren Ganon,

Morris Alper,

Rachel Mikulinsky,

Hadar Averbuch-Elor; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ganon_2025_WACV, author = {Ganon, Keren and Alper, Morris and Mikulinsky, Rachel and Averbuch-Elor, Hadar}, title = {WAFFLE: Multimodal Floorplan Understanding in the Wild}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1488-1497} }
Test-Time Low Rank Adaptation via Confidence Maximization for Zero-Shot Generalization of Vision-Language Models: Raza Imam,

Hanan Gani,

Muhammad Huzaifa,

Karthik Nandakumar; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Imam_2025_WACV, author = {Imam, Raza and Gani, Hanan and Huzaifa, Muhammad and Nandakumar, Karthik}, title = {Test-Time Low Rank Adaptation via Confidence Maximization for Zero-Shot Generalization of Vision-Language Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5449-5459} }
ANTHROPOS-V: Benchmarking the Novel Task of Crowd Volume Estimation: Luca Collorone,

Stefano Darrigo,

Massimiliano Pappa,

Guido M. Damely di Melendugno,

Giovanni Ficarra,

Fabio Galasso; [pdf] [supp]
[bibtex]
@InProceedings{Collorone_2025_WACV, author = {Collorone, Luca and Darrigo, Stefano and Pappa, Massimiliano and di Melendugno, Guido M. Damely and Ficarra, Giovanni and Galasso, Fabio}, title = {ANTHROPOS-V: Benchmarking the Novel Task of Crowd Volume Estimation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5284-5294} }
HybridDepth: Robust Metric Depth Fusion by Leveraging Depth from Focus and Single-Image Priors: Ashkan Ganj,

Hang Su,

Tian Guo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ganj_2025_WACV, author = {Ganj, Ashkan and Su, Hang and Guo, Tian}, title = {HybridDepth: Robust Metric Depth Fusion by Leveraging Depth from Focus and Single-Image Priors}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {973-982} }
MFTIQ: Multi-Flow Tracker with Independent Matching Quality Estimation: Jonas Serych,

Michal Neoral,

Jiri Matas; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Serych_2025_WACV, author = {Serych, Jonas and Neoral, Michal and Matas, Jiri}, title = {MFTIQ: Multi-Flow Tracker with Independent Matching Quality Estimation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8068-8078} }
VHS: High-Resolution Iterative Stereo Matching with Visual Hull Priors: Markus Plack,

Hannah Dröge,

Leif Van Holland,

Matthias B. Hullin; [pdf] [supp]
[bibtex]
@InProceedings{Plack_2025_WACV, author = {Plack, Markus and Dr\"oge, Hannah and Van Holland, Leif and Hullin, Matthias B.}, title = {VHS: High-Resolution Iterative Stereo Matching with Visual Hull Priors}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {505-514} }
A Mamba-Based Siamese Network for Remote Sensing Change Detection: Jay N. Paranjape,

Celso de Melo,

Vishal M. Patel; [pdf] [arXiv]
[bibtex]
@InProceedings{Paranjape_2025_WACV, author = {Paranjape, Jay N. and de Melo, Celso and Patel, Vishal M.}, title = {A Mamba-Based Siamese Network for Remote Sensing Change Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1186-1196} }
Language-Guided Instance-Aware Domain-Adaptive Panoptic Segmentation: Elham Amin Mansour,

Ozan Unal,

Suman Saha,

Benjamin Bejar,

Luc Van Gool; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mansour_2025_WACV, author = {Mansour, Elham Amin and Unal, Ozan and Saha, Suman and Bejar, Benjamin and Van Gool, Luc}, title = {Language-Guided Instance-Aware Domain-Adaptive Panoptic Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1637-1648} }
Bit-Flip Induced Latency Attacks in Object Detection: Manojna Sistla,

Yu Wen,

Aamir Bader Shah,

Chenpei Huang,

Lening Wang,

Xuqing Wu,

Jiefu Chen,

Miao Pan,

Xin Fu; [pdf] [supp]
[bibtex]
@InProceedings{Sistla_2025_WACV, author = {Sistla, Manojna and Wen, Yu and Shah, Aamir Bader and Huang, Chenpei and Wang, Lening and Wu, Xuqing and Chen, Jiefu and Pan, Miao and Fu, Xin}, title = {Bit-Flip Induced Latency Attacks in Object Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6709-6718} }
Foundation Models and Adaptive Feature Selection: A Synergistic Approach to Video Question Answering: Sai Bhargav Rongali,

Mohamad Hassan N C,

Ankit Jha,

Neha Bhargava,

Saurabh Prasad,

Biplab Banerjee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Rongali_2025_WACV, author = {Rongali, Sai Bhargav and C, Mohamad Hassan N and Jha, Ankit and Bhargava, Neha and Prasad, Saurabh and Banerjee, Biplab}, title = {Foundation Models and Adaptive Feature Selection: A Synergistic Approach to Video Question Answering}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9251-9261} }
LLM-RSPF: Large Language Model-Based Robotic System Planning Framework for Domain Specific Use-Cases: Chandan Kumar Singh,

Devesh Kumar,

Vipul Sanap,

Rajesh Sinha; [pdf] [supp]
[bibtex]
@InProceedings{Singh_2025_WACV, author = {Singh, Chandan Kumar and Kumar, Devesh and Sanap, Vipul and Sinha, Rajesh}, title = {LLM-RSPF: Large Language Model-Based Robotic System Planning Framework for Domain Specific Use-Cases}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7277-7286} }
MemFusionMap: Working Memory Fusion for Online Vectorized HD Map Construction: Jingyu Song,

Xudong Chen,

Liupei Lu,

Jie Li,

Katherine A. Skinner; [pdf] [arXiv]
[bibtex]
@InProceedings{Song_2025_WACV, author = {Song, Jingyu and Chen, Xudong and Lu, Liupei and Li, Jie and Skinner, Katherine A.}, title = {MemFusionMap: Working Memory Fusion for Online Vectorized HD Map Construction}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9230-9239} }
DragonTrack: Transformer-Enhanced Graphical Multi-Person Tracking in Complex Scenarios: Bishoy Galoaa,

Somaieh Amraee,

Sarah Ostadabbas; [pdf] [supp]
[bibtex]
@InProceedings{Galoaa_2025_WACV, author = {Galoaa, Bishoy and Amraee, Somaieh and Ostadabbas, Sarah}, title = {DragonTrack: Transformer-Enhanced Graphical Multi-Person Tracking in Complex Scenarios}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6373-6382} }
Improving Detail in Pluralistic Image Inpainting with Feature Dequantization: Kyungri Park,

Woohwan Jung; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Park_2025_WACV, author = {Park, Kyungri and Jung, Woohwan}, title = {Improving Detail in Pluralistic Image Inpainting with Feature Dequantization}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {680-689} }
CRAFT: Class Ranking Aware Fine-Tuning for Enhanced Out-of-Distribution Detection: Naveen Karunanayake,

Suranga Seneviratne,

Sanjay Chawla; [pdf] [supp]
[bibtex]
@InProceedings{Karunanayake_2025_WACV, author = {Karunanayake, Naveen and Seneviratne, Suranga and Chawla, Sanjay}, title = {CRAFT: Class Ranking Aware Fine-Tuning for Enhanced Out-of-Distribution Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4119-4128} }
Improving Faithfulness of Text-to-Image Diffusion Models through Inference Intervention: Danfeng Guo,

Sanchit Agarwal,

Yu-Hsiang Lin,

Jiun-Yu Kao,

Tagyoung Chung,

Nanyun Peng,

Mohit Bansal; [pdf] [supp]
[bibtex]
@InProceedings{Guo_2025_WACV, author = {Guo, Danfeng and Agarwal, Sanchit and Lin, Yu-Hsiang and Kao, Jiun-Yu and Chung, Tagyoung and Peng, Nanyun and Bansal, Mohit}, title = {Improving Faithfulness of Text-to-Image Diffusion Models through Inference Intervention}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4077-4086} }
Learning the Power of "No": Foundation Models with Negations: Jaisidh Singh,

Ishaan Shrivastava,

Mayank Vatsa,

Richa Singh,

Aparna Bharati; [pdf] [supp]
[bibtex]
@InProceedings{Singh_2025_WACV, author = {Singh, Jaisidh and Shrivastava, Ishaan and Vatsa, Mayank and Singh, Richa and Bharati, Aparna}, title = {Learning the Power of ''No'': Foundation Models with Negations}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7991-8001} }
Temporally Streaming Audio-Visual Synchronization for Real-World Videos: Jordan G Voas,

Wei-Cheng Tseng,

Layne Berry,

Xixi Hu,

Puyuan Peng,

James Stuedemann,

David Harwath; [pdf] [supp]
[bibtex]
@InProceedings{Voas_2025_WACV, author = {Voas, Jordan G and Tseng, Wei-Cheng and Berry, Layne and Hu, Xixi and Peng, Puyuan and Stuedemann, James and Harwath, David}, title = {Temporally Streaming Audio-Visual Synchronization for Real-World Videos}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5009-5017} }
SenCLIP: Enhancing Zero-Shot Land-Use Mapping for Sentinel-2 with Ground-Level Prompting: Pallavi Jain,

Dino Ienco,

Roberto Interdonato,

Tristan Berchoux,

Diego Marcos; [pdf] [supp]
[bibtex]
@InProceedings{Jain_2025_WACV, author = {Jain, Pallavi and Ienco, Dino and Interdonato, Roberto and Berchoux, Tristan and Marcos, Diego}, title = {SenCLIP: Enhancing Zero-Shot Land-Use Mapping for Sentinel-2 with Ground-Level Prompting}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5656-5665} }
ENAF: A Multi-Exit Network with an Adaptive Patch Fusion for Large Image Super Resolution: Manh Duong Nguyen,

Tuan Nghia Nguyen,

Xuan Truong Nguyen; [pdf]
[bibtex]
@InProceedings{Nguyen_2025_WACV, author = {Nguyen, Manh Duong and Nguyen, Tuan Nghia and Nguyen, Xuan Truong}, title = {ENAF: A Multi-Exit Network with an Adaptive Patch Fusion for Large Image Super Resolution}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2706-2714} }
DiffQRCoder: Diffusion-Based Aesthetic QR Code Generation with Scanning Robustness Guided Iterative Refinement: Jia-Wei Liao,

Winston Wang,

Tzu-Sian Wang,

Li-Xuan Peng,

Ju-Hsuan Weng,

Cheng-Fu Chou,

Jun-Cheng Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liao_2025_WACV, author = {Liao, Jia-Wei and Wang, Winston and Wang, Tzu-Sian and Peng, Li-Xuan and Weng, Ju-Hsuan and Chou, Cheng-Fu and Chen, Jun-Cheng}, title = {DiffQRCoder: Diffusion-Based Aesthetic QR Code Generation with Scanning Robustness Guided Iterative Refinement}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5916-5925} }
SeCo-INR: Semantically Conditioned Implicit Neural Representations for Improved Medical Image Super-Resolution: Mevan Ekanayake,

Zhifeng Chen,

Gary Egan,

Mehrtash Harandi,

Zhaolin Chen; [pdf] [supp]
[bibtex]
@InProceedings{Ekanayake_2025_WACV, author = {Ekanayake, Mevan and Chen, Zhifeng and Egan, Gary and Harandi, Mehrtash and Chen, Zhaolin}, title = {SeCo-INR: Semantically Conditioned Implicit Neural Representations for Improved Medical Image Super-Resolution}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {117-126} }
Disentangle Source and Target Knowledge for Continual Test-Time Adaptation: Tianyi Ma,

Maoying Qiao; [pdf] [supp]
[bibtex]
@InProceedings{Ma_2025_WACV, author = {Ma, Tianyi and Qiao, Maoying}, title = {Disentangle Source and Target Knowledge for Continual Test-Time Adaptation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8013-8023} }
LiLMaps: Learnable Implicit Language Maps: Evgenii Kruzhkov,

Sven Behnke; [pdf] [arXiv]
[bibtex]
@InProceedings{Kruzhkov_2025_WACV, author = {Kruzhkov, Evgenii and Behnke, Sven}, title = {LiLMaps: Learnable Implicit Language Maps}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7700-7709} }
Boosting Diffusion Guidance via Learning Degradation-Aware Models for Blind Super Resolution: Shao-Hao Lu,

Ren Wang,

Ching-Chun Huang,

Wei-Chen Chiu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lu_2025_WACV, author = {Lu, Shao-Hao and Wang, Ren and Huang, Ching-Chun and Chiu, Wei-Chen}, title = {Boosting Diffusion Guidance via Learning Degradation-Aware Models for Blind Super Resolution}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1237-1246} }
AdaPrefix++: Integrating Adapters Prefixes and Hypernetwork for Continual Learning: Sayanta Adhikari,

Dupati Srikar Chandra,

P. K. Srijith,

Pankaj Wasnik,

Naoyuki Oneo; [pdf] [supp]
[bibtex]
@InProceedings{Adhikari_2025_WACV, author = {Adhikari, Sayanta and Chandra, Dupati Srikar and Srijith, P. K. and Wasnik, Pankaj and Oneo, Naoyuki}, title = {AdaPrefix++: Integrating Adapters Prefixes and Hypernetwork for Continual Learning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7298-7307} }
Enhancing Novel Object Detection via Cooperative Foundational Models: Rohit Bharadwaj,

Muzammal Naseer,

Salman Khan,

Fahad Shahbaz Khan; [pdf] [arXiv]
[bibtex]
@InProceedings{Bharadwaj_2025_WACV, author = {Bharadwaj, Rohit and Naseer, Muzammal and Khan, Salman and Khan, Fahad Shahbaz}, title = {Enhancing Novel Object Detection via Cooperative Foundational Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9025-9034} }
Feature-Level and Spatial-Level Activation Expansion for Weakly-Supervised Semantic Segmentation: Junsu Choi,

Jin-Seop Lee,

Noo-ri Kim,

SuHyun Yoon,

Jee-Hyong Lee; [pdf] [supp]
[bibtex]
@InProceedings{Choi_2025_WACV, author = {Choi, Junsu and Lee, Jin-Seop and Kim, Noo-ri and Yoon, SuHyun and Lee, Jee-Hyong}, title = {Feature-Level and Spatial-Level Activation Expansion for Weakly-Supervised Semantic Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8701-8711} }
SpaGBOL: Spatial-Graph-Based Orientated Localisation: Tavis Shore,

Oscar Mendez,

Simon Hadfield; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shore_2025_WACV, author = {Shore, Tavis and Mendez, Oscar and Hadfield, Simon}, title = {SpaGBOL: Spatial-Graph-Based Orientated Localisation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6858-6867} }
SADA: Semantic Adversarial Unsupervised Domain Adaptation for Temporal Action Localization: David Pujol-Perich,

Albert Clapés,

Sergio Escalera; [pdf]
[bibtex]
@InProceedings{Pujol-Perich_2025_WACV, author = {Pujol-Perich, David and Clap\'es, Albert and Escalera, Sergio}, title = {SADA: Semantic Adversarial Unsupervised Domain Adaptation for Temporal Action Localization}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9219-9229} }
Autoregressive Adaptive Hypergraph Transformer for Skeleton-Based Activity Recognition: Abhisek Ray,

Ayush Raj,

Maheshkumar H. Kolekar; [pdf] [arXiv]
[bibtex]
@InProceedings{Ray_2025_WACV, author = {Ray, Abhisek and Raj, Ayush and Kolekar, Maheshkumar H.}, title = {Autoregressive Adaptive Hypergraph Transformer for Skeleton-Based Activity Recognition}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9672-9681} }
Stratified Domain Adaptation: A Progressive Self-Training Approach for Scene Text Recognition: Kha Nhat Le,

Hoang-Tuan Nguyen,

Hung Tien Tran,

Thanh Duc Ngo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Le_2025_WACV, author = {Le, Kha Nhat and Nguyen, Hoang-Tuan and Tran, Hung Tien and Ngo, Thanh Duc}, title = {Stratified Domain Adaptation: A Progressive Self-Training Approach for Scene Text Recognition}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8972-8982} }
Contrastive Sequential-Diffusion Learning: Non-Linear and Multi-Scene Instructional Video Synthesis: Vasco Ramos,

Yonatan Bitton,

Michal Yarom,

Idan Szpektor,

Joao Magalhaes; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ramos_2025_WACV, author = {Ramos, Vasco and Bitton, Yonatan and Yarom, Michal and Szpektor, Idan and Magalhaes, Joao}, title = {Contrastive Sequential-Diffusion Learning: Non-Linear and Multi-Scene Instructional Video Synthesis}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4645-4654} }
HeightLane: BEV Heightmap Guided 3D Lane Detection: Chaesong Park,

Eunbin Seo,

Jongwoo Lim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Park_2025_WACV, author = {Park, Chaesong and Seo, Eunbin and Lim, Jongwoo}, title = {HeightLane: BEV Heightmap Guided 3D Lane Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1692-1701} }
DASC-SPT: Towards Self-Supervised Panoramic Semantic Segmentation: Tianlong Tan,

Bin Chen,

Hongliang Cao,

Chenggang Yan,

Yike Ma,

Feng Dai; [pdf] [supp]
[bibtex]
@InProceedings{Tan_2025_WACV, author = {Tan, Tianlong and Chen, Bin and Cao, Hongliang and Yan, Chenggang and Ma, Yike and Dai, Feng}, title = {DASC-SPT: Towards Self-Supervised Panoramic Semantic Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8785-8794} }
Point Cloud Color Upsampling with Attention-Based Coarse Colorization and Refinement: Kohei Matsuzaki,

Keisuke Nonaka; [pdf]
[bibtex]
@InProceedings{Matsuzaki_2025_WACV, author = {Matsuzaki, Kohei and Nonaka, Keisuke}, title = {Point Cloud Color Upsampling with Attention-Based Coarse Colorization and Refinement}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {34-43} }
U-MixFormer: UNet-Like Transformer with Mix-Attention for Efficient Semantic Segmentation: Seul-Ki Yeom,

Julian von Klitzing; [pdf] [supp]
[bibtex]
@InProceedings{Yeom_2025_WACV, author = {Yeom, Seul-Ki and von Klitzing, Julian}, title = {U-MixFormer: UNet-Like Transformer with Mix-Attention for Efficient Semantic Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7710-7719} }
Efficient Progressive Image Compression with Variance-Aware Masking: Alberto Presta,

Enzo Tartaglione,

Attilio Fiandrotti,

Marco Grangetto,

Pamela Cosman; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Presta_2025_WACV, author = {Presta, Alberto and Tartaglione, Enzo and Fiandrotti, Attilio and Grangetto, Marco and Cosman, Pamela}, title = {Efficient Progressive Image Compression with Variance-Aware Masking}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7681-7689} }
SegBuilder: A Semi-Automatic Annotation Tool for Segmentation: Md Alimoor Reza,

Eric Manley,

Sean Chen,

Sameer Chaudhary,

Jacob Elafros; [pdf] [supp]
[bibtex]
@InProceedings{Reza_2025_WACV, author = {Reza, Md Alimoor and Manley, Eric and Chen, Sean and Chaudhary, Sameer and Elafros, Jacob}, title = {SegBuilder: A Semi-Automatic Annotation Tool for Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8483-8492} }
Cross-View Meets Diffusion: Aerial Image Synthesis with Geometry and Text Guidance: Ahmad Arrabi,

Xiaohan Zhang,

Waqas Sultani,

Chen Chen,

Safwan Wshah; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Arrabi_2025_WACV, author = {Arrabi, Ahmad and Zhang, Xiaohan and Sultani, Waqas and Chen, Chen and Wshah, Safwan}, title = {Cross-View Meets Diffusion: Aerial Image Synthesis with Geometry and Text Guidance}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5356-5366} }
Multi-View Factorizing and Disentangling: A Novel Framework for Incomplete Multi-View Multi-Label Classification: Wulin Xie,

Lian Zhao,

Jiang Long,

Xiaohuan Lu,

Bingyan Nie; [pdf] [arXiv]
[bibtex]
@InProceedings{Xie_2025_WACV, author = {Xie, Wulin and Zhao, Lian and Long, Jiang and Lu, Xiaohuan and Nie, Bingyan}, title = {Multi-View Factorizing and Disentangling: A Novel Framework for Incomplete Multi-View Multi-Label Classification}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1914-1923} }
UCDR-Adapter: Exploring Adaptation of Pre-Trained Vision-Language Models for Universal Cross-Domain Retrieval: Haoyu Jiang,

Zhi-Qi Cheng,

Gabriel Moreira,

Jiawen Zhu,

Jingdong Sun,

Bukun Ren,

Jun-Yan He,

Qi Dai,

Xian-Sheng Hua; [pdf]
[bibtex]
@InProceedings{Jiang_2025_WACV, author = {Jiang, Haoyu and Cheng, Zhi-Qi and Moreira, Gabriel and Zhu, Jiawen and Sun, Jingdong and Ren, Bukun and He, Jun-Yan and Dai, Qi and Hua, Xian-Sheng}, title = {UCDR-Adapter: Exploring Adaptation of Pre-Trained Vision-Language Models for Universal Cross-Domain Retrieval}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5429-5438} }
User-in-the-Loop Evaluation of Multimodal LLMs for Activity Assistance: Mrinal Verghese,

Brian Chen,

Hamid Eghbalzadeh,

Tushar Nagarajan,

Ruta P Desai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Verghese_2025_WACV, author = {Verghese, Mrinal and Chen, Brian and Eghbalzadeh, Hamid and Nagarajan, Tushar and Desai, Ruta P}, title = {User-in-the-Loop Evaluation of Multimodal LLMs for Activity Assistance}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1144-1154} }
CycleCrash: A Dataset of Bicycle Collision Videos for Collision Prediction and Analysis: Nishq Poorav Desai,

Ali Etemad,

Michael Greenspan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Desai_2025_WACV, author = {Desai, Nishq Poorav and Etemad, Ali and Greenspan, Michael}, title = {CycleCrash: A Dataset of Bicycle Collision Videos for Collision Prediction and Analysis}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6688-6698} }
3D Edge Sketch from Multiview Images: Yilin Zheng,

Chiang-Heng Chien,

Ricardo Fabbri,

Benjamin Kimia; [pdf] [supp]
[bibtex]
@InProceedings{Zheng_2025_WACV, author = {Zheng, Yilin and Chien, Chiang-Heng and Fabbri, Ricardo and Kimia, Benjamin}, title = {3D Edge Sketch from Multiview Images}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3196-3205} }
DTA: Dual Temporal-Channel-Wise Attention for Spiking Neural Networks: Minje Kim,

Minjun Kim,

Xu Yang; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2025_WACV, author = {Kim, Minje and Kim, Minjun and Yang, Xu}, title = {DTA: Dual Temporal-Channel-Wise Attention for Spiking Neural Networks}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9682-9692} }
Comparative Knowledge Distillation: Alex Tianyi Xu,

Alex Wilf,

Paul Pu Liang,

Alexander Obolenskiy,

Daniel Fried,

Louis-Philippe Morency; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2025_WACV, author = {Xu, Alex Tianyi and Wilf, Alex and Liang, Paul Pu and Obolenskiy, Alexander and Fried, Daniel and Morency, Louis-Philippe}, title = {Comparative Knowledge Distillation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7690-7699} }
Noise-Aware Evaluation of Object Detectors: Jeffri Murrugarra Llerena,

Claudio R. Jung; [pdf]
[bibtex]
@InProceedings{Llerena_2025_WACV, author = {Llerena, Jeffri Murrugarra and Jung, Claudio R.}, title = {Noise-Aware Evaluation of Object Detectors}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9304-9313} }
On the Importance of Dual-Space Augmentation for Domain Generalized Object Detection: Hayoung Park,

Choongsang Cho,

Guisik Kim; [pdf]
[bibtex]
@InProceedings{Park_2025_WACV, author = {Park, Hayoung and Cho, Choongsang and Kim, Guisik}, title = {On the Importance of Dual-Space Augmentation for Domain Generalized Object Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9408-9418} }
Learning Visual Grounding from Generative Vision and Language Model: Shijie Wang,

Dahun Kim,

Ali Taalimi,

Chen Sun,

Weicheng Kuo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2025_WACV, author = {Wang, Shijie and Kim, Dahun and Taalimi, Ali and Sun, Chen and Kuo, Weicheng}, title = {Learning Visual Grounding from Generative Vision and Language Model}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8046-8056} }
Oriented Cell Dataset: A Dataset and Benchmark for Oriented Cell Detection and Applications: Lucas Kirsten,

Angelo Angonezi,

Jose Marques,

Fernanda Oliveira,

Juliano Faccioni,

Camila Cassel,

Débora de Sousa,

Samlai Vedovatto,

Guido Lenz,

Claudio Jung; [pdf]
[bibtex]
@InProceedings{Kirsten_2025_WACV, author = {Kirsten, Lucas and Angonezi, Angelo and Marques, Jose and Oliveira, Fernanda and Faccioni, Juliano and Cassel, Camila and de Sousa, D\'ebora and Vedovatto, Samlai and Lenz, Guido and Jung, Claudio}, title = {Oriented Cell Dataset: A Dataset and Benchmark for Oriented Cell Detection and Applications}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3996-4005} }
Sigma: Siamese Mamba Network for Multi-Modal Semantic Segmentation: Zifu Wan,

Pingping Zhang,

Yuhao Wang,

Silong Yong,

Simon Stepputtis,

Katia Sycara,

Yaqi Xie; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wan_2025_WACV, author = {Wan, Zifu and Zhang, Pingping and Wang, Yuhao and Yong, Silong and Stepputtis, Simon and Sycara, Katia and Xie, Yaqi}, title = {Sigma: Siamese Mamba Network for Multi-Modal Semantic Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1734-1744} }
DocMatcher: Document Image Dewarping via Structural and Textual Line Matching: Felix Hertlein,

Alexander Naumann,

York Sure-Vetter; [pdf]
[bibtex]
@InProceedings{Hertlein_2025_WACV, author = {Hertlein, Felix and Naumann, Alexander and Sure-Vetter, York}, title = {DocMatcher: Document Image Dewarping via Structural and Textual Line Matching}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5771-5780} }
Design-o-Meter: Towards Evaluating and Refining Graphic Designs: Sahil Goyal,

Abhinav Mahajan,

Swasti Mishra,

Prateksha Udhayanan,

Tripti Shukla,

KJ Joseph,

Balaji Vasan Srinivasan; [pdf] [supp]
[bibtex]
@InProceedings{Goyal_2025_WACV, author = {Goyal, Sahil and Mahajan, Abhinav and Mishra, Swasti and Udhayanan, Prateksha and Shukla, Tripti and Joseph, KJ and Srinivasan, Balaji Vasan}, title = {Design-o-Meter: Towards Evaluating and Refining Graphic Designs}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5676-5686} }
LumiGauss: Relightable Gaussian Splatting in the Wild: Joanna Kaleta,

Kacper Kania,

Tomasz Trzcinski,

Marek Kowalski; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kaleta_2025_WACV, author = {Kaleta, Joanna and Kania, Kacper and Trzcinski, Tomasz and Kowalski, Marek}, title = {LumiGauss: Relightable Gaussian Splatting in the Wild}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1-10} }
3D Understanding of Deformable Linear Objects: Datasets and Transferability Benchmark: Bare Luka Žagar,

Mingyu Liu,

Tim Hertel,

Ekim Yurtsever,

Alois C. Knoll; [pdf] [supp]
[bibtex]
@InProceedings{Zagar_2025_WACV, author = {\v{Z}agar, Bare Luka and Liu, Mingyu and Hertel, Tim and Yurtsever, Ekim and Knoll, Alois C.}, title = {3D Understanding of Deformable Linear Objects: Datasets and Transferability Benchmark}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6404-6414} }
On Explaining Knowledge Distillation: Measuring and Visualising the Knowledge Transfer Process: Gereziher Adhane,

Mohammad Mahdi Dehshibi,

Dennis Vetter,

David Masip,

Gemma Roig; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Adhane_2025_WACV, author = {Adhane, Gereziher and Dehshibi, Mohammad Mahdi and Vetter, Dennis and Masip, David and Roig, Gemma}, title = {On Explaining Knowledge Distillation: Measuring and Visualising the Knowledge Transfer Process}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3467-3476} }
FLAIR: A Conditional Diffusion Framework with Applications to Face Video Restoration: Zihao Zou,

Jiaming Liu,

Shirin Shoushtari,

Yubo Wang,

Ulugbek S. Kamilov; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zou_2025_WACV, author = {Zou, Zihao and Liu, Jiaming and Shoushtari, Shirin and Wang, Yubo and Kamilov, Ulugbek S.}, title = {FLAIR: A Conditional Diffusion Framework with Applications to Face Video Restoration}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5228-5238} }
Texture Shape and Order Matter: A New Transformer Design for Sequential DeepFake Detection: Yunfei Li,

Yuezun Li,

Xin Wang,

Baoyuan Wu,

Jiaran Zhou,

Junyu Dong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2025_WACV, author = {Li, Yunfei and Li, Yuezun and Wang, Xin and Wu, Baoyuan and Zhou, Jiaran and Dong, Junyu}, title = {Texture Shape and Order Matter: A New Transformer Design for Sequential DeepFake Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {202-211} }
Automated Evaluation of Large Vision-Language Models on Self-Driving Corner Cases: Kai Chen,

Yanze Li,

Wenhua Zhang,

Yanxin Liu,

Pengxiang Li,

Ruiyuan Gao,

Lanqing Hong,

Meng Tian,

Xinhai Zhao,

Zhenguo Li,

Dit-Yan Yeung,

Huchuan Lu,

Xu Jia; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2025_WACV, author = {Chen, Kai and Li, Yanze and Zhang, Wenhua and Liu, Yanxin and Li, Pengxiang and Gao, Ruiyuan and Hong, Lanqing and Tian, Meng and Zhao, Xinhai and Li, Zhenguo and Yeung, Dit-Yan and Lu, Huchuan and Jia, Xu}, title = {Automated Evaluation of Large Vision-Language Models on Self-Driving Corner Cases}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7806-7815} }
Self-Supervised Pre-Training with Diffusion Model for Few-Shot Landmark Detection in X-Ray Images: Roberto Di Via,

Francesca Odone,

Vito Paolo Pastore; [pdf] [supp]
[bibtex]
@InProceedings{Di_Via_2025_WACV, author = {Di Via, Roberto and Odone, Francesca and Pastore, Vito Paolo}, title = {Self-Supervised Pre-Training with Diffusion Model for Few-Shot Landmark Detection in X-Ray Images}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3886-3896} }
A Recipe for Geometry-Aware 3D Mesh Transformers: Mohammad Farazi,

Yalin Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Farazi_2025_WACV, author = {Farazi, Mohammad and Wang, Yalin}, title = {A Recipe for Geometry-Aware 3D Mesh Transformers}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3290-3300} }
CabNIR: A Benchmark for In-Vehicle Infrared Monocular Depth Estimation: Ugo Leone Cavalcanti,

Matteo Poggi,

Fabio Tosi,

Valerio Cambareri,

Vladimir Zlokolica,

Stefano Mattoccia; [pdf] [supp]
[bibtex]
@InProceedings{Cavalcanti_2025_WACV, author = {Cavalcanti, Ugo Leone and Poggi, Matteo and Tosi, Fabio and Cambareri, Valerio and Zlokolica, Vladimir and Mattoccia, Stefano}, title = {CabNIR: A Benchmark for In-Vehicle Infrared Monocular Depth Estimation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2578-2590} }
Improving Shift Invariance in Convolutional Neural Networks with Translation Invariant Polyphase Sampling: Sourajit Saha,

Tejas Gokhale; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Saha_2025_WACV, author = {Saha, Sourajit and Gokhale, Tejas}, title = {Improving Shift Invariance in Convolutional Neural Networks with Translation Invariant Polyphase Sampling}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {620-629} }
ELMGS: Enhancing Memory and Computation Scalability through Compression for 3D Gaussian Splatting: Muhammad Salman Ali,

Sung-Ho Bae,

Enzo Tartaglione; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ali_2025_WACV, author = {Ali, Muhammad Salman and Bae, Sung-Ho and Tartaglione, Enzo}, title = {ELMGS: Enhancing Memory and Computation Scalability through Compression for 3D Gaussian Splatting}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2591-2600} }
Revisiting Disparity from Dual-Pixel Images: Physics-Informed Lightweight Depth Estimation: Teppei Kurita,

Yuhi Kondo,

Legong Sun,

Takayuki Sasaki,

Sho Nitta,

Yasuhiro Hashimoto,

Yoshinori Muramatsu,

Yusuke Moriuchi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kurita_2025_WACV, author = {Kurita, Teppei and Kondo, Yuhi and Sun, Legong and Sasaki, Takayuki and Nitta, Sho and Hashimoto, Yasuhiro and Muramatsu, Yoshinori and Moriuchi, Yusuke}, title = {Revisiting Disparity from Dual-Pixel Images: Physics-Informed Lightweight Depth Estimation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8378-8388} }
Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization: Maxime Fontana,

Michael Spratling,

Miaojing Shi; [pdf] [arXiv]
[bibtex]
@InProceedings{Fontana_2025_WACV, author = {Fontana, Maxime and Spratling, Michael and Shi, Miaojing}, title = {Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8995-9004} }
InvisMark: Invisible and Robust Watermarking for AI-Generated Image Provenance: Rui Xu,

Mengya Hu,

Deren Lei,

Yaxi Li,

David Lowe,

Alex Gorevski,

Mingyu Wang,

Emily Ching,

Alex Deng; [pdf] [arXiv]
[bibtex]
@InProceedings{Xu_2025_WACV, author = {Xu, Rui and Hu, Mengya and Lei, Deren and Li, Yaxi and Lowe, David and Gorevski, Alex and Wang, Mingyu and Ching, Emily and Deng, Alex}, title = {InvisMark: Invisible and Robust Watermarking for AI-Generated Image Provenance}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {909-918} }
PocoLoco: A Point Cloud Diffusion Model of Human Shape in Loose Clothing: Siddharth Seth,

Rishabh Dabral,

Diogo C Luvizon,

Marc Habermann,

Ming-Hsuan Yang,

Christian Theobalt,

Adam Kortylewski; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Seth_2025_WACV, author = {Seth, Siddharth and Dabral, Rishabh and Luvizon, Diogo C and Habermann, Marc and Yang, Ming-Hsuan and Theobalt, Christian and Kortylewski, Adam}, title = {PocoLoco: A Point Cloud Diffusion Model of Human Shape in Loose Clothing}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5197-5206} }
NeuManifold: Neural Watertight Manifold Reconstruction with Efficient and High-Quality Rendering Support: Xinyue Wei,

Fanbo Xiang,

Sai Bi,

Anpei Chen,

Kalyan Sunkavalli,

Zexiang Xu,

Hao Su; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wei_2025_WACV, author = {Wei, Xinyue and Xiang, Fanbo and Bi, Sai and Chen, Anpei and Sunkavalli, Kalyan and Xu, Zexiang and Su, Hao}, title = {NeuManifold: Neural Watertight Manifold Reconstruction with Efficient and High-Quality Rendering Support}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {731-741} }
Learning Visual-Semantic Hierarchical Attribute Space for Interpretable Open-Set Recognition: Zhuo Xu,

Xiang Xiang; [pdf] [supp]
[bibtex]
@InProceedings{Xu_2025_WACV, author = {Xu, Zhuo and Xiang, Xiang}, title = {Learning Visual-Semantic Hierarchical Attribute Space for Interpretable Open-Set Recognition}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5697-5706} }
Channel Propagation Networks for Refreshable Vision Transformer: Junhyeong Go,

Jongbin Ryu; [pdf] [supp]
[bibtex]
@InProceedings{Go_2025_WACV, author = {Go, Junhyeong and Ryu, Jongbin}, title = {Channel Propagation Networks for Refreshable Vision Transformer}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1353-1362} }
Swin-: Gradient-Based Image Restoration from Image Sequences using Video Swin-Transformers: Monika Kwiatkowski,

Simon Matern,

Olaf Hellwich; [pdf] [supp]
[bibtex]
@InProceedings{Kwiatkowski_2025_WACV, author = {Kwiatkowski, Monika and Matern, Simon and Hellwich, Olaf}, title = {Swin-: Gradient-Based Image Restoration from Image Sequences using Video Swin-Transformers}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1383-1391} }
Knockoff Branch: Model Stealing Attack via Adding Neurons in the Pre-Trained Model: Li-Ying Hung,

Cooper Cheng-Yuan Ku; [pdf] [supp]
[bibtex]
@InProceedings{Hung_2025_WACV, author = {Hung, Li-Ying and Ku, Cooper Cheng-Yuan}, title = {Knockoff Branch: Model Stealing Attack via Adding Neurons in the Pre-Trained Model}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7062-7070} }
CLFace: A Scalable and Resource-Efficient Continual Learning Framework for Lifelong Face Recognition: Mahedi Hasan,

Shoaib Meraj Sami,

Nasser Nasrabadi; [pdf] [arXiv]
[bibtex]
@InProceedings{Hasan_2025_WACV, author = {Hasan, Mahedi and Sami, Shoaib Meraj and Nasrabadi, Nasser}, title = {CLFace: A Scalable and Resource-Efficient Continual Learning Framework for Lifelong Face Recognition}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5082-5091} }
CardioSyntax: End-to-End SYNTAX Score Prediction - Dataset Benchmark and Method: Alexander Ponomarchuk,

Ivan Kruzhilov,

Gleb Mazanov,

Ruslan Utegenov,

Artem Shadrin,

Galina Zubkova,

Ivan Bessonov,

Pavel Blinov; [pdf]
[bibtex]
@InProceedings{Ponomarchuk_2025_WACV, author = {Ponomarchuk, Alexander and Kruzhilov, Ivan and Mazanov, Gleb and Utegenov, Ruslan and Shadrin, Artem and Zubkova, Galina and Bessonov, Ivan and Blinov, Pavel}, title = {CardioSyntax: End-to-End SYNTAX Score Prediction - Dataset Benchmark and Method}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5873-5883} }
GroundingMate: Aiding Object Grounding for Goal-Oriented Vision-and-Language Navigation: Qianyi Liu,

Siqi Zhang,

Yanyuan Qiao,

Junyou Zhu,

Xiang Li,

Longteng Guo,

Qunbo Wang,

Xingjian He,

Qi Wu,

Jing Liu; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2025_WACV, author = {Liu, Qianyi and Zhang, Siqi and Qiao, Yanyuan and Zhu, Junyou and Li, Xiang and Guo, Longteng and Wang, Qunbo and He, Xingjian and Wu, Qi and Liu, Jing}, title = {GroundingMate: Aiding Object Grounding for Goal-Oriented Vision-and-Language Navigation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1775-1784} }
AH-OCDA: Amplitude-Based Curriculum Learning and Hopfield Segmentation Model for Open Compound Domain Adaptation: Jaehyun Choi,

Junwon Ko,

Dong-Jae Lee,

Junmo Kim; [pdf] [supp]
[bibtex]
@InProceedings{Choi_2025_WACV, author = {Choi, Jaehyun and Ko, Junwon and Lee, Dong-Jae and Kim, Junmo}, title = {AH-OCDA: Amplitude-Based Curriculum Learning and Hopfield Segmentation Model for Open Compound Domain Adaptation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8269-8279} }
Image Adaptation for Colour Vision Deficient Viewers using Vision Transformers: Thomas Gillooly,

Jean-Baptiste Thomas,

Jon Y. Hardeberg,

Giuseppe Claudio Guarnera; [pdf] [supp]
[bibtex]
@InProceedings{Gillooly_2025_WACV, author = {Gillooly, Thomas and Thomas, Jean-Baptiste and Hardeberg, Jon Y. and Guarnera, Giuseppe Claudio}, title = {Image Adaptation for Colour Vision Deficient Viewers using Vision Transformers}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5646-5655} }
Pixel-Wise Shuffling with Collaborative Sparsity for Melanoma Hyperspectral Image Classification: Favour Ekong,

Jun Zhou,

Kwabena Sarpong,

Yongsheng Gao; [pdf] [supp]
[bibtex]
@InProceedings{Ekong_2025_WACV, author = {Ekong, Favour and Zhou, Jun and Sarpong, Kwabena and Gao, Yongsheng}, title = {Pixel-Wise Shuffling with Collaborative Sparsity for Melanoma Hyperspectral Image Classification}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6485-6494} }
WINE : Wavelet-Guided GAN Inversion and Editing for High-Fidelity Refinement: Chaewon Kim,

Seung Jun Moon,

Gyeong-Moon Park; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2025_WACV, author = {Kim, Chaewon and Moon, Seung Jun and Park, Gyeong-Moon}, title = {WINE : Wavelet-Guided GAN Inversion and Editing for High-Fidelity Refinement}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4523-4532} }
Multi-Spectral Image Color Reproduction: Jiacheng Li,

Chang Chen,

Xue Hu,

Fenglong Song,

Youliang Yan,

Zhiwei Xiong; [pdf] [supp]
[bibtex]
@InProceedings{Li_2025_WACV, author = {Li, Jiacheng and Chen, Chang and Hu, Xue and Song, Fenglong and Yan, Youliang and Xiong, Zhiwei}, title = {Multi-Spectral Image Color Reproduction}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8389-8398} }
Low-Frequency Black-Box Backdoor Attack via Evolutionary Algorithm: Yanqi Qiao,

Dazhuang Liu,

Rui Wang,

Kaitai Liang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Qiao_2025_WACV, author = {Qiao, Yanqi and Liu, Dazhuang and Wang, Rui and Liang, Kaitai}, title = {Low-Frequency Black-Box Backdoor Attack via Evolutionary Algorithm}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7571-7581} }
DepthSSC: Monocular 3D Semantic Scene Completion via Depth-Spatial Alignment and Voxel Adaptation: Jiawei Yao,

Jusheng Zhang,

Xiaochao Pan,

Tong Wu,

Canran Xiao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yao_2025_WACV, author = {Yao, Jiawei and Zhang, Jusheng and Pan, Xiaochao and Wu, Tong and Xiao, Canran}, title = {DepthSSC: Monocular 3D Semantic Scene Completion via Depth-Spatial Alignment and Voxel Adaptation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2154-2163} }
MDCN-PS: Monocular-Depth-Guided Coarse Normal Attention for Robust Photometric Stereo: Masahiro Yamaguchi,

Takashi Shibata,

Shoji Yachida,

Keiko Yokoyama,

Toshinori Hosoi; [pdf] [supp]
[bibtex]
@InProceedings{Yamaguchi_2025_WACV, author = {Yamaguchi, Masahiro and Shibata, Takashi and Yachida, Shoji and Yokoyama, Keiko and Hosoi, Toshinori}, title = {MDCN-PS: Monocular-Depth-Guided Coarse Normal Attention for Robust Photometric Stereo}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3342-3351} }
MONAS-ESNN: Multi-Objective Neural Architecture Search for Efficient Spiking Neural Networks: Esmat Ghasemi Saghand,

Susana K. Lai-Yuen; [pdf]
[bibtex]
@InProceedings{Saghand_2025_WACV, author = {Saghand, Esmat Ghasemi and Lai-Yuen, Susana K.}, title = {MONAS-ESNN: Multi-Objective Neural Architecture Search for Efficient Spiking Neural Networks}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9178-9187} }
SPACE: SPAtial-Aware Consistency rEgularization for Anomaly Detection in Industrial Applications: Daehwan Kim,

Hyungmin Kim,

Daun Jeong,

Sungho Suh,

Hansang Cho; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2025_WACV, author = {Kim, Daehwan and Kim, Hyungmin and Jeong, Daun and Suh, Sungho and Cho, Hansang}, title = {SPACE: SPAtial-Aware Consistency rEgularization for Anomaly Detection in Industrial Applications}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7184-7194} }
Exploring Scalability of Self-Training for Open-Vocabulary Temporal Action Localization: Jeongseok Hyun,

Su Ho Han,

Hyolim Kang,

Joon-Young Lee,

Seon Joo Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hyun_2025_WACV, author = {Hyun, Jeongseok and Han, Su Ho and Kang, Hyolim and Lee, Joon-Young and Kim, Seon Joo}, title = {Exploring Scalability of Self-Training for Open-Vocabulary Temporal Action Localization}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9388-9397} }
CISOL: An Open and Extensible Dataset for Table Structure Recognition in the Construction Industry: David Tschirschwitz,

Volker Rodehorst; [pdf] [arXiv]
[bibtex]
@InProceedings{Tschirschwitz_2025_WACV, author = {Tschirschwitz, David and Rodehorst, Volker}, title = {CISOL: An Open and Extensible Dataset for Table Structure Recognition in the Construction Industry}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7594-7602} }
NestedMorph: Enhancing Deformable Medical Image Registration with Nested Attention Mechanisms: Gurucharan Marthi Krishna Kumar,

Janine Mendola,

Amir Shmuel; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kumar_2025_WACV, author = {Kumar, Gurucharan Marthi Krishna and Mendola, Janine and Shmuel, Amir}, title = {NestedMorph: Enhancing Deformable Medical Image Registration with Nested Attention Mechanisms}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4683-4692} }
Now You See Me: Context-Aware Automatic Audio Description: Seon-Ho Lee,

Jue Wang,

David Fan,

Zhikang Zhang,

Linda Liu,

Xiang Hao,

Vimal Bhat,

Xinyu Li; [pdf] [supp]
[bibtex]
@InProceedings{Lee_2025_WACV, author = {Lee, Seon-Ho and Wang, Jue and Fan, David and Zhang, Zhikang and Liu, Linda and Hao, Xiang and Bhat, Vimal and Li, Xinyu}, title = {Now You See Me: Context-Aware Automatic Audio Description}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5530-5539} }
Geometry-Aware Deep Learning for 3D Skeleton-Based Motion Prediction: Mayssa Zaier,

Hazem Wannous,

Hassen Drira; [pdf] [supp]
[bibtex]
@InProceedings{Zaier_2025_WACV, author = {Zaier, Mayssa and Wannous, Hazem and Drira, Hassen}, title = {Geometry-Aware Deep Learning for 3D Skeleton-Based Motion Prediction}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4831-4840} }
Feature Space Perturbation: A Panacea to Enhanced Transferability Estimation: Prafful Kumar Khoba,

Zijian Wang,

Chetan Arora,

Mahsa Baktashmotlagh; [pdf] [supp]
[bibtex]
@InProceedings{Khoba_2025_WACV, author = {Khoba, Prafful Kumar and Wang, Zijian and Arora, Chetan and Baktashmotlagh, Mahsa}, title = {Feature Space Perturbation: A Panacea to Enhanced Transferability Estimation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1299-1308} }
Radiance Field-Based Pose Estimation via Decoupled Optimization Under Challenging Initial Conditions: Si-Yu Lu,

Yung-Yao Chen,

Yi-Tong Wu,

Hsin-Chun Lin,

Sin-Ye Jhong,

Wen-Huang Cheng; [pdf] [supp]
[bibtex]
@InProceedings{Lu_2025_WACV, author = {Lu, Si-Yu and Chen, Yung-Yao and Wu, Yi-Tong and Lin, Hsin-Chun and Jhong, Sin-Ye and Cheng, Wen-Huang}, title = {Radiance Field-Based Pose Estimation via Decoupled Optimization Under Challenging Initial Conditions}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2664-2673} }
DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshing: Matias Turkulainen,

Xuqian Ren,

Iaroslav Melekhov,

Otto Seiskari,

Esa Rahtu,

Juho Kannala; [pdf] [supp]
[bibtex]
@InProceedings{Turkulainen_2025_WACV, author = {Turkulainen, Matias and Ren, Xuqian and Melekhov, Iaroslav and Seiskari, Otto and Rahtu, Esa and Kannala, Juho}, title = {DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshing}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2421-2431} }
Improving Uncertainty Estimation with Confidence-Aware Training Data: Sergey Korchagin,

Ekaterina Zaychenkova,

Aleksei Khalin,

Aleksandr Yugay,

Alexey Zaytsev,

Egor Ershov; [pdf] [supp]
[bibtex]
@InProceedings{Korchagin_2025_WACV, author = {Korchagin, Sergey and Zaychenkova, Ekaterina and Khalin, Aleksei and Yugay, Aleksandr and Zaytsev, Alexey and Ershov, Egor}, title = {Improving Uncertainty Estimation with Confidence-Aware Training Data}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7980-7990} }
Sli2Vol+: Segmenting 3D Medical Images Based on an Object Estimation Guided Correspondence Flow Network: Delin An,

Pengfei Gu,

Milan Sonka,

Chaoli Wang,

Danny Z. Chen; [pdf] [supp]
[bibtex]
@InProceedings{An_2025_WACV, author = {An, Delin and Gu, Pengfei and Sonka, Milan and Wang, Chaoli and Chen, Danny Z.}, title = {Sli2Vol+: Segmenting 3D Medical Images Based on an Object Estimation Guided Correspondence Flow Network}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3624-3634} }
LIME: Localized Image Editing via Attention Regularization in Diffusion Models: Enis Simsar,

Alessio Tonioni,

Yongqin Xian,

Thomas Hofmann,

Federico Tombari; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Simsar_2025_WACV, author = {Simsar, Enis and Tonioni, Alessio and Xian, Yongqin and Hofmann, Thomas and Tombari, Federico}, title = {LIME: Localized Image Editing via Attention Regularization in Diffusion Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {222-231} }
Sifting through the Haystack - Efficiently Finding Rare Animal Behaviors in Large-Scale Datasets: Shir Bar,

Or Hirschorn,

Roi Holzman,

Shai Avidan; [pdf] [supp]
[bibtex]
@InProceedings{Bar_2025_WACV, author = {Bar, Shir and Hirschorn, Or and Holzman, Roi and Avidan, Shai}, title = {Sifting through the Haystack - Efficiently Finding Rare Animal Behaviors in Large-Scale Datasets}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6290-6299} }
DualCIR: Enhancing Training-Free Composed Image Retrieval via Dual-Directional Descriptions: Jingjiao Zhao,

Jiaju Li,

Dongze Lian,

Liguo Sun,

Pin Lv; [pdf] [supp]
[bibtex]
@InProceedings{Zhao_2025_WACV, author = {Zhao, Jingjiao and Li, Jiaju and Lian, Dongze and Sun, Liguo and Lv, Pin}, title = {DualCIR: Enhancing Training-Free Composed Image Retrieval via Dual-Directional Descriptions}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5926-5936} }
ReMP: Reusable Motion Prior for Multi-Domain 3D Human Pose Estimation and Motion Inbetweening: Hojun Jang,

Young Min Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jang_2025_WACV, author = {Jang, Hojun and Kim, Young Min}, title = {ReMP: Reusable Motion Prior for Multi-Domain 3D Human Pose Estimation and Motion Inbetweening}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2474-2483} }
Decomposed Distribution Matching in Dataset Condensation: Sahar Rahimi Malakshan,

Mohammad Saeed Ebrahimi Saadabadi,

Ali Dabouei,

Nasser Nasrabadi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Malakshan_2025_WACV, author = {Malakshan, Sahar Rahimi and Saadabadi, Mohammad Saeed Ebrahimi and Dabouei, Ali and Nasrabadi, Nasser}, title = {Decomposed Distribution Matching in Dataset Condensation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7112-7122} }
Reviving Poor Object Segmentations in OOD Medical Images using Variational-Deep-PCA Modeling on Segmentation Maps with Sampling-Free Learning: Jimut B. Pal,

Shantanu Welling,

Himali Saini,

Suyash P. Awate; [pdf]
[bibtex]
@InProceedings{Pal_2025_WACV, author = {Pal, Jimut B. and Welling, Shantanu and Saini, Himali and Awate, Suyash P.}, title = {Reviving Poor Object Segmentations in OOD Medical Images using Variational-Deep-PCA Modeling on Segmentation Maps with Sampling-Free Learning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9346-9355} }
Training-Free Medical Image Inverses via Bi-Level Guided Diffusion Models: Hossein Askari,

Fred Roosta,

Hongfu Sun; [pdf] [supp]
[bibtex]
@InProceedings{Askari_2025_WACV, author = {Askari, Hossein and Roosta, Fred and Sun, Hongfu}, title = {Training-Free Medical Image Inverses via Bi-Level Guided Diffusion Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {75-84} }
Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think: Gonzalo Martin Garcia,

Karim Abou Zeid,

Christian Schmidt,

Daan de Geus,

Alexander Hermans,

Bastian Leibe; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Garcia_2025_WACV, author = {Garcia, Gonzalo Martin and Zeid, Karim Abou and Schmidt, Christian and de Geus, Daan and Hermans, Alexander and Leibe, Bastian}, title = {Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {753-762} }
Feature Fusion Transferability Aware Transformer for Unsupervised Domain Adaptation: Xiaowei Yu,

Zhe Huang,

Zao Zhang; [pdf] [arXiv]
[bibtex]
@InProceedings{Yu_2025_WACV, author = {Yu, Xiaowei and Huang, Zhe and Zhang, Zao}, title = {Feature Fusion Transferability Aware Transformer for Unsupervised Domain Adaptation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6752-6761} }
Secrets of Edge-Informed Contrast Maximization for Event-Based Vision: Pritam P. Karmokar,

Quan H. Nguyen,

William J. Beksi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Karmokar_2025_WACV, author = {Karmokar, Pritam P. and Nguyen, Quan H. and Beksi, William J.}, title = {Secrets of Edge-Informed Contrast Maximization for Event-Based Vision}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {630-639} }
Explicit Guidance for Robust Video Frame Interpolation against Discontinuous Motions: JaeHyun Park,

Nam Ik Cho; [pdf] [supp]
[bibtex]
@InProceedings{Park_2025_WACV, author = {Park, JaeHyun and Cho, Nam Ik}, title = {Explicit Guidance for Robust Video Frame Interpolation against Discontinuous Motions}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8453-8462} }
Towards Secure and Usable 3D Assets: A Novel Framework for Automatic Visible Watermarking: Gursimran Singh,

Tianxi Hu,

Mohammad Akbari,

Qiang Tang,

Yong Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Singh_2025_WACV, author = {Singh, Gursimran and Hu, Tianxi and Akbari, Mohammad and Tang, Qiang and Zhang, Yong}, title = {Towards Secure and Usable 3D Assets: A Novel Framework for Automatic Visible Watermarking}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {721-730} }
SensorFlow: Sensor and Image Fused Video Stabilization: Jiyang Yu,

Tianhao Zhang,

Fuhao Shi,

Lei He,

Chia-Kai Liang; [pdf] [supp]
[bibtex]
@InProceedings{Yu_2025_WACV, author = {Yu, Jiyang and Zhang, Tianhao and Shi, Fuhao and He, Lei and Liang, Chia-Kai}, title = {SensorFlow: Sensor and Image Fused Video Stabilization}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8443-8452} }
TrackDiffusion: Tracklet-Conditioned Video Generation via Diffusion Models: Pengxiang Li,

Kai Chen,

Zhili Liu,

Ruiyuan Gao,

Lanqing Hong,

Dit-Yan Yeung,

Huchuan Lu,

Xu Jia; [pdf] [arXiv]
[bibtex]
@InProceedings{Li_2025_WACV, author = {Li, Pengxiang and Chen, Kai and Liu, Zhili and Gao, Ruiyuan and Hong, Lanqing and Yeung, Dit-Yan and Lu, Huchuan and Jia, Xu}, title = {TrackDiffusion: Tracklet-Conditioned Video Generation via Diffusion Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3539-3548} }
Can Adversarial Examples Be Parsed to Reveal Victim Model Information?: Yuguang Yao,

Jiancheng Liu,

Yifan Gong,

Xiaoming Liu,

Yanzhi Wang,

Xue Lin,

Sijia Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yao_2025_WACV, author = {Yao, Yuguang and Liu, Jiancheng and Gong, Yifan and Liu, Xiaoming and Wang, Yanzhi and Lin, Xue and Liu, Sijia}, title = {Can Adversarial Examples Be Parsed to Reveal Victim Model Information?}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7049-7061} }
Aerial Mirage: Unmasking Hallucinations in Large Vision Language Models: Debolena Basak,

Soham Bhatt,

Sahith Kanduri,

Maunendra Sankar Desarkar; [pdf] [supp]
[bibtex]
@InProceedings{Basak_2025_WACV, author = {Basak, Debolena and Bhatt, Soham and Kanduri, Sahith and Desarkar, Maunendra Sankar}, title = {Aerial Mirage: Unmasking Hallucinations in Large Vision Language Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5500-5508} }
Global-Guided Focal Neural Radiance Field for Large-Scale Scene Rendering: Mingqi Shao,

Feng Xiong,

Hang Zhang,

Shuang Yang,

Mu Xu,

Wei Bian,

Xueqian Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shao_2025_WACV, author = {Shao, Mingqi and Xiong, Feng and Zhang, Hang and Yang, Shuang and Xu, Mu and Bian, Wei and Wang, Xueqian}, title = {Global-Guided Focal Neural Radiance Field for Large-Scale Scene Rendering}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2558-2567} }
SAND: Enhancing Open-Set Neuron Descriptions through Spatial Awareness: Anvita Agarwal Srinivas,

Tuomas Oikarinen,

Divyansh Srivastava,

Wei-Hung Weng,

Tsui-Wei Weng; [pdf] [supp]
[bibtex]
@InProceedings{Srinivas_2025_WACV, author = {Srinivas, Anvita Agarwal and Oikarinen, Tuomas and Srivastava, Divyansh and Weng, Wei-Hung and Weng, Tsui-Wei}, title = {SAND: Enhancing Open-Set Neuron Descriptions through Spatial Awareness}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2993-3002} }
When Visual State Space Model Meets Backdoor Attacks: Sankalp Nagaonkar,

Achyut Mani Tripathi,

Ashish Mishra; [pdf] [supp]
[bibtex]
@InProceedings{Nagaonkar_2025_WACV, author = {Nagaonkar, Sankalp and Tripathi, Achyut Mani and Mishra, Ashish}, title = {When Visual State Space Model Meets Backdoor Attacks}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7419-7428} }
ARF-Plus: Controlling Perceptual Factors in Artistic Radiance Fields for 3D Scene Stylization: Wenzhao Li,

Tianhao Wu,

Fangcheng Zhong,

A. Cengiz Oztireli; [pdf] [supp]
[bibtex]
@InProceedings{Li_2025_WACV, author = {Li, Wenzhao and Wu, Tianhao and Zhong, Fangcheng and Oztireli, A. Cengiz}, title = {ARF-Plus: Controlling Perceptual Factors in Artistic Radiance Fields for 3D Scene Stylization}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2301-2310} }
Token Turing Machines are Efficient Vision Models: Purvish Jajal,

Nick Eliopoulous,

Benjamin Shiue-Hal Chou,

George K. Thiravathukal,

James C. Davis,

Yung-Hsiang Lu; [pdf] [supp]
[bibtex]
@InProceedings{Jajal_2025_WACV, author = {Jajal, Purvish and Eliopoulous, Nick and Chou, Benjamin Shiue-Hal and Thiravathukal, George K. and Davis, James C. and Lu, Yung-Hsiang}, title = {Token Turing Machines are Efficient Vision Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7887-7896} }
ReBotNet: Fast Real-Time Video Enhancement: Jeya Maria Jose Valanarasu,

Rahul Garg,

Andeep Toor,

Xin Tong,

Weijuan Xi,

Andreas Lugmayr,

Vishal M. Patel,

Anne Menini; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Valanarasu_2025_WACV, author = {Valanarasu, Jeya Maria Jose and Garg, Rahul and Toor, Andeep and Tong, Xin and Xi, Weijuan and Lugmayr, Andreas and Patel, Vishal M. and Menini, Anne}, title = {ReBotNet: Fast Real-Time Video Enhancement}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1424-1435} }
UniTMGE: Uniform Text-Motion Generation and Editing Model via Diffusion: Ruoyu Wang,

Yangfan He,

Tengjiao Sun,

Xiang Li,

Tianyu Shi; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2025_WACV, author = {Wang, Ruoyu and He, Yangfan and Sun, Tengjiao and Li, Xiang and Shi, Tianyu}, title = {UniTMGE: Uniform Text-Motion Generation and Editing Model via Diffusion}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6104-6114} }
Uncertainty-Aware Online Extrinsic Calibration: A Conformal Prediction Approach: Mathieu Cocheteux,

Julien Moreau,

Franck Davoine; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cocheteux_2025_WACV, author = {Cocheteux, Mathieu and Moreau, Julien and Davoine, Franck}, title = {Uncertainty-Aware Online Extrinsic Calibration: A Conformal Prediction Approach}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6167-6176} }
Pay Attention to Your Neighbours: Training-Free Open-Vocabulary Semantic Segmentation: Sina Hajimiri,

Ismail Ben Ayed,

Jose Dolz; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hajimiri_2025_WACV, author = {Hajimiri, Sina and Ben Ayed, Ismail and Dolz, Jose}, title = {Pay Attention to Your Neighbours: Training-Free Open-Vocabulary Semantic Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5061-5071} }
Facial Expression Recognition with Controlled Privacy Preservation and Feature Compensation: Feng Xu,

David Ahmedt-Aristizabal,

Lars Petersson,

Dadong Wang,

Xun Li; [pdf] [arXiv]
[bibtex]
@InProceedings{Xu_2025_WACV, author = {Xu, Feng and Ahmedt-Aristizabal, David and Petersson, Lars and Wang, Dadong and Li, Xun}, title = {Facial Expression Recognition with Controlled Privacy Preservation and Feature Compensation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2611-2621} }
Learning to Identify Seen Unseen and Unknown in the Open World: A Practical Setting for Zero-Shot Learning: Sethupathy Parameswaran,

Yuan Fang,

Chandan Gautam,

Savitha Ramasamy,

Xiaoli Li; [pdf] [supp]
[bibtex]
@InProceedings{Parameswaran_2025_WACV, author = {Parameswaran, Sethupathy and Fang, Yuan and Gautam, Chandan and Ramasamy, Savitha and Li, Xiaoli}, title = {Learning to Identify Seen Unseen and Unknown in the Open World: A Practical Setting for Zero-Shot Learning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6868-6878} }
Multi-Aperture Transformers for 3D (MAT3D) Segmentation of Clinical and Microscopic Images: Muhammad Sohaib,

Siyavash Shabani,

Sahar A. Mohammed,

Garrett Winkelmaier,

Bahram Parvin; [pdf] [supp]
[bibtex]
@InProceedings{Sohaib_2025_WACV, author = {Sohaib, Muhammad and Shabani, Siyavash and Mohammed, Sahar A. and Winkelmaier, Garrett and Parvin, Bahram}, title = {Multi-Aperture Transformers for 3D (MAT3D) Segmentation of Clinical and Microscopic Images}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4352-4361} }
Harmonizing Attention: Training-Free Texture-Aware Geometry Transfer: Eito Ikuta,

Yohan Lee,

Akihiro Iohara,

Yu Saito,

Toshiyuki Tanaka; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ikuta_2025_WACV, author = {Ikuta, Eito and Lee, Yohan and Iohara, Akihiro and Saito, Yu and Tanaka, Toshiyuki}, title = {Harmonizing Attention: Training-Free Texture-Aware Geometry Transfer}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2042-2051} }
Towards Generalized Face Anti-Spoofing from a Frequency Shortcut View: Junyi Cao,

Chao Ma; [pdf] [supp]
[bibtex]
@InProceedings{Cao_2025_WACV, author = {Cao, Junyi and Ma, Chao}, title = {Towards Generalized Face Anti-Spoofing from a Frequency Shortcut View}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1005-1015} }
PatchFinder: Leveraging Visual Language Models for Accurate Information Retrieval using Model Uncertainty: Roman Colman,

Minh Vu,

Manish Bhattarai,

Martin Ma,

Hari Viswanathan,

Daniel O'Malley,

Javier Santos; [pdf] [arXiv]
[bibtex]
@InProceedings{Colman_2025_WACV, author = {Colman, Roman and Vu, Minh and Bhattarai, Manish and Ma, Martin and Viswanathan, Hari and O'Malley, Daniel and Santos, Javier}, title = {PatchFinder: Leveraging Visual Language Models for Accurate Information Retrieval using Model Uncertainty}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9128-9137} }
DiTAS: Quantizing Diffusion Transformers via Enhanced Activation Smoothing: Zhenyuan Dong,

Sai Qian Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dong_2025_WACV, author = {Dong, Zhenyuan and Zhang, Sai Qian}, title = {DiTAS: Quantizing Diffusion Transformers via Enhanced Activation Smoothing}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4606-4615} }
Improving Conditional Diffusion Models through Re-Noising from Unconditional Diffusion Priors: Kangfu Mei,

Nithin Gopalakrishnan Nair,

Vishal Patel; [pdf]
[bibtex]
@InProceedings{Mei_2025_WACV, author = {Mei, Kangfu and Nair, Nithin Gopalakrishnan and Patel, Vishal}, title = {Improving Conditional Diffusion Models through Re-Noising from Unconditional Diffusion Priors}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3792-3801} }
SANPO: A Scene Understanding Accessibility and Human Navigation Dataset: Sagar M. Waghmare,

Kimberly Wilber,

Dave Hawkey,

Xuan Yang,

Matthew Wilson,

Stephanie Debats,

Cattalyya Nuengsigkapian,

Astuti Sharma,

Lars Pandikow,

Huisheng Wang,

Hartwig Adam,

Mikhail Sirotenko; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Waghmare_2025_WACV, author = {Waghmare, Sagar M. and Wilber, Kimberly and Hawkey, Dave and Yang, Xuan and Wilson, Matthew and Debats, Stephanie and Nuengsigkapian, Cattalyya and Sharma, Astuti and Pandikow, Lars and Wang, Huisheng and Adam, Hartwig and Sirotenko, Mikhail}, title = {SANPO: A Scene Understanding Accessibility and Human Navigation Dataset}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7855-7864} }
SmartKC++: Improving Performance of Smartphone-Based Corneal Topographers: Vaibhav Ganatra,

Siddhartha Gairola,

Pallavi Joshi,

Anand Balasubramaniam,

Kaushik Murali,

Arivunithi Varadharajan,

Bellamkonda Mallikarjuna,

Nipun Kwatra,

Mohit Jain; [pdf] [supp]
[bibtex]
@InProceedings{Ganatra_2025_WACV, author = {Ganatra, Vaibhav and Gairola, Siddhartha and Joshi, Pallavi and Balasubramaniam, Anand and Murali, Kaushik and Varadharajan, Arivunithi and Mallikarjuna, Bellamkonda and Kwatra, Nipun and Jain, Mohit}, title = {SmartKC++: Improving Performance of Smartphone-Based Corneal Topographers}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4392-4399} }
Partial Texture VAE: Color and Texture Encoder for Rock Particle Images: Tetsushi Yamada,

Simone Di Santo; [pdf] [supp]
[bibtex]
@InProceedings{Yamada_2025_WACV, author = {Yamada, Tetsushi and Di Santo, Simone}, title = {Partial Texture VAE: Color and Texture Encoder for Rock Particle Images}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4999-5008} }
Learning Keypoints for Multi-Agent Behavior Analysis using Self-Supervision: Daniel Khalil,

Christina Liu,

Pietro Perona,

Jennifer Sun,

Markus Marks; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Khalil_2025_WACV, author = {Khalil, Daniel and Liu, Christina and Perona, Pietro and Sun, Jennifer and Marks, Markus}, title = {Learning Keypoints for Multi-Agent Behavior Analysis using Self-Supervision}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {578-588} }
GaitContour: Efficient Gait Recognition Based on a Contour-Pose Representation: Yuxiang Guo,

Anshul Shah,

Jiang Liu,

Ayush Gupta,

Rama Chellappa,

Cheng Peng; [pdf] [arXiv]
[bibtex]
@InProceedings{Guo_2025_WACV, author = {Guo, Yuxiang and Shah, Anshul and Liu, Jiang and Gupta, Ayush and Chellappa, Rama and Peng, Cheng}, title = {GaitContour: Efficient Gait Recognition Based on a Contour-Pose Representation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1051-1061} }
LIPIDS: Learning-Based Illumination Planning in Discretized (Light) Space for Photometric Stereo: Ashish Tiwari,

Mihirkumar Sutariya,

Shanmuganathan Raman; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tiwari_2025_WACV, author = {Tiwari, Ashish and Sutariya, Mihirkumar and Raman, Shanmuganathan}, title = {LIPIDS: Learning-Based Illumination Planning in Discretized (Light) Space for Photometric Stereo}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {650-659} }
Multi-View Image Diffusion via Coordinate Noise and Fourier Attention: Justin Theiss,

Norman Müller,

Daeil Kim,

Aayush Prakash; [pdf] [supp]
[bibtex]
@InProceedings{Theiss_2025_WACV, author = {Theiss, Justin and M\"uller, Norman and Kim, Daeil and Prakash, Aayush}, title = {Multi-View Image Diffusion via Coordinate Noise and Fourier Attention}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4310-4319} }
Tumor Synthesis Conditioned on Radiomics: Jonghun Kim,

Inye Na,

Eun Sook Ko,

Hyunjin Park; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2025_WACV, author = {Kim, Jonghun and Na, Inye and Ko, Eun Sook and Park, Hyunjin}, title = {Tumor Synthesis Conditioned on Radiomics}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3635-3646} }
PTQ4VM: Post-Training Quantization for Visual Mamba: Younghyun Cho,

Changhun Lee,

Seonggon Kim,

Eunhyeok Park; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cho_2025_WACV, author = {Cho, Younghyun and Lee, Changhun and Kim, Seonggon and Park, Eunhyeok}, title = {PTQ4VM: Post-Training Quantization for Visual Mamba}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1176-1185} }
AIDE: Improving 3D Open-Vocabulary Semantic Segmentation by Aligned Vision-Language Learning: Yimu Wang,

Krzysztof Czarnecki; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2025_WACV, author = {Wang, Yimu and Czarnecki, Krzysztof}, title = {AIDE: Improving 3D Open-Vocabulary Semantic Segmentation by Aligned Vision-Language Learning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2674-2685} }
Recurrence-Based Vanishing Point Detection: Skanda Bharadwaj,

Robert T. Collins,

Yanxi Liu; [pdf] [arXiv]
[bibtex]
@InProceedings{Bharadwaj_2025_WACV, author = {Bharadwaj, Skanda and Collins, Robert T. and Liu, Yanxi}, title = {Recurrence-Based Vanishing Point Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8909-8918} }
AMP-ViT: Optimizing Vision Transformer Efficiency with Adaptive Mixed-Precision Post-Training Quantization: Yu-Shan Tai,

An-Yeu Wu; [pdf] [supp]
[bibtex]
@InProceedings{Tai_2025_WACV, author = {Tai, Yu-Shan and Wu, An-Yeu}, title = {AMP-ViT: Optimizing Vision Transformer Efficiency with Adaptive Mixed-Precision Post-Training Quantization}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6828-6837} }
Delta-NAS: Difference of Architecture Encoding for Predictor-Based Evolutionary Neural Architecture Search: Arjun Sridhar,

Yiran Chen; [pdf]
[bibtex]
@InProceedings{Sridhar_2025_WACV, author = {Sridhar, Arjun and Chen, Yiran}, title = {Delta-NAS: Difference of Architecture Encoding for Predictor-Based Evolutionary Neural Architecture Search}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7846-7854} }
VLTP: Vision-Language Guided Token Pruning for Task-Oriented Segmentation: Hanning Chen,

Yang Ni,

Wenjun Huang,

Yezi Liu,

SungHeon Jeong,

Fei Wen,

Nathaniel Bastian,

Hugo Latapie,

Mohsen Imani; [pdf] [arXiv]
[bibtex]
@InProceedings{Chen_2025_WACV, author = {Chen, Hanning and Ni, Yang and Huang, Wenjun and Liu, Yezi and Jeong, SungHeon and Wen, Fei and Bastian, Nathaniel and Latapie, Hugo and Imani, Mohsen}, title = {VLTP: Vision-Language Guided Token Pruning for Task-Oriented Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9335-9345} }
Achieving Byzantine-Resilient Federated Learning via Layer-Adaptive Sparsified Model Aggregation: Jiahao Xu,

Zikai Zhang,

Rui Hu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2025_WACV, author = {Xu, Jiahao and Zhang, Zikai and Hu, Rui}, title = {Achieving Byzantine-Resilient Federated Learning via Layer-Adaptive Sparsified Model Aggregation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1508-1517} }
Disentangling Spatio-Temporal Knowledge for Weakly Supervised Object Detection and Segmentation in Surgical Video: Guiqiu Liao,

Matjaz Jogan,

Sai Koushik,

Eric Eaton,

Daniel A. Hashimoto; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liao_2025_WACV, author = {Liao, Guiqiu and Jogan, Matjaz and Koushik, Sai and Eaton, Eric and Hashimoto, Daniel A.}, title = {Disentangling Spatio-Temporal Knowledge for Weakly Supervised Object Detection and Segmentation in Surgical Video}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8002-8012} }
Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understanding: Lingdong Kong,

Xiang Xu,

Jun Cen,

Wenwei Zhang,

Liang Pan,

Kai Chen,

Ziwei Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kong_2025_WACV, author = {Kong, Lingdong and Xu, Xiang and Cen, Jun and Zhang, Wenwei and Pan, Liang and Chen, Kai and Liu, Ziwei}, title = {Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understanding}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1965-1978} }
TACLE: Task and Class-Aware Exemplar-Free Semi-Supervised Class Incremental Learning: Jayateja Kalla,

Rohit Kumar,

Soma Biswas; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kalla_2025_WACV, author = {Kalla, Jayateja and Kumar, Rohit and Biswas, Soma}, title = {TACLE: Task and Class-Aware Exemplar-Free Semi-Supervised Class Incremental Learning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6944-6954} }
Background-Aware Moment Detection for Video Moment Retrieval: Minjoon Jung,

Youwon Jang,

Seongho Choi,

Joochan Kim,

Jin-Hwa Kim,

Byoung-Tak Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jung_2025_WACV, author = {Jung, Minjoon and Jang, Youwon and Choi, Seongho and Kim, Joochan and Kim, Jin-Hwa and Zhang, Byoung-Tak}, title = {Background-Aware Moment Detection for Video Moment Retrieval}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8575-8585} }
MFNeRF: Memory Efficient NeRF with Mixed-Feature Hash Table: Yongjae Lee,

Li Yang,

Deliang Fan; [pdf] [supp]
[bibtex]
@InProceedings{Lee_2025_WACV, author = {Lee, Yongjae and Yang, Li and Fan, Deliang}, title = {MFNeRF: Memory Efficient NeRF with Mixed-Feature Hash Table}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2686-2695} }
PETALface: Parameter Efficient Transfer Learning for Low-Resolution Face Recognition: Kartik Narayan,

Nithin Gopalakrishnan Nair,

Jennifer Xu,

Rama Chellappa,

Vishal M. Patel; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Narayan_2025_WACV, author = {Narayan, Kartik and Nair, Nithin Gopalakrishnan and Xu, Jennifer and Chellappa, Rama and Patel, Vishal M.}, title = {PETALface: Parameter Efficient Transfer Learning for Low-Resolution Face Recognition}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {804-814} }
MissionGNN: Hierarchical Multimodal GNN-Based Weakly Supervised Video Anomaly Recognition with Mission-Specific Knowledge Graph Generation: Sanggeon Yun,

Ryozo Masukawa,

Minhyoung Na,

Mohsen Imani; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yun_2025_WACV, author = {Yun, Sanggeon and Masukawa, Ryozo and Na, Minhyoung and Imani, Mohsen}, title = {MissionGNN: Hierarchical Multimodal GNN-Based Weakly Supervised Video Anomaly Recognition with Mission-Specific Knowledge Graph Generation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4736-4745} }
Cascaded Dual Vision Transformer for Accurate Facial Landmark Detection: Ziqiang Dang,

Jianfang Li,

Lin Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dang_2025_WACV, author = {Dang, Ziqiang and Li, Jianfang and Liu, Lin}, title = {Cascaded Dual Vision Transformer for Accurate Facial Landmark Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5884-5894} }
QuantAttack: Exploiting Quantization Techniques to Attack Vision Transformers: Amit Baras,

Alon Zolfi,

Yuval Elovici,

Asaf Shabtai; [pdf] [supp]
[bibtex]
@InProceedings{Baras_2025_WACV, author = {Baras, Amit and Zolfi, Alon and Elovici, Yuval and Shabtai, Asaf}, title = {QuantAttack: Exploiting Quantization Techniques to Attack Vision Transformers}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6730-6740} }
RendBEV: Semantic Novel View Synthesis for Self-Supervised Bird's Eye View Segmentation: Henrique Piñeiro Monteagudo,

Leonardo Taccari,

Aurel Pjetri,

Francesco Sambo,

Samuele Salti; [pdf] [supp]
[bibtex]
@InProceedings{Monteagudo_2025_WACV, author = {Monteagudo, Henrique Pi\~neiro and Taccari, Leonardo and Pjetri, Aurel and Sambo, Francesco and Salti, Samuele}, title = {RendBEV: Semantic Novel View Synthesis for Self-Supervised Bird's Eye View Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {535-544} }
NeuroViG - Integrating Event Cameras for Resource-Efficient Video Grounding: Dulanga Weerakoon,

Vigneshwaran Subbaraju,

Joo Hwee Lim,

Archan Misra; [pdf]
[bibtex]
@InProceedings{Weerakoon_2025_WACV, author = {Weerakoon, Dulanga and Subbaraju, Vigneshwaran and Lim, Joo Hwee and Misra, Archan}, title = {NeuroViG - Integrating Event Cameras for Resource-Efficient Video Grounding}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5781-5790} }
Aggregated Attributions for Explanatory Analysis of 3D Segmentation Models: Maciej Chrabaszcz,

Hubert Baniecki,

Piotr Komorowski,

Szymon Plotka,

Przemyslaw Biecek; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chrabaszcz_2025_WACV, author = {Chrabaszcz, Maciej and Baniecki, Hubert and Komorowski, Piotr and Plotka, Szymon and Biecek, Przemyslaw}, title = {Aggregated Attributions for Explanatory Analysis of 3D Segmentation Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {160-171} }
GANESH: Generalizable NeRF for Lensless Imaging: Rakesh Raj Madhavan,

Akshat Kaimal,

Badhrinarayanan K.V,

Vinayak Gupta,

Rohit Choudhary,

Chandrakala Shanmuganathan,

Kaushik Mitra; [pdf]
[bibtex]
@InProceedings{Madhavan_2025_WACV, author = {Madhavan, Rakesh Raj and Kaimal, Akshat and K.V, Badhrinarayanan and Gupta, Vinayak and Choudhary, Rohit and Shanmuganathan, Chandrakala and Mitra, Kaushik}, title = {GANESH: Generalizable NeRF for Lensless Imaging}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9481-9490} }
Looking at Model Debiasing through the Lens of Anomaly Detection: Vito Paolo Pastore,

Massimiliano Ciranni,

Davide Marinelli,

Francesca Odone,

Vittorio Murino; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pastore_2025_WACV, author = {Pastore, Vito Paolo and Ciranni, Massimiliano and Marinelli, Davide and Odone, Francesca and Murino, Vittorio}, title = {Looking at Model Debiasing through the Lens of Anomaly Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2548-2557} }
On Neural BRDFs: A Thorough Comparison of State-of-the-Art Approaches: Florian Hofherr,

Bjoern Haefner,

Daniel Cremers; [pdf] [supp]
[bibtex]
@InProceedings{Hofherr_2025_WACV, author = {Hofherr, Florian and Haefner, Bjoern and Cremers, Daniel}, title = {On Neural BRDFs: A Thorough Comparison of State-of-the-Art Approaches}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1785-1794} }
Focusing on What to Decode and What to Train: SOV Decoding with Specific Target Guided DeNoising and Vision Language Advisor: Junwen Chen,

Yingcheng Wang,

Keiji Yanai; [pdf] [arXiv]
[bibtex]
@InProceedings{Chen_2025_WACV, author = {Chen, Junwen and Wang, Yingcheng and Yanai, Keiji}, title = {Focusing on What to Decode and What to Train: SOV Decoding with Specific Target Guided DeNoising and Vision Language Advisor}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9398-9407} }
Efficient Video Object Segmentation via Modulated Cross-Attention Memory: Abdelrahman Shaker,

Syed Talal Wasim,

Martin Danelljan,

Salman Khan,

Ming-Hsuan Yang,

Fahad Shahbaz Khan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shaker_2025_WACV, author = {Shaker, Abdelrahman and Wasim, Syed Talal and Danelljan, Martin and Khan, Salman and Yang, Ming-Hsuan and Khan, Fahad Shahbaz}, title = {Efficient Video Object Segmentation via Modulated Cross-Attention Memory}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8670-8679} }
OpenCity3D: What do Vision-Language Models Know About Urban Environments?: Valentin Bieri,

Marco Zamboni,

Nicolas Samuel Blumer,

Qingxuan Chen,

Francis Engelmann; [pdf] [supp]
[bibtex]
@InProceedings{Bieri_2025_WACV, author = {Bieri, Valentin and Zamboni, Marco and Blumer, Nicolas Samuel and Chen, Qingxuan and Engelmann, Francis}, title = {OpenCity3D: What do Vision-Language Models Know About Urban Environments?}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5147-5155} }
NPL-MVPS: Neural Point-Light Multi-View Photometric Stereo: Fotios Logothetis,

Ignas Budvytis,

Roberto Cipolla; [pdf] [supp]
[bibtex]
@InProceedings{Logothetis_2025_WACV, author = {Logothetis, Fotios and Budvytis, Ignas and Cipolla, Roberto}, title = {NPL-MVPS: Neural Point-Light Multi-View Photometric Stereo}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2291-2300} }
RAW-Diffusion: RGB-Guided Diffusion Models for High-Fidelity RAW Image Generation: Christoph Reinders,

Radu Berdan,

Beril Besbinar,

Junji Otsuka,

Daisuke Iso; [pdf] [supp]
[bibtex]
@InProceedings{Reinders_2025_WACV, author = {Reinders, Christoph and Berdan, Radu and Besbinar, Beril and Otsuka, Junji and Iso, Daisuke}, title = {RAW-Diffusion: RGB-Guided Diffusion Models for High-Fidelity RAW Image Generation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8420-8432} }
Uncertainty-Guided Metric Learning without Labels: Dhanunjaya Varma Devalraju,

C Chandra Sekhar; [pdf] [supp]
[bibtex]
@InProceedings{Devalraju_2025_WACV, author = {Devalraju, Dhanunjaya Varma and Sekhar, C Chandra}, title = {Uncertainty-Guided Metric Learning without Labels}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7029-7038} }
TaxaBind: A Unified Embedding Space for Ecological Applications: Srikumar Sastry,

Subash Khanal,

Aayush Dhakal,

Adeel Ahmad,

Nathan Jacobs; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sastry_2025_WACV, author = {Sastry, Srikumar and Khanal, Subash and Dhakal, Aayush and Ahmad, Adeel and Jacobs, Nathan}, title = {TaxaBind: A Unified Embedding Space for Ecological Applications}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1765-1774} }
MetaVIn: Meteorological and Visual Integration for Atmospheric Turbulence Strength Estimation: Ripon Kumar Saha,

Scott McCloskey,

Suren Jayasuriya; [pdf] [supp]
[bibtex]
@InProceedings{Saha_2025_WACV, author = {Saha, Ripon Kumar and McCloskey, Scott and Jayasuriya, Suren}, title = {MetaVIn: Meteorological and Visual Integration for Atmospheric Turbulence Strength Estimation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8565-8574} }
A Versatile and Differentiable Hand-Object Interaction Representation: Théo Morales,

Omid Taheri,

Gerard Lacey; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Morales_2025_WACV, author = {Morales, Th\'eo and Taheri, Omid and Lacey, Gerard}, title = {A Versatile and Differentiable Hand-Object Interaction Representation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {23-33} }
Data Augmentation for Image Classification using Generative AI: Fazle Rahat,

M Shifat Hossain,

Md Rubel Ahmed,

Sumit Kumar Jha,

Rickard Ewetz; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Rahat_2025_WACV, author = {Rahat, Fazle and Hossain, M Shifat and Ahmed, Md Rubel and Jha, Sumit Kumar and Ewetz, Rickard}, title = {Data Augmentation for Image Classification using Generative AI}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4173-4182} }
EchoDFKD: Data-Free Knowledge Distillation for Cardiac Ultrasound Segmentation using Synthetic Data: Grégoire Petit,

Nathan Palluau,

Axel Bauer,

Clemens Dlaska; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Petit_2025_WACV, author = {Petit, Gr\'egoire and Palluau, Nathan and Bauer, Axel and Dlaska, Clemens}, title = {EchoDFKD: Data-Free Knowledge Distillation for Cardiac Ultrasound Segmentation using Synthetic Data}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8504-8513} }
Latency Robust Cooperative Perception using Asynchronous Feature Fusion: Junjie Wang,

Tomas Nordström; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2025_WACV, author = {Wang, Junjie and Nordstr\"om, Tomas}, title = {Latency Robust Cooperative Perception using Asynchronous Feature Fusion}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4862-4871} }
DSTR: Dual Scenes Transformer for Cross-Modal Fusion in 3D Object Detection: Haojie Cai,

Dongfu Yin,

Fei Richard Yu,

Siting Xiong; [pdf]
[bibtex]
@InProceedings{Cai_2025_WACV, author = {Cai, Haojie and Yin, Dongfu and Yu, Fei Richard and Xiong, Siting}, title = {DSTR: Dual Scenes Transformer for Cross-Modal Fusion in 3D Object Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3064-3073} }
SAM-DA: Decoder Adapter for Efficient Medical Domain Adaptation: Javier Gamazo Tejero,

Moritz J Schmid,

Pablo Márquez Neila,

Martin Zinkernagel,

Sebastian Wolf,

Raphael Sznitman; [pdf] [supp]
[bibtex]
@InProceedings{Tejero_2025_WACV, author = {Tejero, Javier Gamazo and Schmid, Moritz J and Neila, Pablo M\'arquez and Zinkernagel, Martin and Wolf, Sebastian and Sznitman, Raphael}, title = {SAM-DA: Decoder Adapter for Efficient Medical Domain Adaptation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6775-6784} }
Social EgoMesh Estimation: Luca Scofano,

Alessio Sampieri,

Edoardo De Matteis,

Indro Spinelli,

Fabio Galasso; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Scofano_2025_WACV, author = {Scofano, Luca and Sampieri, Alessio and De Matteis, Edoardo and Spinelli, Indro and Galasso, Fabio}, title = {Social EgoMesh Estimation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5948-5958} }
Localized Gaussian Splatting Editing with Contextual Awareness: Hanyuan Xiao,

Yingshu Chen,

Huajian Huang,

Haolin Xiong,

Jing Yang,

Pratusha Prasad,

Yajie Zhao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xiao_2025_WACV, author = {Xiao, Hanyuan and Chen, Yingshu and Huang, Huajian and Xiong, Haolin and Yang, Jing and Prasad, Pratusha and Zhao, Yajie}, title = {Localized Gaussian Splatting Editing with Contextual Awareness}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5207-5217} }
S3PT: Scene Semantics and Structure Guided Clustering to Boost Self-Supervised Pre-Training for Autonomous Driving: Maciej K. Wozniak,

Hariprasath Govindarajan,

Marvin Klingner,

Camille Maurice,

B Ravi Kiran,

Senthil Yogamani; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wozniak_2025_WACV, author = {Wozniak, Maciej K. and Govindarajan, Hariprasath and Klingner, Marvin and Maurice, Camille and Kiran, B Ravi and Yogamani, Senthil}, title = {S3PT: Scene Semantics and Structure Guided Clustering to Boost Self-Supervised Pre-Training for Autonomous Driving}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1660-1670} }
Shapley Consensus Deep Learning for Ensemble Pruning: Youcef Djenouri,

Ahmed Nabil Belbachir,

Asma Belhadi,

Nassim Belmecheri,

Tomasz Michalak; [pdf] [supp]
[bibtex]
@InProceedings{Djenouri_2025_WACV, author = {Djenouri, Youcef and Belbachir, Ahmed Nabil and Belhadi, Asma and Belmecheri, Nassim and Michalak, Tomasz}, title = {Shapley Consensus Deep Learning for Ensemble Pruning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6657-6666} }
Personalized Mixture of Experts for Multi-Site Medical Image Segmentation: Md Motiur Rahman,

Mohamed Trabelsi,

Huseyin Uzunalioglu,

Aidan Boyd; [pdf] [supp]
[bibtex]
@InProceedings{Rahman_2025_WACV, author = {Rahman, Md Motiur and Trabelsi, Mohamed and Uzunalioglu, Huseyin and Boyd, Aidan}, title = {Personalized Mixture of Experts for Multi-Site Medical Image Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3172-3184} }
Learning Semantic Part-Based Graph Structure for 3D Point Cloud Domain Generalization: G Ujwal Sai,

Arkadipta De,

Vartika Sengar,

Anuj Rathore,

Daksh Thapar,

Manohar Kaul; [pdf] [supp]
[bibtex]
@InProceedings{Sai_2025_WACV, author = {Sai, G Ujwal and De, Arkadipta and Sengar, Vartika and Rathore, Anuj and Thapar, Daksh and Kaul, Manohar}, title = {Learning Semantic Part-Based Graph Structure for 3D Point Cloud Domain Generalization}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2332-2341} }
MENTOR: Human Perception-Guided Pretraining for Increased Generalization: Colton R. Crum,

Adam Czajka; [pdf] [arXiv]
[bibtex]
@InProceedings{Crum_2025_WACV, author = {Crum, Colton R. and Czajka, Adam}, title = {MENTOR: Human Perception-Guided Pretraining for Increased Generalization}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7470-7479} }
Multi-Modal Large Language Model with RAG Strategies in Soccer Commentary Generation: Xiang Li,

Yangfan He,

Shuaishuai Zu,

Zhengyang Li,

Tianyu Shi,

Yiting Xie,

Kevin Zhang; [pdf]
[bibtex]
@InProceedings{Li_2025_WACV, author = {Li, Xiang and He, Yangfan and Zu, Shuaishuai and Li, Zhengyang and Shi, Tianyu and Xie, Yiting and Zhang, Kevin}, title = {Multi-Modal Large Language Model with RAG Strategies in Soccer Commentary Generation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6197-6206} }
UAL-Bench: The First Comprehensive Unusual Activity Localization Benchmark: Hasnat Md Abdullah,

Tian Liu,

Kangda Wei,

Shu Kong,

Ruihong Huang; [pdf]
[bibtex]
@InProceedings{Abdullah_2025_WACV, author = {Abdullah, Hasnat Md and Liu, Tian and Wei, Kangda and Kong, Shu and Huang, Ruihong}, title = {UAL-Bench: The First Comprehensive Unusual Activity Localization Benchmark}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5801-5811} }
FOR: Finetuning for Object Level Open Vocabulary Image Retrieval: Hila Levi,

Guy Heller,

Dan Levi; [pdf] [arXiv]
[bibtex]
@InProceedings{Levi_2025_WACV, author = {Levi, Hila and Heller, Guy and Levi, Dan}, title = {FOR: Finetuning for Object Level Open Vocabulary Image Retrieval}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8950-8961} }
FRAUD-Net: Fraud News Detection using Sample Uncertainty & Domain Aware Generalized Network: Devendra Patel,

Vikas Verma,

Shreyas Kumar Tah,

Shwetabh Biswas,

Soma Biswas; [pdf]
[bibtex]
@InProceedings{Patel_2025_WACV, author = {Patel, Devendra and Verma, Vikas and Tah, Shreyas Kumar and Biswas, Shwetabh and Biswas, Soma}, title = {FRAUD-Net: Fraud News Detection using Sample Uncertainty \& Domain Aware Generalized Network}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3363-3371} }
All-in-One Image Compression and Restoration: Huimin Zeng,

Jiacheng Li,

Ziqiang Zheng,

Zhiwei Xiong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zeng_2025_WACV, author = {Zeng, Huimin and Li, Jiacheng and Zheng, Ziqiang and Xiong, Zhiwei}, title = {All-in-One Image Compression and Restoration}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {609-619} }
PLReMix: Combating Noisy Labels with Pseudo-Label Relaxed Contrastive Representation Learning: Xiaoyu Liu,

Beitong Zhou,

Zuogong Yue,

Cheng Cheng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2025_WACV, author = {Liu, Xiaoyu and Zhou, Beitong and Yue, Zuogong and Cheng, Cheng}, title = {PLReMix: Combating Noisy Labels with Pseudo-Label Relaxed Contrastive Representation Learning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6517-6527} }
Data Generation for Hardware-Friendly Post-Training Quantization: Lior Dikstein,

Ariel Lapid,

Arnon Netzer,

Hai Victor Habi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dikstein_2025_WACV, author = {Dikstein, Lior and Lapid, Ariel and Netzer, Arnon and Habi, Hai Victor}, title = {Data Generation for Hardware-Friendly Post-Training Quantization}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5103-5113} }
An Investigation on LLMs' Visual Understanding Ability using SVG for Image-Text Bridging: Mu Cai,

Zeyi Huang,

Yuheng Li,

Utkarsh Ojha,

Haohan Wang,

Yong Jae Lee; [pdf] [supp]
[bibtex]
@InProceedings{Cai_2025_WACV, author = {Cai, Mu and Huang, Zeyi and Li, Yuheng and Ojha, Utkarsh and Wang, Haohan and Lee, Yong Jae}, title = {An Investigation on LLMs' Visual Understanding Ability using SVG for Image-Text Bridging}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5377-5386} }
RiemStega: Covariance-Based Loss for Print-Proof Transmission of Data in Images: Aniana Cruz,

Guilherme Schardong,

Luiz Schirmer,

João Marcos,

Farhad Shadmand,

Nuno Gonçalves; [pdf] [supp]
[bibtex]
@InProceedings{Cruz_2025_WACV, author = {Cruz, Aniana and Schardong, Guilherme and Schirmer, Luiz and Marcos, Jo\~ao and Shadmand, Farhad and Gon\c{c}alves, Nuno}, title = {RiemStega: Covariance-Based Loss for Print-Proof Transmission of Data in Images}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7561-7570} }
Rethinking Low-Rank Adaptation in Vision: Exploring Head-Level Responsiveness Across Diverse Tasks: Yibo Zhong,

Yao Zhou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhong_2025_WACV, author = {Zhong, Yibo and Zhou, Yao}, title = {Rethinking Low-Rank Adaptation in Vision: Exploring Head-Level Responsiveness Across Diverse Tasks}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7776-7785} }
Dynamic Adapter Tuning for Long-Tailed Class-Incremental Learning: Yanan Gu,

Muli Yang,

Xu Yang,

Kun Wei,

Hongyuan Zhu,

Gabriel James Goenawan,

Cheng Deng; [pdf] [supp]
[bibtex]
@InProceedings{Gu_2025_WACV, author = {Gu, Yanan and Yang, Muli and Yang, Xu and Wei, Kun and Zhu, Hongyuan and Goenawan, Gabriel James and Deng, Cheng}, title = {Dynamic Adapter Tuning for Long-Tailed Class-Incremental Learning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8165-8174} }
Distilling Aggregated Knowledge for Weakly-Supervised Video Anomaly Detection: Jash Dalvi,

Ali Dabouei,

Gunjan Dhanuka,

Min Xu; [pdf] [arXiv]
[bibtex]
@InProceedings{Dalvi_2025_WACV, author = {Dalvi, Jash and Dabouei, Ali and Dhanuka, Gunjan and Xu, Min}, title = {Distilling Aggregated Knowledge for Weakly-Supervised Video Anomaly Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5439-5448} }
WiGNet: Windowed Vision Graph Neural Network: Gabriele Spadaro,

Marco Grangetto,

Attilio Fiandrotti,

Enzo Tartaglione,

Jhony H. Giraldo; [pdf] [arXiv]
[bibtex]
@InProceedings{Spadaro_2025_WACV, author = {Spadaro, Gabriele and Grangetto, Marco and Fiandrotti, Attilio and Tartaglione, Enzo and Giraldo, Jhony H.}, title = {WiGNet: Windowed Vision Graph Neural Network}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {859-868} }
Transferring Foundation Models for Generalizable Robotic Manipulation: Jiange Yang,

Wenhui Tan,

Chuhao Jin,

Keling Yao,

Bei Liu,

Jianlong Fu,

Ruihua Song,

Gangshan Wu,

Limin Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2025_WACV, author = {Yang, Jiange and Tan, Wenhui and Jin, Chuhao and Yao, Keling and Liu, Bei and Fu, Jianlong and Song, Ruihua and Wu, Gangshan and Wang, Limin}, title = {Transferring Foundation Models for Generalizable Robotic Manipulation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1999-2010} }
Robust Novelty Detection through Style-Conscious Feature Ranking: Stefan Smeu,

Elena Burceanu,

Emanuela Haller,

Andrei Liviu Nicolicioiu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Smeu_2025_WACV, author = {Smeu, Stefan and Burceanu, Elena and Haller, Emanuela and Nicolicioiu, Andrei Liviu}, title = {Robust Novelty Detection through Style-Conscious Feature Ranking}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7409-7418} }
LowFormer: Hardware Efficient Design for Convolutional Transformer Backbones: Moritz Nottebaum,

Matteo Dunnhofer,

Christian Micheloni; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nottebaum_2025_WACV, author = {Nottebaum, Moritz and Dunnhofer, Matteo and Micheloni, Christian}, title = {LowFormer: Hardware Efficient Design for Convolutional Transformer Backbones}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7008-7018} }
Towards Unbiased Continual Learning: Avoiding Forgetting in the Presence of Spurious Correlations: Giacomo Capitani,

Lorenzo Bonicelli,

Angelo Porrello,

Federico Bolelli,

Simone Calderara,

Elisa Ficarra; [pdf] [supp]
[bibtex]
@InProceedings{Capitani_2025_WACV, author = {Capitani, Giacomo and Bonicelli, Lorenzo and Porrello, Angelo and Bolelli, Federico and Calderara, Simone and Ficarra, Elisa}, title = {Towards Unbiased Continual Learning: Avoiding Forgetting in the Presence of Spurious Correlations}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2527-2537} }
Denoising Diffusion Models for High-Resolution Microscopy Image Restoration: Pamela Osuna-Vargas,

Maren H. Wehrheim,

Lucas Zinz,

Johanna Rahm,

Ashwin Balakrishnan,

Alexandra Kaminer,

Mike Heilemann,

Matthias Kaschube; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Osuna-Vargas_2025_WACV, author = {Osuna-Vargas, Pamela and Wehrheim, Maren H. and Zinz, Lucas and Rahm, Johanna and Balakrishnan, Ashwin and Kaminer, Alexandra and Heilemann, Mike and Kaschube, Matthias}, title = {Denoising Diffusion Models for High-Resolution Microscopy Image Restoration}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4320-4330} }
Prior2Posterior: Model Prior Correction for Long-Tailed Learning: S Divakar Bhat,

Amit More,

Mudit Soni,

Surbhi Agrawal; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bhat_2025_WACV, author = {Bhat, S Divakar and More, Amit and Soni, Mudit and Agrawal, Surbhi}, title = {Prior2Posterior: Model Prior Correction for Long-Tailed Learning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1289-1298} }
Domain Generalization using Large Pretrained Models with Mixture-of-Adapters: Gyuseong Lee,

Wooseok Jang,

Jinhyeon Kim,

Jaewoo Jung,

Seungryong Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2025_WACV, author = {Lee, Gyuseong and Jang, Wooseok and Kim, Jinhyeon and Jung, Jaewoo and Kim, Seungryong}, title = {Domain Generalization using Large Pretrained Models with Mixture-of-Adapters}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8248-8258} }
From Visual Explanations to Counterfactual Explanations with Latent Diffusion: Tung Luu,

Nam Le,

Duc Le,

Bac Le; [pdf] [supp]
[bibtex]
@InProceedings{Luu_2025_WACV, author = {Luu, Tung and Le, Nam and Le, Duc and Le, Bac}, title = {From Visual Explanations to Counterfactual Explanations with Latent Diffusion}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {420-429} }
Active Learning with Context Sampling and One-vs-Rest Entropy for Semantic Segmentation: Fei Wu,

Pablo Márquez Neila,

Hedyeh Rafii-Tari,

Raphael Sznitman; [pdf] [supp]
[bibtex]
@InProceedings{Wu_2025_WACV, author = {Wu, Fei and Neila, Pablo M\'arquez and Rafii-Tari, Hedyeh and Sznitman, Raphael}, title = {Active Learning with Context Sampling and One-vs-Rest Entropy for Semantic Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {869-878} }
Learning Unified Distance Metric Across Diverse Data Distributions with Parameter-Efficient Transfer Learning: Sungyeon Kim,

Donghyun Kim,

Suha Kwak; [pdf] [arXiv]
[bibtex]
@InProceedings{Kim_2025_WACV, author = {Kim, Sungyeon and Kim, Donghyun and Kwak, Suha}, title = {Learning Unified Distance Metric Across Diverse Data Distributions with Parameter-Efficient Transfer Learning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9356-9366} }
VisualFusion: Enhancing Blog Content with Advanced Infographic Pipeline: Anurag Deo,

Savita Bhat,

Shirish Karande; [pdf] [supp]
[bibtex]
@InProceedings{Deo_2025_WACV, author = {Deo, Anurag and Bhat, Savita and Karande, Shirish}, title = {VisualFusion: Enhancing Blog Content with Advanced Infographic Pipeline}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5591-5600} }
Class-Agnostic Visio-Temporal Scene Sketch Semantic Segmentation: Aleyna Kütük,

Tevfik Metin Sezgin; [pdf] [supp]
[bibtex]
@InProceedings{Kutuk_2025_WACV, author = {K\"ut\"uk, Aleyna and Sezgin, Tevfik Metin}, title = {Class-Agnostic Visio-Temporal Scene Sketch Semantic Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8433-8442} }
Can Out-of-Domain Data Help to Learn Domain-Specific Prompts for Multimodal Misinformation Detection?: Amartya Bhattacharya,

Debarshi Brahma,

Suraj Nagaje,

Anmol Asati,

Vikas Verma,

Soma Biswas; [pdf] [arXiv]
[bibtex]
@InProceedings{Bhattacharya_2025_WACV, author = {Bhattacharya, Amartya and Brahma, Debarshi and Nagaje, Suraj and Asati, Anmol and Verma, Vikas and Biswas, Soma}, title = {Can Out-of-Domain Data Help to Learn Domain-Specific Prompts for Multimodal Misinformation Detection?}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2808-2817} }
Scene-LLM: Extending Language Model for 3D Visual Reasoning: Rao Fu,

Jingyu Liu,

Xilun Chen,

Yixin Nie,

Wenhan Xiong; [pdf] [supp]
[bibtex]
@InProceedings{Fu_2025_WACV, author = {Fu, Rao and Liu, Jingyu and Chen, Xilun and Nie, Yixin and Xiong, Wenhan}, title = {Scene-LLM: Extending Language Model for 3D Visual Reasoning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2195-2206} }
Style-Pro: Style-Guided Prompt Learning for Generalizable Vision-Language Models: Niloufar Alipour Talemi,

Hossein Kashiani,

Fatemeh Afghah; [pdf]
[bibtex]
@InProceedings{Talemi_2025_WACV, author = {Talemi, Niloufar Alipour and Kashiani, Hossein and Afghah, Fatemeh}, title = {Style-Pro: Style-Guided Prompt Learning for Generalizable Vision-Language Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6207-6216} }
DivAvatar: Diverse 3D Avatar Generation with a Single Prompt: Weijing Tao,

Biwen Lei,

Kunhao Liu,

Shijian Lu,

Miaomiao Cui,

Xuansong Xie; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tao_2025_WACV, author = {Tao, Weijing and Lei, Biwen and Liu, Kunhao and Lu, Shijian and Cui, Miaomiao and Xie, Xuansong}, title = {DivAvatar: Diverse 3D Avatar Generation with a Single Prompt}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2568-2577} }
Information Extraction from Heterogeneous Documents without Ground Truth Labels using Synthetic Label Generation and Knowledge Distillation: Aniket Bhattacharyya,

Anurag Tripathi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bhattacharyya_2025_WACV, author = {Bhattacharyya, Aniket and Tripathi, Anurag}, title = {Information Extraction from Heterogeneous Documents without Ground Truth Labels using Synthetic Label Generation and Knowledge Distillation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6351-6361} }
Exo2EgoDVC: Dense Video Captioning of Egocentric Procedural Activities using Web Instructional Videos: Takehiko Ohkawa,

Takuma Yagi,

Taichi Nishimura,

Ryosuke Furuta,

Atsushi Hashimoto,

Yoshitaka Ushiku,

Yoichi Sato; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ohkawa_2025_WACV, author = {Ohkawa, Takehiko and Yagi, Takuma and Nishimura, Taichi and Furuta, Ryosuke and Hashimoto, Atsushi and Ushiku, Yoshitaka and Sato, Yoichi}, title = {Exo2EgoDVC: Dense Video Captioning of Egocentric Procedural Activities using Web Instructional Videos}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8313-8324} }
Street TryOn: Learning In-the-Wild Virtual Try-On from Unpaired Person Images: Aiyu Cui,

Jay Mahajan,

Viraj Shah,

Preeti Gomathinayagam,

Chang Liu,

Svetlana Lazebnik; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cui_2025_WACV, author = {Cui, Aiyu and Mahajan, Jay and Shah, Viraj and Gomathinayagam, Preeti and Liu, Chang and Lazebnik, Svetlana}, title = {Street TryOn: Learning In-the-Wild Virtual Try-On from Unpaired Person Images}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1414-1423} }
Elemental Composite Prototypical Network: Few-Shot Object Detection on Outdoor 3D Point Cloud Scenes: Arkadipta De,

Vartika Sengar,

Daksh Thapar,

Mahesh Chandran,

Manohar Kaul; [pdf] [supp]
[bibtex]
@InProceedings{De_2025_WACV, author = {De, Arkadipta and Sengar, Vartika and Thapar, Daksh and Chandran, Mahesh and Kaul, Manohar}, title = {Elemental Composite Prototypical Network: Few-Shot Object Detection on Outdoor 3D Point Cloud Scenes}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3216-3226} }
DiffMesh: A Motion-Aware Diffusion Framework for Human Mesh Recovery from Videos: Ce Zheng,

Xianpeng Liu,

Qucheng Peng,

Tianfu Wu,

Pu Wang,

Chen Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zheng_2025_WACV, author = {Zheng, Ce and Liu, Xianpeng and Peng, Qucheng and Wu, Tianfu and Wang, Pu and Chen, Chen}, title = {DiffMesh: A Motion-Aware Diffusion Framework for Human Mesh Recovery from Videos}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4891-4901} }
CrackStructures and CrackEnsembles: The Power of Multi-View for 2.5D Crack Detection: Christian Benz,

Volker Rodehorst; [pdf]
[bibtex]
@InProceedings{Benz_2025_WACV, author = {Benz, Christian and Rodehorst, Volker}, title = {CrackStructures and CrackEnsembles: The Power of Multi-View for 2.5D Crack Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5990-5999} }
SplatFace: Gaussian Splat Face Reconstruction Leveraging an Optimizable Surface: Jiahao Luo,

Jing Liu,

James Davis; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Luo_2025_WACV, author = {Luo, Jiahao and Liu, Jing and Davis, James}, title = {SplatFace: Gaussian Splat Face Reconstruction Leveraging an Optimizable Surface}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {774-783} }
GazeSearch: Radiology Findings Search Benchmark: Trong Thang Pham,

Tien-Phat Nguyen,

Yuki Ikebe,

Akash Awasthi,

Zhigang Deng,

Carol C. Wu,

Hien Nguyen,

Ngan Le; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pham_2025_WACV, author = {Pham, Trong Thang and Nguyen, Tien-Phat and Ikebe, Yuki and Awasthi, Akash and Deng, Zhigang and Wu, Carol C. and Nguyen, Hien and Le, Ngan}, title = {GazeSearch: Radiology Findings Search Benchmark}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {96-106} }
Pix2Poly: A Sequence Prediction Method for End-to-End Polygonal Building Footprint Extraction from Remote Sensing Imagery: Yeshwanth Kumar Adimoolam,

Charalambos Poullis,

Melinos Averkiou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Adimoolam_2025_WACV, author = {Adimoolam, Yeshwanth Kumar and Poullis, Charalambos and Averkiou, Melinos}, title = {Pix2Poly: A Sequence Prediction Method for End-to-End Polygonal Building Footprint Extraction from Remote Sensing Imagery}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8473-8482} }
Flatness Improves Backbone Generalisation in Few-Shot Classification: Rui Li,

Martin Trapp,

Marcus Klasson,

Arno Solin; [pdf] [arXiv]
[bibtex]
@InProceedings{Li_2025_WACV, author = {Li, Rui and Trapp, Martin and Klasson, Marcus and Solin, Arno}, title = {Flatness Improves Backbone Generalisation in Few-Shot Classification}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1072-1089} }
ORFormer: Occlusion-Robust Transformer for Accurate Facial Landmark Detection: Jui-Che Chiang,

Hou-Ning Hu,

Bo-Syuan Hou,

Chia-Yu Tseng,

Yu-Lun Liu,

Min-Hung Chen,

Yen-Yu Lin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chiang_2025_WACV, author = {Chiang, Jui-Che and Hu, Hou-Ning and Hou, Bo-Syuan and Tseng, Chia-Yu and Liu, Yu-Lun and Chen, Min-Hung and Lin, Yen-Yu}, title = {ORFormer: Occlusion-Robust Transformer for Accurate Facial Landmark Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {784-793} }
Unleashing Potentials of Vision-Language Models for Zero-Shot HOI Detection: Moyuru Yamada,

Nimish Dharamshi,

Ayushi Kohli,

Prasad Kasu,

Ainulla Khan,

Manu Ghulyani; [pdf] [supp]
[bibtex]
@InProceedings{Yamada_2025_WACV, author = {Yamada, Moyuru and Dharamshi, Nimish and Kohli, Ayushi and Kasu, Prasad and Khan, Ainulla and Ghulyani, Manu}, title = {Unleashing Potentials of Vision-Language Models for Zero-Shot HOI Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5751-5760} }
Memory-Efficient Pseudo-Labeling for Online Source-Free Universal Domain Adaptation using a Gaussian Mixture Model: Pascal Schlachter,

Simon Wagner,

Bin Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Schlachter_2025_WACV, author = {Schlachter, Pascal and Wagner, Simon and Yang, Bin}, title = {Memory-Efficient Pseudo-Labeling for Online Source-Free Universal Domain Adaptation using a Gaussian Mixture Model}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6425-6434} }
SyncViolinist: Music-Oriented Violin Motion Generation Based on Bowing and Fingering: Hiroki Nishizawa,

Keitaro Tanaka,

Asuka Hirata,

Shugo Yamaguchi,

Qi Feng,

Masatoshi Hamanaka,

Shigeo Morishima; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nishizawa_2025_WACV, author = {Nishizawa, Hiroki and Tanaka, Keitaro and Hirata, Asuka and Yamaguchi, Shugo and Feng, Qi and Hamanaka, Masatoshi and Morishima, Shigeo}, title = {SyncViolinist: Music-Oriented Violin Motion Generation Based on Bowing and Fingering}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5419-5428} }
Deduce and Select Evidences with Language Models for Training-Free Video Goal Inference: Yeo Keat Ee,

Hao Zhang,

Alexander Matyasko,

Basura Fernando; [pdf] [supp]
[bibtex]
@InProceedings{Ee_2025_WACV, author = {Ee, Yeo Keat and Zhang, Hao and Matyasko, Alexander and Fernando, Basura}, title = {Deduce and Select Evidences with Language Models for Training-Free Video Goal Inference}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5937-5947} }
DrIFT: Autonomous Drone Dataset with Integrated Real and Synthetic Data Flexible Views and Transformed Domains: Fardad Dadboud,

Hamid Azad,

Varun Mehta,

Miodrag Bolic,

Iraj Mantegh; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dadboud_2025_WACV, author = {Dadboud, Fardad and Azad, Hamid and Mehta, Varun and Bolic, Miodrag and Mantegh, Iraj}, title = {DrIFT: Autonomous Drone Dataset with Integrated Real and Synthetic Data Flexible Views and Transformed Domains}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6900-6910} }
PixSwap: High-Resolution Face Swapping for Effective Reflection of Identity via Pixel-Level Supervision with Synthetic Paired Dataset: Taewoo Kim,

Geonsu Lee,

Hyukgi Lee,

Seongtae Kim,

Younggun Lee; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2025_WACV, author = {Kim, Taewoo and Lee, Geonsu and Lee, Hyukgi and Kim, Seongtae and Lee, Younggun}, title = {PixSwap: High-Resolution Face Swapping for Effective Reflection of Identity via Pixel-Level Supervision with Synthetic Paired Dataset}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3742-3751} }
Hijacking Vision-and-Language Navigation Agents with Adversarial Environmental Attacks: Zijiao Yang,

Xiangxi Shi,

Eric Slyman,

Stefan Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2025_WACV, author = {Yang, Zijiao and Shi, Xiangxi and Slyman, Eric and Lee, Stefan}, title = {Hijacking Vision-and-Language Navigation Agents with Adversarial Environmental Attacks}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6094-6103} }
TORE: Token Recycling in Vision Transformers for Efficient Active Visual Exploration: Jan Olszewski,

Dawid Damian Rymarczyk,

Piotr Wojcik,

Mateusz Pach,

Bartosz Zielinski; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Olszewski_2025_WACV, author = {Olszewski, Jan and Rymarczyk, Dawid Damian and Wojcik, Piotr and Pach, Mateusz and Zielinski, Bartosz}, title = {TORE: Token Recycling in Vision Transformers for Efficient Active Visual Exploration}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8595-8605} }
CharDiff: Improving Sampling Convergence via Characteristic Function Consistency in Diffusion Models: Abhishek Kumar Sinha,

S. Manthira Moorthi; [pdf] [supp]
[bibtex]
@InProceedings{Sinha_2025_WACV, author = {Sinha, Abhishek Kumar and Moorthi, S. Manthira}, title = {CharDiff: Improving Sampling Convergence via Characteristic Function Consistency in Diffusion Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3955-3964} }
eLIR-Net: An Efficient AI Solution for Image Retouching: Tingting Zhao,

Chenguang Liu,

Kamal Jnawali,

Chang Su; [pdf]
[bibtex]
@InProceedings{Zhao_2025_WACV, author = {Zhao, Tingting and Liu, Chenguang and Jnawali, Kamal and Su, Chang}, title = {eLIR-Net: An Efficient AI Solution for Image Retouching}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3055-3063} }
Bandwidth-Efficient Communication Modelling for Autonomous Vehicle Collaborative Perception: Dinghao Jin,

Yuan Zeng,

Yi Gong; [pdf]
[bibtex]
@InProceedings{Jin_2025_WACV, author = {Jin, Dinghao and Zeng, Yuan and Gong, Yi}, title = {Bandwidth-Efficient Communication Modelling for Autonomous Vehicle Collaborative Perception}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6146-6155} }
Guardian of the Ensembles: Introducing Pairwise Adversarially Robust Loss for Resisting Adversarial Attacks in DNN Ensembles: Shubhi Shukla,

Subhadeep Dalui,

Manaar Alam,

Shubhajit Datta,

Arijit Mondal,

Debdeep Mukhopadhyay,

Partha Pratim Chakrabarti; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shukla_2025_WACV, author = {Shukla, Shubhi and Dalui, Subhadeep and Alam, Manaar and Datta, Shubhajit and Mondal, Arijit and Mukhopadhyay, Debdeep and Chakrabarti, Partha Pratim}, title = {Guardian of the Ensembles: Introducing Pairwise Adversarially Robust Loss for Resisting Adversarial Attacks in DNN Ensembles}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7205-7214} }
A Conic Transformation Approach for Solving the Perspective-Three-Point Problem: Haidong Wu,

Snehal Bhayani,

Janne Heikkilä; [pdf] [supp]
[bibtex]
@InProceedings{Wu_2025_WACV, author = {Wu, Haidong and Bhayani, Snehal and Heikkil\"a, Janne}, title = {A Conic Transformation Approach for Solving the Perspective-Three-Point Problem}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3237-3245} }
Robot Instance Segmentation with Few Annotations for Grasping: Moshe Kimhi,

David Vainshtein,

Chaim Baskin,

Dotan Di Castro; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kimhi_2025_WACV, author = {Kimhi, Moshe and Vainshtein, David and Baskin, Chaim and Di Castro, Dotan}, title = {Robot Instance Segmentation with Few Annotations for Grasping}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7928-7938} }
Volumetric Conditioning Module to Control Pretrained Diffusion Models for 3D Medical Images: Suhyun Ahn,

Wonjung Park,

Jihoon Cho,

Jinah Park; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ahn_2025_WACV, author = {Ahn, Suhyun and Park, Wonjung and Cho, Jihoon and Park, Jinah}, title = {Volumetric Conditioning Module to Control Pretrained Diffusion Models for 3D Medical Images}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {85-95} }
Revisiting Machine Unlearning with Dimensional Alignment: Seonguk Seo,

Dongwan Kim,

Bohyung Han; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Seo_2025_WACV, author = {Seo, Seonguk and Kim, Dongwan and Han, Bohyung}, title = {Revisiting Machine Unlearning with Dimensional Alignment}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3206-3215} }
OT-VP: Optimal Transport-Guided Visual Prompting for Test-Time Adaptation: Yunbei Zhang,

Akshay Mehra,

Jihun Hamm; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2025_WACV, author = {Zhang, Yunbei and Mehra, Akshay and Hamm, Jihun}, title = {OT-VP: Optimal Transport-Guided Visual Prompting for Test-Time Adaptation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1122-1132} }
Towards Zero-Shot 3D Anomaly Localization: Yizhou Wang,

Kuan-Chuan Peng,

Yun Fu; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2025_WACV, author = {Wang, Yizhou and Peng, Kuan-Chuan and Fu, Yun}, title = {Towards Zero-Shot 3D Anomaly Localization}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1447-1456} }
SegDesicNet: Lightweight Semantic Segmentation in Remote Sensing with Geo-Coordinate Embeddings for Domain Adaptation: Sachin Verma,

Frank Lindseth,

Gabriel Kiss; [pdf] [supp]
[bibtex]
@InProceedings{Verma_2025_WACV, author = {Verma, Sachin and Lindseth, Frank and Kiss, Gabriel}, title = {SegDesicNet: Lightweight Semantic Segmentation in Remote Sensing with Geo-Coordinate Embeddings for Domain Adaptation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9075-9086} }
HexaGen3D: StableDiffusion is One Step Away from Fast and Diverse Text-to-3D Generation: Antoine Mercier,

Ramin Nakhli,

Mahesh Reddy,

Rajeev Yasarla,

Hong Cai,

Fatih Porikli,

Guillaume Berger; [pdf] [supp]
[bibtex]
@InProceedings{Mercier_2025_WACV, author = {Mercier, Antoine and Nakhli, Ramin and Reddy, Mahesh and Yasarla, Rajeev and Cai, Hong and Porikli, Fatih and Berger, Guillaume}, title = {HexaGen3D: StableDiffusion is One Step Away from Fast and Diverse Text-to-3D Generation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1247-1257} }
VMAs: Video-to-Music Generation via Semantic Alignment in Web Music Videos: Yan-Bo Lin,

Yu Tian,

Linjie Yang,

Gedas Bertasius,

Heng Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lin_2025_WACV, author = {Lin, Yan-Bo and Tian, Yu and Yang, Linjie and Bertasius, Gedas and Wang, Heng}, title = {VMAs: Video-to-Music Generation via Semantic Alignment in Web Music Videos}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1155-1165} }
Situational Scene Graph for Structured Human-Centric Situation Understanding: Chinthani Sugandhika,

Chen Li,

Deepu Rajan,

Basura Fernando; [pdf] [arXiv]
[bibtex]
@InProceedings{Sugandhika_2025_WACV, author = {Sugandhika, Chinthani and Li, Chen and Rajan, Deepu and Fernando, Basura}, title = {Situational Scene Graph for Structured Human-Centric Situation Understanding}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9197-9207} }
Continual Learning in 3D Point Clouds: Employing Spectral Techniques for Exemplar Selection: Hossein Resani,

Behrooz Nasihatkon,

Mohammadreza Alimoradi Jazi; [pdf] [arXiv]
[bibtex]
@InProceedings{Resani_2025_WACV, author = {Resani, Hossein and Nasihatkon, Behrooz and Jazi, Mohammadreza Alimoradi}, title = {Continual Learning in 3D Point Clouds: Employing Spectral Techniques for Exemplar Selection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2921-2931} }
Good Seed Makes a Good Crop: Discovering Secret Seeds in Text-to-Image Diffusion Models: Katherine Xu,

Lingzhi Zhang,

Jianbo Shi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2025_WACV, author = {Xu, Katherine and Zhang, Lingzhi and Shi, Jianbo}, title = {Good Seed Makes a Good Crop: Discovering Secret Seeds in Text-to-Image Diffusion Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3024-3034} }
OmniGS: Fast Radiance Field Reconstruction using Omnidirectional Gaussian Splatting: Longwei Li,

Huajian Huang,

Sai-Kit Yeung,

Hui Cheng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2025_WACV, author = {Li, Longwei and Huang, Huajian and Yeung, Sai-Kit and Cheng, Hui}, title = {OmniGS: Fast Radiance Field Reconstruction using Omnidirectional Gaussian Splatting}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2260-2268} }
CusConcept: Customized Visual Concept Decomposition with Diffusion Models: Zhi Xu,

Shaozhe Hao,

Kai Han; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2025_WACV, author = {Xu, Zhi and Hao, Shaozhe and Han, Kai}, title = {CusConcept: Customized Visual Concept Decomposition with Diffusion Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3678-3687} }
ALPI: Auto-Labeller with Proxy Injection for 3D Object Detection using 2D Labels Only: Saad Lahlali,

Nicolas Granger,

Herve Le Borgne,

Quoc-Cuong Pham; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lahlali_2025_WACV, author = {Lahlali, Saad and Granger, Nicolas and Le Borgne, Herve and Pham, Quoc-Cuong}, title = {ALPI: Auto-Labeller with Proxy Injection for 3D Object Detection using 2D Labels Only}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2185-2194} }
One VLM to Keep it Learning: Generation and Balancing for Data-Free Continual Visual Question Answering: Deepayan Das,

Davide Talon,

Massimiliano Mancini,

Yiming Wang,

Elisa Ricci; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Das_2025_WACV, author = {Das, Deepayan and Talon, Davide and Mancini, Massimiliano and Wang, Yiming and Ricci, Elisa}, title = {One VLM to Keep it Learning: Generation and Balancing for Data-Free Continual Visual Question Answering}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5635-5645} }
Improving Accuracy and Generalization for Efficient Visual Tracking: Ram Zaveri,

Shivang Patel,

Yu Gu,

Gianfranco Doretto; [pdf] [arXiv]
[bibtex]
@InProceedings{Zaveri_2025_WACV, author = {Zaveri, Ram and Patel, Shivang and Gu, Yu and Doretto, Gianfranco}, title = {Improving Accuracy and Generalization for Efficient Visual Tracking}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9450-9460} }
Diffusion-Based Generative Regularization for Supervised Discriminative Learning: Takuya Asakura,

Nakamasa Inoue,

Koichi Shinoda; [pdf]
[bibtex]
@InProceedings{Asakura_2025_WACV, author = {Asakura, Takuya and Inoue, Nakamasa and Shinoda, Koichi}, title = {Diffusion-Based Generative Regularization for Supervised Discriminative Learning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8897-8908} }
DDS: Decoupled Dynamic Scene-Graph Generation Network: A S M Iftekhar,

Raphael Ruschel,

Satish Kumar,

Suya You,

B. S. Manjunath; [pdf] [arXiv]
[bibtex]
@InProceedings{Iftekhar_2025_WACV, author = {Iftekhar, A S M and Ruschel, Raphael and Kumar, Satish and You, Suya and Manjunath, B. S.}, title = {DDS: Decoupled Dynamic Scene-Graph Generation Network}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9652-9662} }
Generalizable Single-View Object Pose Estimation by Two-Side Generating and Matching: Yujing Sun,

Caiyi Sun,

Yuan Liu,

Yuexin Ma,

Siu Ming Yiu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sun_2025_WACV, author = {Sun, Yujing and Sun, Caiyi and Liu, Yuan and Ma, Yuexin and Yiu, Siu Ming}, title = {Generalizable Single-View Object Pose Estimation by Two-Side Generating and Matching}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {545-556} }
Per-Pixel Solution of Multispectral Photometric Stereo: Shin Ishihara,

Imari Sato; [pdf]
[bibtex]
@InProceedings{Ishihara_2025_WACV, author = {Ishihara, Shin and Sato, Imari}, title = {Per-Pixel Solution of Multispectral Photometric Stereo}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9148-9157} }
Leveraging Vision Language Models for Specialized Agricultural Tasks: Muhammad Arbab Arshad,

Talukder Zaki Jubery,

Tirtho Roy,

Rim Nassiri,

Asheesh K. Singh,

Arti Singh,

Chinmay Hegde,

Baskar Ganapathysubramanian,

Aditya Balu,

Adarsh Krishnamurthy,

Soumik Sarkar; [pdf] [supp]
[bibtex]
@InProceedings{Arshad_2025_WACV, author = {Arshad, Muhammad Arbab and Jubery, Talukder Zaki and Roy, Tirtho and Nassiri, Rim and Singh, Asheesh K. and Singh, Arti and Hegde, Chinmay and Ganapathysubramanian, Baskar and Balu, Aditya and Krishnamurthy, Adarsh and Sarkar, Soumik}, title = {Leveraging Vision Language Models for Specialized Agricultural Tasks}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6320-6329} }
RopeTP: Global Human Motion Recovery via Integrating Robust Pose Estimation with Diffusion Trajectory Prior: Mingjiang Liang,

Yongkang Cheng,

Hualin Liang,

Shaoli Huang,

Wei Liu; [pdf] [arXiv]
[bibtex]
@InProceedings{Liang_2025_WACV, author = {Liang, Mingjiang and Cheng, Yongkang and Liang, Hualin and Huang, Shaoli and Liu, Wei}, title = {RopeTP: Global Human Motion Recovery via Integrating Robust Pose Estimation with Diffusion Trajectory Prior}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2973-2982} }
GeoDiffuser: Geometry-Based Image Editing with Diffusion Models: Rahul Sajnani,

Jeroen Vanbaar,

Jie Min,

Kapil D Katyal,

Srinath Sridhar; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sajnani_2025_WACV, author = {Sajnani, Rahul and Vanbaar, Jeroen and Min, Jie and Katyal, Kapil D and Sridhar, Srinath}, title = {GeoDiffuser: Geometry-Based Image Editing with Diffusion Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {472-482} }
BioNet and NeFF: Crop Biomass Prediction from Point Clouds to Drone Imagery: Xuesong Li,

Zeeshan Hayder,

Ali Zia,

Connor Cassidy,

Shiming Liu,

Warwick Stiller,

Eric Stone,

Warren Conaty,

Lars Petersson,

Vivien Rolland; [pdf] [supp]
[bibtex]
@InProceedings{Li_2025_WACV, author = {Li, Xuesong and Hayder, Zeeshan and Zia, Ali and Cassidy, Connor and Liu, Shiming and Stiller, Warwick and Stone, Eric and Conaty, Warren and Petersson, Lars and Rolland, Vivien}, title = {BioNet and NeFF: Crop Biomass Prediction from Point Clouds to Drone Imagery}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7754-7764} }
AutoProSAM: Automated Prompting SAM for 3D Multi-Organ Segmentation: Chengyin Li,

Rafi Ibn Sultan,

Prashant Khanduri,

Yao Qiang,

Chetty Indrin,

Dongxiao Zhu; [pdf] [arXiv]
[bibtex]
@InProceedings{Li_2025_WACV, author = {Li, Chengyin and Ibn Sultan, Rafi and Khanduri, Prashant and Qiang, Yao and Indrin, Chetty and Zhu, Dongxiao}, title = {AutoProSAM: Automated Prompting SAM for 3D Multi-Organ Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3570-3580} }
VideoGameBunny: Towards Vision Assistants for Video Games: Mohammad Reza Taesiri,

Cor-Paul Bezemer; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Taesiri_2025_WACV, author = {Taesiri, Mohammad Reza and Bezemer, Cor-Paul}, title = {VideoGameBunny: Towards Vision Assistants for Video Games}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1403-1413} }
ShapeMorph: 3D Shape Completion via Blockwise Discrete Diffusion: Jiahui Li,

Pourya Shamsolmoali,

Yue Lu,

Masoumeh Zareapoor; [pdf] [supp]
[bibtex]
@InProceedings{Li_2025_WACV, author = {Li, Jiahui and Shamsolmoali, Pourya and Lu, Yue and Zareapoor, Masoumeh}, title = {ShapeMorph: 3D Shape Completion via Blockwise Discrete Diffusion}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2818-2827} }
NAT: Learning to Attack Neurons for Enhanced Adversarial Transferability: Krishna Kanth Nakka,

Alexandre Alahi; [pdf] [supp]
[bibtex]
@InProceedings{Nakka_2025_WACV, author = {Nakka, Krishna Kanth and Alahi, Alexandre}, title = {NAT: Learning to Attack Neurons for Enhanced Adversarial Transferability}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7582-7593} }
GEXIA: Granularity Expansion and Iterative Approximation for Scalable Multi-Grained Video-Language Learning: Yicheng Wang,

Zhikang Zhang,

Jue Wang,

David Fan,

Zhenlin Xu,

Linda Liu,

Xiang Hao,

Vimal Bhat,

Xinyu Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2025_WACV, author = {Wang, Yicheng and Zhang, Zhikang and Wang, Jue and Fan, David and Xu, Zhenlin and Liu, Linda and Hao, Xiang and Bhat, Vimal and Li, Xinyu}, title = {GEXIA: Granularity Expansion and Iterative Approximation for Scalable Multi-Grained Video-Language Learning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4725-4735} }
MoRAG - Multi-Fusion Retrieval Augmented Generation for Human Motion: Sai Shashank Kalakonda,

Shubh Maheshwari,

Ravi Kiran Sarvadevabhatla; [pdf] [supp]
[bibtex]
@InProceedings{Kalakonda_2025_WACV, author = {Kalakonda, Sai Shashank and Maheshwari, Shubh and Sarvadevabhatla, Ravi Kiran}, title = {MoRAG - Multi-Fusion Retrieval Augmented Generation for Human Motion}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4564-4573} }
PositiveCoOp: Rethinking Prompting Strategies for Multi-Label Recognition with Partial Annotations: Samyak Rawlekar,

Shubhang Bhatnagar,

Narendra Ahuja; [pdf] [supp]
[bibtex]
@InProceedings{Rawlekar_2025_WACV, author = {Rawlekar, Samyak and Bhatnagar, Shubhang and Ahuja, Narendra}, title = {PositiveCoOp: Rethinking Prompting Strategies for Multi-Label Recognition with Partial Annotations}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5863-5872} }
AIC3DOD: Advancing Indoor Class-Incremental 3D Object Detection with Point Transformer Architecture and Room Layout Constraints: Zhongyao Cheng,

Fang Wu,

Peisheng Qian,

Ziyuan Zhao,

Xulei Yang; [pdf]
[bibtex]
@InProceedings{Cheng_2025_WACV, author = {Cheng, Zhongyao and Wu, Fang and Qian, Peisheng and Zhao, Ziyuan and Yang, Xulei}, title = {AIC3DOD: Advancing Indoor Class-Incremental 3D Object Detection with Point Transformer Architecture and Room Layout Constraints}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7501-7510} }
PACA: Prespective-Aware Cross-Attention Representation for Zero-Shot Scene Rearrangement: Shutong Jin,

Ruiyu Wang,

Kuangyi Chen,

Florian T. Pokorny; [pdf] [supp]
[bibtex]
@InProceedings{Jin_2025_WACV, author = {Jin, Shutong and Wang, Ruiyu and Chen, Kuangyi and Pokorny, Florian T.}, title = {PACA: Prespective-Aware Cross-Attention Representation for Zero-Shot Scene Rearrangement}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6559-6569} }
SUM: Saliency Unification through Mamba for Visual Attention Modeling: Alireza Hosseini,

Amirhossein Kazerouni,

Saeed Akhavan,

Michael Brudno,

Babak Taati; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hosseini_2025_WACV, author = {Hosseini, Alireza and Kazerouni, Amirhossein and Akhavan, Saeed and Brudno, Michael and Taati, Babak}, title = {SUM: Saliency Unification through Mamba for Visual Attention Modeling}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1597-1607} }
Adversarial Learning Based Knowledge Distillation on 3D Point Clouds: Sanjay S J,

Akash J,

Sreehari Rajan,

Dimple A Shajahan,

Charu Sharma; [pdf]
[bibtex]
@InProceedings{J_2025_WACV, author = {J, Sanjay S and J, Akash and Rajan, Sreehari and A Shajahan, Dimple and Sharma, Charu}, title = {Adversarial Learning Based Knowledge Distillation on 3D Point Clouds}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2932-2941} }
Shift Equivariant Pose Network: Pengxiao Wang,

Tzu-Heng Lin,

Chunyu Wang,

Yizhou Wang; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2025_WACV, author = {Wang, Pengxiao and Lin, Tzu-Heng and Wang, Chunyu and Wang, Yizhou}, title = {Shift Equivariant Pose Network}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {192-201} }
Relaxing Binary Constraints in Contrastive Vision-Language Medical Representation Learning: Xiaoyang Wei,

Camille Kurtz,

Florence Cloppet; [pdf] [supp]
[bibtex]
@InProceedings{Wei_2025_WACV, author = {Wei, Xiaoyang and Kurtz, Camille and Cloppet, Florence}, title = {Relaxing Binary Constraints in Contrastive Vision-Language Medical Representation Learning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4462-4471} }
Few-Shot Structure-Informed Machinery Part Segmentation with Foundation Models and Graph Neural Networks: Michael Schwingshackl,

Fabio F. Oberweger,

Markus Murschitz; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Schwingshackl_2025_WACV, author = {Schwingshackl, Michael and Oberweger, Fabio F. and Murschitz, Markus}, title = {Few-Shot Structure-Informed Machinery Part Segmentation with Foundation Models and Graph Neural Networks}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1989-1998} }
EasyRet3D: Uncalibrated Multi-View Multi-Human 3D Reconstruction and Tracking: Junjie Oscar Yin,

Ting Li,

Jiahao Wang,

Yi Zhang,

Alan Yuille; [pdf] [supp]
[bibtex]
@InProceedings{Yin_2025_WACV, author = {Yin, Junjie Oscar and Li, Ting and Wang, Jiahao and Zhang, Yi and Yuille, Alan}, title = {EasyRet3D: Uncalibrated Multi-View Multi-Human 3D Reconstruction and Tracking}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3128-3137} }
Spatially-Adaptive Hash Encodings for Neural Surface Reconstruction: Thomas Walker,

Octave Mariotti,

Amir Vaxman,

Hakan Bilen; [pdf] [arXiv]
[bibtex]
@InProceedings{Walker_2025_WACV, author = {Walker, Thomas and Mariotti, Octave and Vaxman, Amir and Bilen, Hakan}, title = {Spatially-Adaptive Hash Encodings for Neural Surface Reconstruction}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2963-2972} }
MagicStick: Controllable Video Editing via Control Handle Transformations: Yue Ma,

Xiaodong Cun,

Sen Liang,

Jinbo Xing,

Yingqing He,

Chenyang Qi,

Siran Chen,

Qifeng Chen; [pdf] [arXiv]
[bibtex]
@InProceedings{Ma_2025_WACV, author = {Ma, Yue and Cun, Xiaodong and Liang, Sen and Xing, Jinbo and He, Yingqing and Qi, Chenyang and Chen, Siran and Chen, Qifeng}, title = {MagicStick: Controllable Video Editing via Control Handle Transformations}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9367-9377} }
D-LUT: Photorealistic Style Transfer via Diffusion Process: Mujing Li,

Guanjie Wang,

Xingguang Zhang,

Qifeng Liao,

Chenxi Xiao; [pdf] [supp]
[bibtex]
@InProceedings{Li_2025_WACV, author = {Li, Mujing and Wang, Guanjie and Zhang, Xingguang and Liao, Qifeng and Xiao, Chenxi}, title = {D-LUT: Photorealistic Style Transfer via Diffusion Process}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9188-9196} }
OTCXR: Rethinking Self-Supervised Alignment using Optimal Transport for Chest X-ray Analysis: Vandan Gorade,

Azad Singh,

Deepak Mishra; [pdf] [supp]
[bibtex]
@InProceedings{Gorade_2025_WACV, author = {Gorade, Vandan and Singh, Azad and Mishra, Deepak}, title = {OTCXR: Rethinking Self-Supervised Alignment using Optimal Transport for Chest X-ray Analysis}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7143-7152} }
Adversarial Attention Deficit: Fooling Deformable Vision Transformers with Collaborative Adversarial Patches: Quazi Mishkatul Alam,

Bilel Tarchoun,

Ihsen Alouani,

Nael Abu-Ghazaleh; [pdf] [supp]
[bibtex]
@InProceedings{Alam_2025_WACV, author = {Alam, Quazi Mishkatul and Tarchoun, Bilel and Alouani, Ihsen and Abu-Ghazaleh, Nael}, title = {Adversarial Attention Deficit: Fooling Deformable Vision Transformers with Collaborative Adversarial Patches}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7123-7132} }
Reflective Teacher: Semi-Supervised Multimodal 3D Object Detection in Bird's-Eye-View via Uncertainty Measure: Saheli Hazra,

Sudip Das,

Rohit Choudhary,

Arindam Das,

Ganesh Sistu,

Ciarán Eising,

Ujjwal Bhattacharya; [pdf]
[bibtex]
@InProceedings{Hazra_2025_WACV, author = {Hazra, Saheli and Das, Sudip and Choudhary, Rohit and Das, Arindam and Sistu, Ganesh and Eising, Ciar\'an and Bhattacharya, Ujjwal}, title = {Reflective Teacher: Semi-Supervised Multimodal 3D Object Detection in Bird's-Eye-View via Uncertainty Measure}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1649-1659} }
MaskVD: Region Masking for Efficient Video Object Detection: Sreetama Sarkar,

Gourav Datta,

Souvik Kundu,

Kai Zheng,

Chirayata Bhattacharyya,

Peter A. Beerel; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sarkar_2025_WACV, author = {Sarkar, Sreetama and Datta, Gourav and Kundu, Souvik and Zheng, Kai and Bhattacharyya, Chirayata and Beerel, Peter A.}, title = {MaskVD: Region Masking for Efficient Video Object Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1955-1964} }
Flowering Time Prediction of Wheat from DIA-MS Data: Yan Yang,

Utpal Bose,

James Broadbent,

Sally Stockwell,

Keren A Byrne,

Md Zakir Hossain,

Eric A Stone,

Shannon Dillon; [pdf]
[bibtex]
@InProceedings{Yang_2025_WACV, author = {Yang, Yan and Bose, Utpal and Broadbent, James and Stockwell, Sally and A Byrne, Keren and Hossain, Md Zakir and A Stone, Eric and Dillon, Shannon}, title = {Flowering Time Prediction of Wheat from DIA-MS Data}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4810-4820} }
Vision-Aware Text Features in Referring Image Segmentation: From Object Understanding to Context Understanding: Hai Nguyen-Truong,

E-Ro Nguyen,

Tuan-Anh Vu,

Minh-Triet Tran,

Binh-Son Hua,

Sai-Kit Yeung; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nguyen-Truong_2025_WACV, author = {Nguyen-Truong, Hai and Nguyen, E-Ro and Vu, Tuan-Anh and Tran, Minh-Triet and Hua, Binh-Son and Yeung, Sai-Kit}, title = {Vision-Aware Text Features in Referring Image Segmentation: From Object Understanding to Context Understanding}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4988-4998} }
Forensic Iris Image-Based Post-Mortem Interval Estimation: Rasel Ahmed Bhuiyan,

Adam Czajka; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bhuiyan_2025_WACV, author = {Bhuiyan, Rasel Ahmed and Czajka, Adam}, title = {Forensic Iris Image-Based Post-Mortem Interval Estimation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4258-4267} }
MFTrans: A Multi-Resolution Fusion Transformer for Robust Tumor Segmentation in Whole Slide Images: Sungkyu Yang,

Woohyun Park,

Kwangil Yim,

Mansu Kim; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2025_WACV, author = {Yang, Sungkyu and Park, Woohyun and Yim, Kwangil and Kim, Mansu}, title = {MFTrans: A Multi-Resolution Fusion Transformer for Robust Tumor Segmentation in Whole Slide Images}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4595-4605} }
360PanT: Training-Free Text-Driven 360-Degree Panorama-to-Panorama Translation: Hai Wang,

Jing-Hao Xue; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2025_WACV, author = {Wang, Hai and Xue, Jing-Hao}, title = {360PanT: Training-Free Text-Driven 360-Degree Panorama-to-Panorama Translation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {212-221} }
Spk2ImgMamba: Spiking Camera Image Reconstruction with Multi-Scale State Space Models: Jiaoyang Yin,

Bin Fan,

Chao Xu,

Tiejun Huang,

Boxin Shi; [pdf]
[bibtex]
@InProceedings{Yin_2025_WACV, author = {Yin, Jiaoyang and Fan, Bin and Xu, Chao and Huang, Tiejun and Shi, Boxin}, title = {Spk2ImgMamba: Spiking Camera Image Reconstruction with Multi-Scale State Space Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9324-9334} }
DARDA: Domain-Aware Real-Time Dynamic Neural Network Adaptation: Shahriar Rifat,

Jonathan Ashdown,

Francesco Restuccia; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Rifat_2025_WACV, author = {Rifat, Shahriar and Ashdown, Jonathan and Restuccia, Francesco}, title = {DARDA: Domain-Aware Real-Time Dynamic Neural Network Adaptation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1924-1932} }
A New Benchmark and Baseline for Real-Time High-Resolution Image Inpainting on Edge Devices: Marcelo Sánchez Ortega,

Gil Triginer Garces,

Coloma Ballester,

Ignacio Sarasua,

Lara Raad; [pdf]
[bibtex]
@InProceedings{Ortega_2025_WACV, author = {Ortega, Marcelo S\'anchez and Garces, Gil Triginer and Ballester, Coloma and Sarasua, Ignacio and Raad, Lara}, title = {A New Benchmark and Baseline for Real-Time High-Resolution Image Inpainting on Edge Devices}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1133-1143} }
FastVideoEdit: Leveraging Consistency Models for Efficient Text-to-Video Editing: Youyuan Zhang,

Xuan Ju,

James J. Clark; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2025_WACV, author = {Zhang, Youyuan and Ju, Xuan and Clark, James J.}, title = {FastVideoEdit: Leveraging Consistency Models for Efficient Text-to-Video Editing}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3657-3666} }
InDistill: Information Flow-Preserving Knowledge Distillation for Model Compression: Ioannis Sarridis,

Christos Koutlis,

Giorgos Kordopatis-Zilos,

Yiannis Kompatsiaris,

Symeon Papadopoulos; [pdf] [arXiv]
[bibtex]
@InProceedings{Sarridis_2025_WACV, author = {Sarridis, Ioannis and Koutlis, Christos and Kordopatis-Zilos, Giorgos and Kompatsiaris, Yiannis and Papadopoulos, Symeon}, title = {InDistill: Information Flow-Preserving Knowledge Distillation for Model Compression}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9015-9024} }
Who Brings the Frisbee: Probing Hidden Hallucination Factors in Large Vision-Language Model via Causality Analysis: Po-Hsuan Huang,

Jeng-Lin Li,

Chin-Po Chen,

Ming-Ching Chang,

Wei-Chao Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2025_WACV, author = {Huang, Po-Hsuan and Li, Jeng-Lin and Chen, Chin-Po and Chang, Ming-Ching and Chen, Wei-Chao}, title = {Who Brings the Frisbee: Probing Hidden Hallucination Factors in Large Vision-Language Model via Causality Analysis}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6125-6135} }
SV-data2vec: Guiding Video Representation Learning with Latent Skeleton Targets: Zorana Doždor,

Tomislav Hrkac,

Zoran Kalafatic; [pdf]
[bibtex]
@InProceedings{Dozdor_2025_WACV, author = {Do\v{z}dor, Zorana and Hrkac, Tomislav and Kalafatic, Zoran}, title = {SV-data2vec: Guiding Video Representation Learning with Latent Skeleton Targets}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6967-6976} }
DocTTT: Test-Time Training for Handwritten Document Recognition using Meta-Auxiliary Learning: Wenhao Gu,

Li Gu,

Ziqiang Wang,

Ching Y Suen,

Yang Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Gu_2025_WACV, author = {Gu, Wenhao and Gu, Li and Wang, Ziqiang and Suen, Ching Y and Wang, Yang}, title = {DocTTT: Test-Time Training for Handwritten Document Recognition using Meta-Auxiliary Learning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1904-1913} }
LLaVA-SpaceSGG: Visual Instruct Tuning for Open-Vocabulary Scene Graph Generation with Enhanced Spatial Relations: Mingjie Xu,

Mengyang Wu,

Yuzhi Zhao,

Jason Chun Lok Li,

Weifeng Ou; [pdf] [supp]
[bibtex]
@InProceedings{Xu_2025_WACV, author = {Xu, Mingjie and Wu, Mengyang and Zhao, Yuzhi and Li, Jason Chun Lok and Ou, Weifeng}, title = {LLaVA-SpaceSGG: Visual Instruct Tuning for Open-Vocabulary Scene Graph Generation with Enhanced Spatial Relations}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6362-6372} }
BASED: Bundle-Adjusting Surgical Endoscopic Dynamic Video Reconstruction using Neural Radiance Fields: Shreya Saha,

Zekai Liang,

Shan Lin,

Jingpei Lu,

Michael Yip,

Sainan Liu; [pdf] [arXiv]
[bibtex]
@InProceedings{Saha_2025_WACV, author = {Saha, Shreya and Liang, Zekai and Lin, Shan and Lu, Jingpei and Yip, Michael and Liu, Sainan}, title = {BASED: Bundle-Adjusting Surgical Endoscopic Dynamic Video Reconstruction using Neural Radiance Fields}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3003-3012} }
Make VLM Recognize Visual Hallucination on Cartoon Character Image with Pose Information: Bumsoo Kim,

Wonseop Shin,

Kyuchul Lee,

Yonghoon Jung,

Sanghyun Seo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2025_WACV, author = {Kim, Bumsoo and Shin, Wonseop and Lee, Kyuchul and Jung, Yonghoon and Seo, Sanghyun}, title = {Make VLM Recognize Visual Hallucination on Cartoon Character Image with Pose Information}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5398-5407} }
SODA: Spectral Orthogonal Decomposition Adaptation for Diffusion Models: Xinxi Zhang,

Song Wen,

Ligong Han,

Felix Juefei-Xu,

Akash Srivastava,

Junzhou Huang,

Vladimir Pavlovic,

Hao Wang,

Molei Tao,

Dimitris Metaxas; [pdf]
[bibtex]
@InProceedings{Zhang_2025_WACV, author = {Zhang, Xinxi and Wen, Song and Han, Ligong and Juefei-Xu, Felix and Srivastava, Akash and Huang, Junzhou and Pavlovic, Vladimir and Wang, Hao and Tao, Molei and Metaxas, Dimitris}, title = {SODA: Spectral Orthogonal Decomposition Adaptation for Diffusion Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4665-4682} }
Retaining and Enhancing Pre-Trained Knowledge in Vision-Language Models with Prompt Ensembling: Donggeun Kim,

Yujin Jo,

Myungjoo Lee,

Taesup Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2025_WACV, author = {Kim, Donggeun and Jo, Yujin and Lee, Myungjoo and Kim, Taesup}, title = {Retaining and Enhancing Pre-Trained Knowledge in Vision-Language Models with Prompt Ensembling}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5550-5559} }
DisCo: Discovering Common Affordance from Large Models for Actionable Part Perception: Youpeng Wen,

Yi Zhu,

Zhihao Zhan,

Pengzhen Ren,

Jianhua Han,

Hang Xu,

Shen Zhao,

Xiaodan Liang; [pdf] [supp]
[bibtex]
@InProceedings{Wen_2025_WACV, author = {Wen, Youpeng and Zhu, Yi and Zhan, Zhihao and Ren, Pengzhen and Han, Jianhua and Xu, Hang and Zhao, Shen and Liang, Xiaodan}, title = {DisCo: Discovering Common Affordance from Large Models for Actionable Part Perception}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3320-3329} }
Endoscopic Scoring and Localization in Unconstrained Clinical Trial Videos: Jinlin Xiang,

Hillol Sarker,

Bozhao Qi,

Ruisu Zhang,

Roger Trullo,

Salvatore Badalamenti,

Maria Wiekowski,

Annie Kruger,

Etienne Pochet,

Qi Tang,

Wei Zhao; [pdf] [supp]
[bibtex]
@InProceedings{Xiang_2025_WACV, author = {Xiang, Jinlin and Sarker, Hillol and Qi, Bozhao and Zhang, Ruisu and Trullo, Roger and Badalamenti, Salvatore and Wiekowski, Maria and Kruger, Annie and Pochet, Etienne and Tang, Qi and Zhao, Wei}, title = {Endoscopic Scoring and Localization in Unconstrained Clinical Trial Videos}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4006-4015} }
Just Shift It: Test-Time Prototype Shifting for Zero-Shot Generalization with Vision-Language Models: Elaine Sui,

Xiaohan Wang,

Serena Yeung-Levy; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sui_2025_WACV, author = {Sui, Elaine and Wang, Xiaohan and Yeung-Levy, Serena}, title = {Just Shift It: Test-Time Prototype Shifting for Zero-Shot Generalization with Vision-Language Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {825-835} }
Ad^2mix: Adversarial and Adaptive Mixup for Unsupervised Domain Adaptation: Lei Zhu,

Yanyu Xu,

Yong Liu,

Rick Siow Mong Goh,

Xinxing Xu; [pdf] [supp]
[bibtex]
@InProceedings{Zhu_2025_WACV, author = {Zhu, Lei and Xu, Yanyu and Liu, Yong and Goh, Rick Siow Mong and Xu, Xinxing}, title = {Ad{\textasciicircum}2mix: Adversarial and Adaptive Mixup for Unsupervised Domain Adaptation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6581-6590} }
WARLearn: Weather-Adaptive Representation Learning: Shubham Agarwal,

Raz Birman,

Ofer Hadar; [pdf] [arXiv]
[bibtex]
@InProceedings{Agarwal_2025_WACV, author = {Agarwal, Shubham and Birman, Raz and Hadar, Ofer}, title = {WARLearn: Weather-Adaptive Representation Learning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4978-4987} }
Generation of Complex 3D Human Motion by Temporal and Spatial Composition of Diffusion Models: Lorenzo Mandelli,

Stefano Berretti; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mandelli_2025_WACV, author = {Mandelli, Lorenzo and Berretti, Stefano}, title = {Generation of Complex 3D Human Motion by Temporal and Spatial Composition of Diffusion Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1279-1288} }
Inverting the Generation Process of Denoising Diffusion Implicit Models: Empirical Evaluation and a Novel Method: Yan Zeng,

Masanori Suganuma,

Takayuki Okatani; [pdf]
[bibtex]
@InProceedings{Zeng_2025_WACV, author = {Zeng, Yan and Suganuma, Masanori and Okatani, Takayuki}, title = {Inverting the Generation Process of Denoising Diffusion Implicit Models: Empirical Evaluation and a Novel Method}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4616-4624} }
HeightMapNet: Explicit Height Modeling for End-to-End HD Map Learning: Wenzhao Qiu,

Shanmin Pang,

Hao Zhang,

Jianwu Fang,

Jianru Xue; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Qiu_2025_WACV, author = {Qiu, Wenzhao and Pang, Shanmin and Zhang, Hao and Fang, Jianwu and Xue, Jianru}, title = {HeightMapNet: Explicit Height Modeling for End-to-End HD Map Learning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6022-6031} }
Invariant Shape Representation Learning for Image Classification: Tonmoy Hossain,

Jing Ma,

Jundong Li,

Miaomiao Zhang; [pdf] [arXiv]
[bibtex]
@InProceedings{Hossain_2025_WACV, author = {Hossain, Tonmoy and Ma, Jing and Li, Jundong and Zhang, Miaomiao}, title = {Invariant Shape Representation Learning for Image Classification}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4279-4289} }
Multi-Resolution Guided 3D GANs for Medical Image Translation: Juhyung Ha,

Jong Sung Park,

David Crandall,

Eleftherios Garyfallidis,

Xuhong Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ha_2025_WACV, author = {Ha, Juhyung and Park, Jong Sung and Crandall, David and Garyfallidis, Eleftherios and Zhang, Xuhong}, title = {Multi-Resolution Guided 3D GANs for Medical Image Translation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4342-4351} }
Ada-VE: Training-Free Consistent Video Editing using Adaptive Motion Prior: Tanvir Mahmud,

Mustafa Munir,

Radu Marculescu,

Diana Marculescu; [pdf] [supp]
[bibtex]
@InProceedings{Mahmud_2025_WACV, author = {Mahmud, Tanvir and Munir, Mustafa and Marculescu, Radu and Marculescu, Diana}, title = {Ada-VE: Training-Free Consistent Video Editing using Adaptive Motion Prior}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {940-949} }
Cross-Modal Feature Alignment and MMD Improve Robustness of Prompt Tuning: Jingchen Sun,

Rohan Sharma,

Vishnu Lokhande,

Changyou Chen; [pdf] [supp]
[bibtex]
@InProceedings{Sun_2025_WACV, author = {Sun, Jingchen and Sharma, Rohan and Lokhande, Vishnu and Chen, Changyou}, title = {Cross-Modal Feature Alignment and MMD Improve Robustness of Prompt Tuning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4714-4724} }
ReinDiffuse: Crafting Physically Plausible Motions with Reinforced Diffusion Model: Gaoge Han,

Mingjiang Liang,

Jinglei Tang,

Yongkang Cheng,

Wei Liu,

Shaoli Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Han_2025_WACV, author = {Han, Gaoge and Liang, Mingjiang and Tang, Jinglei and Cheng, Yongkang and Liu, Wei and Huang, Shaoli}, title = {ReinDiffuse: Crafting Physically Plausible Motions with Reinforced Diffusion Model}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2218-2227} }
VerA: Versatile Anonymization Applicable to Clinical Facial Photographs: Majed El Helou,

Doruk Cetin,

Petar Stamenkovic,

Niko Benjamin Huber,

Fabio Zünd; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{El_Helou_2025_WACV, author = {El Helou, Majed and Cetin, Doruk and Stamenkovic, Petar and Huber, Niko Benjamin and Z\"und, Fabio}, title = {VerA: Versatile Anonymization Applicable to Clinical Facial Photographs}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {127-138} }
Event-Guided Fusion-Mamba for Context-Aware 3D Human Pose Estimation: Bo Lang,

Mooi Choo Chuah; [pdf]
[bibtex]
@InProceedings{Lang_2025_WACV, author = {Lang, Bo and Chuah, Mooi Choo}, title = {Event-Guided Fusion-Mamba for Context-Aware 3D Human Pose Estimation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {950-960} }
MegaFusion: Extend Diffusion Models towards Higher-Resolution Image Generation without Further Tuning: Haoning Wu,

Shaocheng Shen,

Qiang Hu,

Xiaoyun Zhang,

Ya Zhang,

Yanfeng Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2025_WACV, author = {Wu, Haoning and Shen, Shaocheng and Hu, Qiang and Zhang, Xiaoyun and Zhang, Ya and Wang, Yanfeng}, title = {MegaFusion: Extend Diffusion Models towards Higher-Resolution Image Generation without Further Tuning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3944-3954} }
Defending Against Repetitive Backdoor Attacks on Semi-Supervised Learning through Lens of Rate-Distortion-Perception Trade-Off: Cheng-Yi Lee,

Ching-Chia Kao,

Cheng-Han Yeh,

Chun-Shien Lu,

Chia-Mu Yu,

Chu-Song Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2025_WACV, author = {Lee, Cheng-Yi and Kao, Ching-Chia and Yeh, Cheng-Han and Lu, Chun-Shien and Yu, Chia-Mu and Chen, Chu-Song}, title = {Defending Against Repetitive Backdoor Attacks on Semi-Supervised Learning through Lens of Rate-Distortion-Perception Trade-Off}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6465-6474} }
BeautyBank: Encoding Facial Makeup in Latent Space: Qianwen Lu,

Xingchao Yang,

Takafumi Taketomi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lu_2025_WACV, author = {Lu, Qianwen and Yang, Xingchao and Taketomi, Takafumi}, title = {BeautyBank: Encoding Facial Makeup in Latent Space}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4183-4193} }
MVFNet: Multipurpose Video Forensics Network using Multiple Forms of Forensic Evidence: Tai D Nguyen,

Matthew C Stamm; [pdf] [supp]
[bibtex]
@InProceedings{Nguyen_2025_WACV, author = {Nguyen, Tai D and Stamm, Matthew C}, title = {MVFNet: Multipurpose Video Forensics Network using Multiple Forms of Forensic Evidence}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2207-2217} }
PV-VTT: A Privacy-Centric Dataset for Mission-Specific Anomaly Detection and Natural Language Interpretation: Ryozo Masukawa,

Sanggeon Yun,

Yoshiki Yamaguchi,

Mohsen Imani; [pdf]
[bibtex]
@InProceedings{Masukawa_2025_WACV, author = {Masukawa, Ryozo and Yun, Sanggeon and Yamaguchi, Yoshiki and Imani, Mohsen}, title = {PV-VTT: A Privacy-Centric Dataset for Mission-Specific Anomaly Detection and Natural Language Interpretation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6415-6424} }
MulModSeg: Enhancing Unpaired Multi-Modal Medical Image Segmentation with Modality-Conditioned Text Embedding and Alternating Training: Chengyin Li,

Hui Zhu,

Rafi Ibn Sultan,

Hassan Bagher Ebadian,

Prashant Khanduri,

Chetty Indrin,

Kundan Thind,

Dongxiao Zhu; [pdf] [arXiv]
[bibtex]
@InProceedings{Li_2025_WACV, author = {Li, Chengyin and Zhu, Hui and Ibn Sultan, Rafi and Ebadian, Hassan Bagher and Khanduri, Prashant and Indrin, Chetty and Thind, Kundan and Zhu, Dongxiao}, title = {MulModSeg: Enhancing Unpaired Multi-Modal Medical Image Segmentation with Modality-Conditioned Text Embedding and Alternating Training}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3581-3591} }
TokenBinder: Text-Video Retrieval with One-to-Many Alignment Paradigm: Bingqing Zhang,

Zhuo Cao,

Heming Du,

Xin Yu,

Xue Li,

Jiajun Liu,

Sen Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2025_WACV, author = {Zhang, Bingqing and Cao, Zhuo and Du, Heming and Yu, Xin and Li, Xue and Liu, Jiajun and Wang, Sen}, title = {TokenBinder: Text-Video Retrieval with One-to-Many Alignment Paradigm}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4957-4967} }
@BENCH: Benchmarking Vision-Language Models for Human-Centered Assistive Technology: Xin Jiang,

Junwei Zheng,

Ruiping Liu,

Jiahang Li,

Jiaming Zhang,

Sven Matthiesen,

Rainer Stiefelhagen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jiang_2025_WACV, author = {Jiang, Xin and Zheng, Junwei and Liu, Ruiping and Li, Jiahang and Zhang, Jiaming and Matthiesen, Sven and Stiefelhagen, Rainer}, title = {@BENCH: Benchmarking Vision-Language Models for Human-Centered Assistive Technology}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3934-3943} }
VioPose: Violin Performance 4D Pose Estimation by Hierarchical Audiovisual Inference: Seong Jong Yoo,

Snehesh Shrestha,

Irina Muresanu,

Cornelia Fermuller; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yoo_2025_WACV, author = {Yoo, Seong Jong and Shrestha, Snehesh and Muresanu, Irina and Fermuller, Cornelia}, title = {VioPose: Violin Performance 4D Pose Estimation by Hierarchical Audiovisual Inference}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4923-4934} }
Event-Guided Video Transformer for End-to-End 3D Human Pose Estimation: Bo Lang,

Mooi Choo Chuah; [pdf]
[bibtex]
@InProceedings{Lang_2025_WACV, author = {Lang, Bo and Chuah, Mooi Choo}, title = {Event-Guided Video Transformer for End-to-End 3D Human Pose Estimation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5114-5124} }
GlobalDoc: A Cross-Modal Vision-Language Framework for Real-World Document Image Retrieval and Classification: Souhail Bakkali,

Sanket Biswas,

Zuheng Ming,

Mickaël Coustaty,

Marçal Rusiñol,

Oriol Ramos Terrades,

Josep Lladós; [pdf] [arXiv]
[bibtex]
@InProceedings{Bakkali_2025_WACV, author = {Bakkali, Souhail and Biswas, Sanket and Ming, Zuheng and Coustaty, Micka\"el and Rusi\~nol, Mar\c{c}al and Terrades, Oriol Ramos and Llad\'os, Josep}, title = {GlobalDoc: A Cross-Modal Vision-Language Framework for Real-World Document Image Retrieval and Classification}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1436-1446} }
TRH2TQA: Table Recognition with Hierarchical Relationships to Table Question-Answering on Business Table Images: Pongsakorn Jirachanchaisiri,

Nam Tuan Ly,

Atsuhiro Takasu; [pdf]
[bibtex]
@InProceedings{Jirachanchaisiri_2025_WACV, author = {Jirachanchaisiri, Pongsakorn and Ly, Nam Tuan and Takasu, Atsuhiro}, title = {TRH2TQA: Table Recognition with Hierarchical Relationships to Table Question-Answering on Business Table Images}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8826-8834} }
Beta Sampling is All You Need: Efficient Image Generation Strategy for Diffusion Models using Stepwise Spectral Analysis: Haeil Lee,

Hansang Lee,

Seoyeon Gye,

Junmo Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2025_WACV, author = {Lee, Haeil and Lee, Hansang and Gye, Seoyeon and Kim, Junmo}, title = {Beta Sampling is All You Need: Efficient Image Generation Strategy for Diffusion Models using Stepwise Spectral Analysis}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4215-4224} }
GAUDA: Generative Adaptive Uncertainty-Guided Diffusion-Based Augmentation for Surgical Segmentation: Yannik Frisch,

Christina Bornberg,

Moritz Fuchs,

Anirban Mukhopadhyay; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Frisch_2025_WACV, author = {Frisch, Yannik and Bornberg, Christina and Fuchs, Moritz and Mukhopadhyay, Anirban}, title = {GAUDA: Generative Adaptive Uncertainty-Guided Diffusion-Based Augmentation for Surgical Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3762-3771} }
Multi-Task Learning of Classification and Generation for Set-Structured Data: Fumioki Sato,

Hideaki Hayashi,

Hajime Nagahara; [pdf] [supp]
[bibtex]
@InProceedings{Sato_2025_WACV, author = {Sato, Fumioki and Hayashi, Hideaki and Nagahara, Hajime}, title = {Multi-Task Learning of Classification and Generation for Set-Structured Data}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6741-6751} }
TaCOS: Task-Specific Camera Optimization with Simulation: Chengyang Yan,

Donald G. Dansereau; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yan_2025_WACV, author = {Yan, Chengyang and Dansereau, Donald G.}, title = {TaCOS: Task-Specific Camera Optimization with Simulation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2052-2062} }
SAM-Mamba: Mamba Guided SAM Architecture for Generalized Zero-Shot Polyp Segmentation: Tapas Kumar Dutta,

Snehashis Majhi,

Deepak Ranjan Nayak,

Debesh Jha; [pdf] [supp]
[bibtex]
@InProceedings{Dutta_2025_WACV, author = {Dutta, Tapas Kumar and Majhi, Snehashis and Nayak, Deepak Ranjan and Jha, Debesh}, title = {SAM-Mamba: Mamba Guided SAM Architecture for Generalized Zero-Shot Polyp Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4655-4664} }
KDC-MAE: Knowledge Distilled Contrastive Mask Auto-Encoder: Maheswar Bora,

Saurabh Atreya,

Aritra Mukherjee,

Abhijit Das; [pdf]
[bibtex]
@InProceedings{Bora_2025_WACV, author = {Bora, Maheswar and Atreya, Saurabh and Mukherjee, Aritra and Das, Abhijit}, title = {KDC-MAE: Knowledge Distilled Contrastive Mask Auto-Encoder}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7511-7521} }
Corgi: Cached Memory Guided Video Generation: Xindi Wu,

Uriel Singer,

Zhaojiang Lin,

Andrea Madotto,

Xide Xia,

Yifan Xu,

Paul Crook,

Xin Luna Dong,

Seungwhan Moon; [pdf] [supp]
[bibtex]
@InProceedings{Wu_2025_WACV, author = {Wu, Xindi and Singer, Uriel and Lin, Zhaojiang and Madotto, Andrea and Xia, Xide and Xu, Yifan and Crook, Paul and Dong, Xin Luna and Moon, Seungwhan}, title = {Corgi: Cached Memory Guided Video Generation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4585-4594} }
I Dream My Painting: Connecting MLLMs and Diffusion Models via Prompt Generation for Text-Guided Multi-Mask Inpainting: Nicola Fanelli,

Gennaro Vessio,

Giovanna Castellano; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fanelli_2025_WACV, author = {Fanelli, Nicola and Vessio, Gennaro and Castellano, Giovanna}, title = {I Dream My Painting: Connecting MLLMs and Diffusion Models via Prompt Generation for Text-Guided Multi-Mask Inpainting}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6073-6082} }
CATALOG: A Camera Trap Language-Guided Contrastive Learning Model: Julian D. Santamaria,

Claudia Isaza,

Jhony H. Giraldo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Santamaria_2025_WACV, author = {Santamaria, Julian D. and Isaza, Claudia and Giraldo, Jhony H.}, title = {CATALOG: A Camera Trap Language-Guided Contrastive Learning Model}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1197-1206} }
Patch Ranking: Token Pruning as Ranking Prediction for Efficient CLIP: Cheng-En Wu,

Jinhong Lin,

Yu Hen Hu,

Pedro Morgado; [pdf] [supp]
[bibtex]
@InProceedings{Wu_2025_WACV, author = {Wu, Cheng-En and Lin, Jinhong and Hu, Yu Hen and Morgado, Pedro}, title = {Patch Ranking: Token Pruning as Ranking Prediction for Efficient CLIP}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5842-5851} }
Refining Text-to-Image Generation: Towards Accurate Training-Free Glyph-Enhanced Image Generation: Sanyam Lakhanpal,

Shivang Chopra,

Vinija Jain,

Aman Chadha,

Man Luo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lakhanpal_2025_WACV, author = {Lakhanpal, Sanyam and Chopra, Shivang and Jain, Vinija and Chadha, Aman and Luo, Man}, title = {Refining Text-to-Image Generation: Towards Accurate Training-Free Glyph-Enhanced Image Generation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4372-4381} }
CLIPArTT: Adaptation of CLIP to New Domains at Test Time: Gustavo A Vargas Hakim,

David Osowiechi,

Mehrdad Noori,

Milad Cheraghalikhani,

Ali Bahri,

Moslem Yazdanpanah,

Ismail Ben Ayed,

Christian Desrosiers; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{A_Vargas_Hakim_2025_WACV, author = {A Vargas Hakim, Gustavo and Osowiechi, David and Noori, Mehrdad and Cheraghalikhani, Milad and Bahri, Ali and Yazdanpanah, Moslem and Ben Ayed, Ismail and Desrosiers, Christian}, title = {CLIPArTT: Adaptation of CLIP to New Domains at Test Time}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7092-7101} }
Crafting Distribution Shifts for Validation and Training in Single Source Domain Generalization: Nikos Efthymiadis,

Giorgos Tolias,

Ondřej Chum; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Efthymiadis_2025_WACV, author = {Efthymiadis, Nikos and Tolias, Giorgos and Chum, Ond\v{r}ej}, title = {Crafting Distribution Shifts for Validation and Training in Single Source Domain Generalization}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1883-1892} }
High-Fidelity Document Stain Removal via A Large-Scale Real-World Dataset and A Memory-Augmented Transformer: Mingxian Li,

Hao Sun,

Yingtie Lei,

Xiaofeng Zhang,

Yihang Dong,

Yilin Zhou,

Zimeng Li,

Xuhang Chen; [pdf] [arXiv]
[bibtex]
@InProceedings{Li_2025_WACV, author = {Li, Mingxian and Sun, Hao and Lei, Yingtie and Zhang, Xiaofeng and Dong, Yihang and Zhou, Yilin and Li, Zimeng and Chen, Xuhang}, title = {High-Fidelity Document Stain Removal via A Large-Scale Real-World Dataset and A Memory-Augmented Transformer}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7603-7613} }
Distillation of Diffusion Features for Semantic Correspondence: Frank Fundel,

Johannes Schusterbauer,

Vincent Tao Hu,

Björn Ommer; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fundel_2025_WACV, author = {Fundel, Frank and Schusterbauer, Johannes and Hu, Vincent Tao and Ommer, Bj\"orn}, title = {Distillation of Diffusion Features for Semantic Correspondence}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6762-6774} }
Clarity Amidst Blur: A Deterministic Method for Synthetic Generation of Water Droplets on Camera Lenses: Tim Dieter Eberhardt,

Tim Brühl,

Robin Schwager,

Tin Stribor Sohn,

Wilhelm Stork; [pdf]
[bibtex]
@InProceedings{Eberhardt_2025_WACV, author = {Eberhardt, Tim Dieter and Br\"uhl, Tim and Schwager, Robin and Sohn, Tin Stribor and Stork, Wilhelm}, title = {Clarity Amidst Blur: A Deterministic Method for Synthetic Generation of Water Droplets on Camera Lenses}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5187-5196} }
A Pipeline and NIR-Enhanced Dataset for Parking Lot Segmentation: Shirin Qiam,

Saipraneeth Devunuri,

Lewis J. Lehe; [pdf] [arXiv]
[bibtex]
@InProceedings{Qiam_2025_WACV, author = {Qiam, Shirin and Devunuri, Saipraneeth and Lehe, Lewis J.}, title = {A Pipeline and NIR-Enhanced Dataset for Parking Lot Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1227-1236} }
A Realistic Protocol for Evaluation of Weakly Supervised Object Localization: Shakeeb Murtaza,

Soufiane Belharbi,

Marco Pedersoli,

Eric Granger; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Murtaza_2025_WACV, author = {Murtaza, Shakeeb and Belharbi, Soufiane and Pedersoli, Marco and Granger, Eric}, title = {A Realistic Protocol for Evaluation of Weakly Supervised Object Localization}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5367-5376} }
AlignIT: Enhancing Prompt Alignment in Customization of Text-to-Image Models: Aishwarya Agarwal,

Srikrishna Karanam,

Balaji Vasan Srinivasan; [pdf] [arXiv]
[bibtex]
@InProceedings{Agarwal_2025_WACV, author = {Agarwal, Aishwarya and Karanam, Srikrishna and Srinivasan, Balaji Vasan}, title = {AlignIT: Enhancing Prompt Alignment in Customization of Text-to-Image Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4882-4890} }
DiffuseKronA: A Parameter Efficient Fine-Tuning Method for Personalized Diffusion Models: Shyam Marjit,

Harshit Singh,

Nityanand Mathur,

Sayak Paul,

Chia-Mu Yu,

Pin-Yu Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Marjit_2025_WACV, author = {Marjit, Shyam and Singh, Harshit and Mathur, Nityanand and Paul, Sayak and Yu, Chia-Mu and Chen, Pin-Yu}, title = {DiffuseKronA: A Parameter Efficient Fine-Tuning Method for Personalized Diffusion Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3529-3538} }
Effective Backdoor Learning on Open-Set Face Recognition Systems: Diana Voth,

Leonidas Dane,

Jonas Grebe,

Sebastian Peitz,

Philipp Terhörst; [pdf] [supp]
[bibtex]
@InProceedings{Voth_2025_WACV, author = {Voth, Diana and Dane, Leonidas and Grebe, Jonas and Peitz, Sebastian and Terh\"orst, Philipp}, title = {Effective Backdoor Learning on Open-Set Face Recognition Systems}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1027-1039} }
Uncertainty Aware Interest Point Detection and Description: Jingbo Zeng,

Zaiwang Gu,

Weide Liu,

Lile Cai,

Jun Cheng; [pdf]
[bibtex]
@InProceedings{Zeng_2025_WACV, author = {Zeng, Jingbo and Gu, Zaiwang and Liu, Weide and Cai, Lile and Cheng, Jun}, title = {Uncertainty Aware Interest Point Detection and Description}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2144-2153} }
Strategic Base Representation Learning via Feature Augmentations for Few-Shot Class Incremental Learning: Parinita Nema,

Vinod K Kurmi; [pdf] [arXiv]
[bibtex]
@InProceedings{Nema_2025_WACV, author = {Nema, Parinita and Kurmi, Vinod K}, title = {Strategic Base Representation Learning via Feature Augmentations for Few-Shot Class Incremental Learning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6394-6403} }
Adaptive Deviation Learning for Visual Anomaly Detection with Data Contamination: Anindya Sundar Das,

Guansong Pang,

Monowar Bhuyan; [pdf] [arXiv]
[bibtex]
@InProceedings{Das_2025_WACV, author = {Das, Anindya Sundar and Pang, Guansong and Bhuyan, Monowar}, title = {Adaptive Deviation Learning for Visual Anomaly Detection with Data Contamination}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8845-8854} }
Self-Relaxed Joint Training: Sample Selection for Severity Estimation with Ordinal Noisy Labels: Shumpei Takezaki,

Kiyohito Tanaka,

Seiichi Uchida; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Takezaki_2025_WACV, author = {Takezaki, Shumpei and Tanaka, Kiyohito and Uchida, Seiichi}, title = {Self-Relaxed Joint Training: Sample Selection for Severity Estimation with Ordinal Noisy Labels}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {368-377} }
Learning Anatomy-Disease Entangled Representation: Fatemeh Haghighi,

Michael B. Gotway,

Jianming Liang; [pdf] [supp]
[bibtex]
@InProceedings{Haghighi_2025_WACV, author = {Haghighi, Fatemeh and Gotway, Michael B. and Liang, Jianming}, title = {Learning Anatomy-Disease Entangled Representation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4129-4141} }
MemControl: Mitigating Memorization in Diffusion Models via Automated Parameter Selection: Raman Dutt,

Ondrej Bohdal,

Pedro Sanchez,

Sotirios Tsaftaris,

Timothy Hospedales; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dutt_2025_WACV, author = {Dutt, Raman and Bohdal, Ondrej and Sanchez, Pedro and Tsaftaris, Sotirios and Hospedales, Timothy}, title = {MemControl: Mitigating Memorization in Diffusion Models via Automated Parameter Selection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4491-4501} }
Recognizing Unseen States of Unknown Objects by Leveraging Knowledge Graphs: Filippos Gouidis,

Konstantinos Papoutsakis,

Theodore Patkos,

Antonis Argyros,

Dimitris Plexousakis; [pdf] [supp]
[bibtex]
@InProceedings{Gouidis_2025_WACV, author = {Gouidis, Filippos and Papoutsakis, Konstantinos and Patkos, Theodore and Argyros, Antonis and Plexousakis, Dimitris}, title = {Recognizing Unseen States of Unknown Objects by Leveraging Knowledge Graphs}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8637-8648} }
SynDRA: Synthetic Dataset for Railway Applications: Gianluca D'Amico,

Federico Nesti,

Giulio Rossolini,

Mauro Marinoni,

Salvatore Sabina,

Giorgio Buttazzo; [pdf] [supp]
[bibtex]
@InProceedings{D'Amico_2025_WACV, author = {D'Amico, Gianluca and Nesti, Federico and Rossolini, Giulio and Marinoni, Mauro and Sabina, Salvatore and Buttazzo, Giorgio}, title = {SynDRA: Synthetic Dataset for Railway Applications}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3437-3446} }
VISIONARY: Novel Spatial-Spectral Attention Mechanism for Hyperspectral Image Denoising: Aditya Dixit,

Nischit Hosamani,

Puneet Gupta,

Ankur Garg; [pdf] [supp]
[bibtex]
@InProceedings{Dixit_2025_WACV, author = {Dixit, Aditya and Hosamani, Nischit and Gupta, Puneet and Garg, Ankur}, title = {VISIONARY: Novel Spatial-Spectral Attention Mechanism for Hyperspectral Image Denoising}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2736-2745} }
TPD-STR: Text Polygon Detection with Split Transformers: Sangyeon Kim,

Sangkuk Lee,

Jeesoo Kim,

Nojun Kwak; [pdf]
[bibtex]
@InProceedings{Kim_2025_WACV, author = {Kim, Sangyeon and Lee, Sangkuk and Kim, Jeesoo and Kwak, Nojun}, title = {TPD-STR: Text Polygon Detection with Split Transformers}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8940-8949} }
ReC-TTT: Contrastive Feature Reconstruction for Test-Time Training: Marco Colussi,

Sergio Mascetti,

Jose Dolz,

Christian Desrosiers; [pdf] [supp]
[bibtex]
@InProceedings{Colussi_2025_WACV, author = {Colussi, Marco and Mascetti, Sergio and Dolz, Jose and Desrosiers, Christian}, title = {ReC-TTT: Contrastive Feature Reconstruction for Test-Time Training}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6699-6708} }
Effective Scene Graph Generation by Statistical Relation Distillation: Thanh-Son Nguyen,

Hong Yang,

Basura Fernando; [pdf] [supp]
[bibtex]
@InProceedings{Nguyen_2025_WACV, author = {Nguyen, Thanh-Son and Yang, Hong and Fernando, Basura}, title = {Effective Scene Graph Generation by Statistical Relation Distillation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8409-8419} }
Cross Image Feature Perturbation with Pseudo Label Fusion for Semi-Supervised Medical Image Segmentation: Minxia Xu,

Han Yang,

Bo Song,

Weida Hu,

Jinshui Miao,

Erkang Cheng; [pdf]
[bibtex]
@InProceedings{Xu_2025_WACV, author = {Xu, Minxia and Yang, Han and Song, Bo and Hu, Weida and Miao, Jinshui and Cheng, Erkang}, title = {Cross Image Feature Perturbation with Pseudo Label Fusion for Semi-Supervised Medical Image Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7337-7347} }
DeCLIP: Decoding CLIP Representations for Deepfake Localization: Stefan Smeu,

Elisabeta Oneata,

Dan Oneata; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Smeu_2025_WACV, author = {Smeu, Stefan and Oneata, Elisabeta and Oneata, Dan}, title = {DeCLIP: Decoding CLIP Representations for Deepfake Localization}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {149-159} }
Instance-Warp: Saliency Guided Image Warping for Unsupervised Domain Adaptation: Shen Zheng,

Anurag Ghosh,

Srinivasa Narasimhan; [pdf] [supp]
[bibtex]
@InProceedings{Zheng_2025_WACV, author = {Zheng, Shen and Ghosh, Anurag and Narasimhan, Srinivasa}, title = {Instance-Warp: Saliency Guided Image Warping for Unsupervised Domain Adaptation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8186-8195} }
ZAHA: Introducing the Level of Facade Generalization and the Large-Scale Point Cloud Facade Semantic Segmentation Benchmark Dataset: Olaf Wysocki,

Yue Tan,

Thomas Froech,

Yan Xia,

Magdalena Wysocki,

Ludwig Hoegner,

Daniel Cremers,

Christoph Holst; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wysocki_2025_WACV, author = {Wysocki, Olaf and Tan, Yue and Froech, Thomas and Xia, Yan and Wysocki, Magdalena and Hoegner, Ludwig and Cremers, Daniel and Holst, Christoph}, title = {ZAHA: Introducing the Level of Facade Generalization and the Large-Scale Point Cloud Facade Semantic Segmentation Benchmark Dataset}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7637-7647} }
Make-A-Texture: Fast Shape-Aware 3D Texture Generation in 3 Seconds: Liat Sless Gorelik,

Yuchen Fan,

Omri Armstrong,

Forrest N Iandola,

Yilei Li,

Ita Lifshitz,

Rakesh Ranjan; [pdf]
[bibtex]
@InProceedings{Gorelik_2025_WACV, author = {Gorelik, Liat Sless and Fan, Yuchen and Armstrong, Omri and Iandola, Forrest N and Li, Yilei and Lifshitz, Ita and Ranjan, Rakesh}, title = {Make-A-Texture: Fast Shape-Aware 3D Texture Generation in 3 Seconds}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4872-4881} }
PRoGS: Progressive Rendering of Gaussian Splats: Brent Zoomers,

Maarten Wijnants,

Ivan Molenaers,

Joni Vanherck,

Jeroen Put,

Lode Jorissen,

Nick Michiels; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zoomers_2025_WACV, author = {Zoomers, Brent and Wijnants, Maarten and Molenaers, Ivan and Vanherck, Joni and Put, Jeroen and Jorissen, Lode and Michiels, Nick}, title = {PRoGS: Progressive Rendering of Gaussian Splats}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3118-3127} }
SynDroneVision: A Synthetic Dataset for Image-Based Drone Detection: Tamara R. Lenhard,

Andreas Weinmann,

Kai Franke,

Tobias Koch; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lenhard_2025_WACV, author = {Lenhard, Tamara R. and Weinmann, Andreas and Franke, Kai and Koch, Tobias}, title = {SynDroneVision: A Synthetic Dataset for Image-Based Drone Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7626-7636} }
Distribution Optimization under Gaussian Hypothesis for Domain Adaptive Semantic Segmentation: Chen Liang,

Weihua Chen,

Xin Zhao,

Junyan Wang,

Lijun Cao,

Junge Zhang; [pdf]
[bibtex]
@InProceedings{Liang_2025_WACV, author = {Liang, Chen and Chen, Weihua and Zhao, Xin and Wang, Junyan and Cao, Lijun and Zhang, Junge}, title = {Distribution Optimization under Gaussian Hypothesis for Domain Adaptive Semantic Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9262-9272} }
Utilizing Uncertainty in 2D Pose Detectors for Probabilistic 3D Human Mesh Recovery: Tom Wehrbein,

Marco Rudolph,

Bodo Rosenhahn,

Bastian Wandt; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wehrbein_2025_WACV, author = {Wehrbein, Tom and Rudolph, Marco and Rosenhahn, Bodo and Wandt, Bastian}, title = {Utilizing Uncertainty in 2D Pose Detectors for Probabilistic 3D Human Mesh Recovery}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5852-5862} }
Comparative Evaluation of 3D Reconstruction Methods for Object Pose Estimation: Varun Burde,

Assia Benbihi,

Pavel Burget,

Torsten Sattler; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Burde_2025_WACV, author = {Burde, Varun and Benbihi, Assia and Burget, Pavel and Sattler, Torsten}, title = {Comparative Evaluation of 3D Reconstruction Methods for Object Pose Estimation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7658-7670} }
Re-Identifying People in Video via Learned Temporal Attention and Multi-Modal Foundation Models: Cole Hill,

Florence Yellin,

Krishna Regmi,

Dawei Du,

Scott McCloskey; [pdf] [supp]
[bibtex]
@InProceedings{Hill_2025_WACV, author = {Hill, Cole and Yellin, Florence and Regmi, Krishna and Du, Dawei and McCloskey, Scott}, title = {Re-Identifying People in Video via Learned Temporal Attention and Multi-Modal Foundation Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6259-6268} }
GET-UP: GEomeTric-Aware Depth Estimation with Radar Points UPsampling: Huawei Sun,

Zixu Wang,

Hao Feng,

Julius Ott,

Lorenzo Servadei,

Robert Wille; [pdf] [supp]
[bibtex]
@InProceedings{Sun_2025_WACV, author = {Sun, Huawei and Wang, Zixu and Feng, Hao and Ott, Julius and Servadei, Lorenzo and Wille, Robert}, title = {GET-UP: GEomeTric-Aware Depth Estimation with Radar Points UPsampling}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1850-1860} }
Detecting Origin Attribution for Text-to-Image Diffusion Models: Katherine Xu,

Lingzhi Zhang,

Jianbo Shi; [pdf] [supp]
[bibtex]
@InProceedings{Xu_2025_WACV, author = {Xu, Katherine and Zhang, Lingzhi and Shi, Jianbo}, title = {Detecting Origin Attribution for Text-to-Image Diffusion Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8764-8774} }
SALVE: A 3D Reconstruction Benchmark of Wounds from Consumer-Grade Videos: Remi Chierchia,

Leo Lebrat,

David Ahmedt-Aristizabal,

Olivier Salvado,

Clinton Fookes,

Rodrigo Santa Cruz; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chierchia_2025_WACV, author = {Chierchia, Remi and Lebrat, Leo and Ahmedt-Aristizabal, David and Salvado, Olivier and Fookes, Clinton and Cruz, Rodrigo Santa}, title = {SALVE: A 3D Reconstruction Benchmark of Wounds from Consumer-Grade Videos}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4205-4214} }
Hierarchical Light Transformer Ensembles for Multimodal Trajectory Forecasting: Adrien Lafage,

Mathieu Barbier,

Gianni Franchi,

David Filliat; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lafage_2025_WACV, author = {Lafage, Adrien and Barbier, Mathieu and Franchi, Gianni and Filliat, David}, title = {Hierarchical Light Transformer Ensembles for Multimodal Trajectory Forecasting}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1682-1691} }
Compositional Segmentation of Cardiac Images Leveraging Metadata: Abbas Khan,

Muhammad Asad,

Martin Benning,

Caroline Roney,

Gregory Slabaugh; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Khan_2025_WACV, author = {Khan, Abbas and Asad, Muhammad and Benning, Martin and Roney, Caroline and Slabaugh, Gregory}, title = {Compositional Segmentation of Cardiac Images Leveraging Metadata}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9471-9480} }
Instructive3D: Editing Large Reconstruction Models with Text Instructions: Kunal Kathare,

Ankit Dhiman,

K Vikas Gowda,

Siddharth Aravindan,

Shubham Monga,

Basavaraja Shanthappa Vandrotti,

Lokesh R Boregowda; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kathare_2025_WACV, author = {Kathare, Kunal and Dhiman, Ankit and Gowda, K Vikas and Aravindan, Siddharth and Monga, Shubham and Vandrotti, Basavaraja Shanthappa and Boregowda, Lokesh R}, title = {Instructive3D: Editing Large Reconstruction Models with Text Instructions}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3246-3256} }
PVP: Polar Representation Boost for 3D Semantic Occupancy Prediction: Yujing Xue,

Jiaxiang Liu,

Jiawei Du,

Joey Tianyi Zhou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xue_2025_WACV, author = {Xue, Yujing and Liu, Jiaxiang and Du, Jiawei and Zhou, Joey Tianyi}, title = {PVP: Polar Representation Boost for 3D Semantic Occupancy Prediction}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2746-2755} }
TempA-VLP: Temporal-Aware Vision-Language Pretraining for Longitudinal Exploration in Chest X-ray Image: Zhuoyi Yang,

Liyue Shen; [pdf]
[bibtex]
@InProceedings{Yang_2025_WACV, author = {Yang, Zhuoyi and Shen, Liyue}, title = {TempA-VLP: Temporal-Aware Vision-Language Pretraining for Longitudinal Exploration in Chest X-ray Image}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4625-4634} }
SpotDiffusion: A Fast Approach for Seamless Panorama Generation Over Time: Stanislav Frolov,

Brian B. Moser,

Andreas Dengel; [pdf] [arXiv]
[bibtex]
@InProceedings{Frolov_2025_WACV, author = {Frolov, Stanislav and Moser, Brian B. and Dengel, Andreas}, title = {SpotDiffusion: A Fast Approach for Seamless Panorama Generation Over Time}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2073-2081} }
OccLoff: Learning Optimized Feature Fusion for 3D Occupancy Prediction: Ji Zhang,

Yiran Ding,

Zixin Liu; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2025_WACV, author = {Zhang, Ji and Ding, Yiran and Liu, Zixin}, title = {OccLoff: Learning Optimized Feature Fusion for 3D Occupancy Prediction}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3096-3106} }
Beyond Spatial Explanations: Explainable Face Recognition in the Frequency Domain: Marco Huber,

Naser Damer; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huber_2025_WACV, author = {Huber, Marco and Damer, Naser}, title = {Beyond Spatial Explanations: Explainable Face Recognition in the Frequency Domain}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1016-1026} }
A Conflict-Guided Evidential Multimodal Fusion for Semantic Segmentation: Lucas Deregnaucourt,

Hind Laghmara,

Alexis Lechervy,

Samia Ainouz; [pdf]
[bibtex]
@InProceedings{Deregnaucourt_2025_WACV, author = {Deregnaucourt, Lucas and Laghmara, Hind and Lechervy, Alexis and Ainouz, Samia}, title = {A Conflict-Guided Evidential Multimodal Fusion for Semantic Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1373-1382} }
Elucidating Optimal Reward-Diversity Tradeoffs in Text-to-Image Diffusion Models: Rohit Jena,

Ali Taghibakhshi,

Sahil Jain,

Gerald Shen,

Nima Tajbakhsh,

Arash Vahdat; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jena_2025_WACV, author = {Jena, Rohit and Taghibakhshi, Ali and Jain, Sahil and Shen, Gerald and Tajbakhsh, Nima and Vahdat, Arash}, title = {Elucidating Optimal Reward-Diversity Tradeoffs in Text-to-Image Diffusion Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {232-242} }
Are Exemplar-Based Class Incremental Learning Models Victim of Black-Box Poison Attacks?: Neeresh Kumar Perla,

Md. Iqbal Hossain,

Afia Sajeeda,

Ming Shao; [pdf] [supp]
[bibtex]
@InProceedings{Perla_2025_WACV, author = {Perla, Neeresh Kumar and Hossain, Md. Iqbal and Sajeeda, Afia and Shao, Ming}, title = {Are Exemplar-Based Class Incremental Learning Models Victim of Black-Box Poison Attacks?}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6785-6794} }
CLIPping Imbalances: A Novel Evaluation Baseline and PEARL Dataset for Pedestrian Attribute Recognition: Kamalakar Vijay,

Lalit Lohani,

Kamakshya Prasad Nayak,

Debi Prosad Dogra,

Heeseung Choi,

Hyungjoo Jung,

Ig-Jae Kim; [pdf] [supp]
[bibtex]
@InProceedings{Vijay_2025_WACV, author = {Vijay, Kamalakar and Lohani, Lalit and Nayak, Kamakshya Prasad and Dogra, Debi Prosad and Choi, Heeseung and Jung, Hyungjoo and Kim, Ig-Jae}, title = {CLIPping Imbalances: A Novel Evaluation Baseline and PEARL Dataset for Pedestrian Attribute Recognition}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7102-7111} }
Exploring the Stability Gap in Continual Learning: The Role of the Classification Head: Wojciech Łapacz,

Daniel Marczak,

Filip Szatkowski,

Tomasz Trzciński; [pdf] [supp]
[bibtex]
@InProceedings{Lapacz_2025_WACV, author = {{\L}apacz, Wojciech and Marczak, Daniel and Szatkowski, Filip and Trzci\'nski, Tomasz}, title = {Exploring the Stability Gap in Continual Learning: The Role of the Classification Head}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7551-7560} }
Bayesian Optimal Latent Projection for Noisy Image Restoration: Ziqiang Shi,

Rujie Liu,

Jun Takahashi,

Takuma Yamamoto; [pdf] [supp]
[bibtex]
@InProceedings{Shi_2025_WACV, author = {Shi, Ziqiang and Liu, Rujie and Takahashi, Jun and Yamamoto, Takuma}, title = {Bayesian Optimal Latent Projection for Noisy Image Restoration}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2799-2807} }
Towards a Training Free Approach for 3D Scene Editing: Vivek Madhavaram,

Shivangana Rawat,

Chaitanya Devaguptapu,

Charu Sharma,

Manohar Kaul; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Madhavaram_2025_WACV, author = {Madhavaram, Vivek and Rawat, Shivangana and Devaguptapu, Chaitanya and Sharma, Charu and Kaul, Manohar}, title = {Towards a Training Free Approach for 3D Scene Editing}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2890-2899} }
Self-Supervised Learning with Probabilistic Density Labeling for Rainfall Probability Estimation: Junha Lee,

Sojung An,

Sujeong You,

Namik Cho; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2025_WACV, author = {Lee, Junha and An, Sojung and You, Sujeong and Cho, Namik}, title = {Self-Supervised Learning with Probabilistic Density Labeling for Rainfall Probability Estimation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5560-5569} }
STAY Diffusion: Styled Layout Diffusion Model for Diverse Layout-to-Image Generation: Ruyu Wang,

Xuefeng Hou,

Sabrina Schmedding,

Marco Huber; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2025_WACV, author = {Wang, Ruyu and Hou, Xuefeng and Schmedding, Sabrina and Huber, Marco}, title = {STAY Diffusion: Styled Layout Diffusion Model for Diverse Layout-to-Image Generation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3855-3865} }
Learning to Count from Pseudo-Labeled Segmentation: Jingyi Xu,

Hieu Le,

Dimitris Samaras; [pdf] [supp]
[bibtex]
@InProceedings{Xu_2025_WACV, author = {Xu, Jingyi and Le, Hieu and Samaras, Dimitris}, title = {Learning to Count from Pseudo-Labeled Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8743-8752} }
Text-to-Image Synthesis for Domain Generalization in Face Anti-Spoofing: Naeun Ko,

Yonghyun Jeong,

Jong Chul Ye; [pdf] [supp]
[bibtex]
@InProceedings{Ko_2025_WACV, author = {Ko, Naeun and Jeong, Yonghyun and Ye, Jong Chul}, title = {Text-to-Image Synthesis for Domain Generalization in Face Anti-Spoofing}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6340-6350} }
Generalizable Single-Source Cross-Modality Medical Image Segmentation via Invariant Causal Mechanisms: Boqi Chen,

Yuanzhi Zhu,

Yunke Ao,

Sebastiano Caprara,

Reto Sutter,

Gunnar Rätsch,

Ender Konukoglu,

Anna Susmelj; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2025_WACV, author = {Chen, Boqi and Zhu, Yuanzhi and Ao, Yunke and Caprara, Sebastiano and Sutter, Reto and R\"atsch, Gunnar and Konukoglu, Ender and Susmelj, Anna}, title = {Generalizable Single-Source Cross-Modality Medical Image Segmentation via Invariant Causal Mechanisms}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3592-3602} }
Combining Inherent Knowledge of Vision-Language Models with Unsupervised Domain Adaptation through Strong-Weak Guidance: Thomas Westfechtel,

Dexuan Zhang,

Tatsuya Harada; [pdf] [arXiv]
[bibtex]
@InProceedings{Westfechtel_2025_WACV, author = {Westfechtel, Thomas and Zhang, Dexuan and Harada, Tatsuya}, title = {Combining Inherent Knowledge of Vision-Language Models with Unsupervised Domain Adaptation through Strong-Weak Guidance}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6528-6537} }
Text Change Detection in Multilingual Documents using Image Comparison: Doyoung Park,

Naresh Reddy Yarram,

Sunjin Kim,

MinKyu Kim,

Seongho Joe,

Taehee Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Park_2025_WACV, author = {Park, Doyoung and Yarram, Naresh Reddy and Kim, Sunjin and Kim, MinKyu and Joe, Seongho and Lee, Taehee}, title = {Text Change Detection in Multilingual Documents using Image Comparison}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5218-5227} }
ComFace: Facial Representation Learning with Synthetic Data for Comparing Faces: Yusuke Akamatsu,

Terumi Umematsu,

Hitoshi Imaoka,

Shizuko Gomi,

Hideo Tsurushima; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Akamatsu_2025_WACV, author = {Akamatsu, Yusuke and Umematsu, Terumi and Imaoka, Hitoshi and Gomi, Shizuko and Tsurushima, Hideo}, title = {ComFace: Facial Representation Learning with Synthetic Data for Comparing Faces}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5263-5273} }
Click&Describe: Multimodal Grounding and Tracking for Aerial Objects: Rupanjali Kukal,

Jay Patravali,

Fuxun Yu,

Simranjit Singh,

Nikolaos Karianakis,

Rishi Madhok; [pdf] [supp]
[bibtex]
@InProceedings{Kukal_2025_WACV, author = {Kukal, Rupanjali and Patravali, Jay and Yu, Fuxun and Singh, Simranjit and Karianakis, Nikolaos and Madhok, Rishi}, title = {Click\&Describe: Multimodal Grounding and Tracking for Aerial Objects}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6011-6021} }
Disentangling Disentangled Representations: Towards Improved Latent Units via Diffusion Models: Youngjun Jun,

Jiwoo Park,

Kyobin Choo,

Tae Eun Choi,

Seong Jae Hwang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jun_2025_WACV, author = {Jun, Youngjun and Park, Jiwoo and Choo, Kyobin and Choi, Tae Eun and Hwang, Seong Jae}, title = {Disentangling Disentangled Representations: Towards Improved Latent Units via Diffusion Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3559-3569} }
XR-MBT: Multi-Modal Full Body Tracking for XR through Self-Supervision with Learned Depth Point Cloud Registration: Denys Rozumnyi,

Nadine Bertsch,

Othman Sbai,

Filippo Arcadu,

Yuhua Chen,

Artsiom Sanakoyeu,

Manoj Kumar,

Catherine Herold,

Robin Kips; [pdf] [supp]
[bibtex]
@InProceedings{Rozumnyi_2025_WACV, author = {Rozumnyi, Denys and Bertsch, Nadine and Sbai, Othman and Arcadu, Filippo and Chen, Yuhua and Sanakoyeu, Artsiom and Kumar, Manoj and Herold, Catherine and Kips, Robin}, title = {XR-MBT: Multi-Modal Full Body Tracking for XR through Self-Supervision with Learned Depth Point Cloud Registration}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5041-5050} }
SHIP: Structural Hierarchies for Instance-Dependent Partial Labels: Tushar Kadam,

Utkarsh Mishra,

Aakarsh Malhotra; [pdf]
[bibtex]
@InProceedings{Kadam_2025_WACV, author = {Kadam, Tushar and Mishra, Utkarsh and Malhotra, Aakarsh}, title = {SHIP: Structural Hierarchies for Instance-Dependent Partial Labels}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7256-7265} }
CEMIL: Contextual Attention Based Efficient Weakly Supervised Approach for Histopathology Image Classification: Tawsifur Rahman,

Alexander S. Baras,

Rama Chellappa; [pdf] [supp]
[bibtex]
@InProceedings{Rahman_2025_WACV, author = {Rahman, Tawsifur and Baras, Alexander S. and Chellappa, Rama}, title = {CEMIL: Contextual Attention Based Efficient Weakly Supervised Approach for Histopathology Image Classification}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4248-4257} }
A Novel Perspective for Multi-Modal Multi-Label Skin Lesion Classification: Yuan Zhang,

Yutong Xie,

Hu Wang,

Jodie C Avery,

M Louise Hull,

Gustavo Carneiro; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2025_WACV, author = {Zhang, Yuan and Xie, Yutong and Wang, Hu and Avery, Jodie C and Hull, M Louise and Carneiro, Gustavo}, title = {A Novel Perspective for Multi-Modal Multi-Label Skin Lesion Classification}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3549-3558} }
Dual-Schedule Inversion: Training- and Tuning-Free Inversion for Real Image Editing: Jiancheng Huang,

Yi Huang,

Jianzhuang Liu,

Donghao Zhou,

Yifan Liu,

Shifeng Chen; [pdf] [supp]
[bibtex]
@InProceedings{Huang_2025_WACV, author = {Huang, Jiancheng and Huang, Yi and Liu, Jianzhuang and Zhou, Donghao and Liu, Yifan and Chen, Shifeng}, title = {Dual-Schedule Inversion: Training- and Tuning-Free Inversion for Real Image Editing}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {660-669} }
Mind the Prompt: A Novel Benchmark for Prompt-Based Class-Agnostic Counting: Luca Ciampi,

Nicola Messina,

Matteo Pierucci,

Giuseppe Amato,

Marco Avvenuti,

Fabrizio Falchi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ciampi_2025_WACV, author = {Ciampi, Luca and Messina, Nicola and Pierucci, Matteo and Amato, Giuseppe and Avvenuti, Marco and Falchi, Fabrizio}, title = {Mind the Prompt: A Novel Benchmark for Prompt-Based Class-Agnostic Counting}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7959-7968} }
DLCR: A Generative Data Expansion Framework via Diffusion for Clothes-Changing Person Re-ID: Nyle Siddiqui,

Florinel Alin Croitoru,

Gaurav Kumar Nayak,

Radu Tudor Ionescu,

Mubarak Shah; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Siddiqui_2025_WACV, author = {Siddiqui, Nyle and Croitoru, Florinel Alin and Nayak, Gaurav Kumar and Ionescu, Radu Tudor and Shah, Mubarak}, title = {DLCR: A Generative Data Expansion Framework via Diffusion for Clothes-Changing Person Re-ID}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1608-1617} }
Diffusion-Based Particle-DETR for BEV Perception: Asen Nachkov,

Danda Pani Paudel,

Martin Danelljan,

Luc Van Gool; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nachkov_2025_WACV, author = {Nachkov, Asen and Paudel, Danda Pani and Danelljan, Martin and Van Gool, Luc}, title = {Diffusion-Based Particle-DETR for BEV Perception}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2725-2735} }
Enhancing Scene Graph Generation with Hierarchical Relationships and Commonsense Knowledge: Bowen Jiang,

Zhijun Zhuang,

Shreyas S. Shivakumar,

Camillo J. Taylor; [pdf] [arXiv]
[bibtex]
@InProceedings{Jiang_2025_WACV, author = {Jiang, Bowen and Zhuang, Zhijun and Shivakumar, Shreyas S. and Taylor, Camillo J.}, title = {Enhancing Scene Graph Generation with Hierarchical Relationships and Commonsense Knowledge}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8865-8876} }
Domain-Generalized Object Anti-Spoofing: Bridging Gaps and Patch Selection for Robust Detection Across Domains: Geonu Lee,

Yonghyun Jeong,

Haneol Jang,

Youngjoon Yoo; [pdf] [supp]
[bibtex]
@InProceedings{Lee_2025_WACV, author = {Lee, Geonu and Jeong, Yonghyun and Jang, Haneol and Yoo, Youngjoon}, title = {Domain-Generalized Object Anti-Spoofing: Bridging Gaps and Patch Selection for Robust Detection Across Domains}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8919-8928} }
VILLS : Video-Image Learning to Learn Semantics for Person Re-Identification: Siyuan Huang,

Ram Prabhakar Kathirvel,

Yuxiang Guo,

Rama Chellappa,

Cheng Peng; [pdf] [supp]
[bibtex]
@InProceedings{Huang_2025_WACV, author = {Huang, Siyuan and Kathirvel, Ram Prabhakar and Guo, Yuxiang and Chellappa, Rama and Peng, Cheng}, title = {VILLS : Video-Image Learning to Learn Semantics for Person Re-Identification}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5969-5979} }
ERUP-YOLO: Enhancing Object Detection Robustness for Adverse Weather Condition by Unified Image-Adaptive Processing: Yuka Ogino,

Yuho Shoji,

Takahiro Toizumi,

Atsushi Ito; [pdf] [supp]
[bibtex]
@InProceedings{Ogino_2025_WACV, author = {Ogino, Yuka and Shoji, Yuho and Toizumi, Takahiro and Ito, Atsushi}, title = {ERUP-YOLO: Enhancing Object Detection Robustness for Adverse Weather Condition by Unified Image-Adaptive Processing}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8586-8594} }
Conditional GAN for Enhancing Diffusion Models in Efficient and Authentic Global Gesture Generation from Audios: Yongkang Cheng,

Mingjiang Liang,

Shaoli Huang,

Gaoge Han,

Jifeng Ning,

Wei Liu; [pdf] [arXiv]
[bibtex]
@InProceedings{Cheng_2025_WACV, author = {Cheng, Yongkang and Liang, Mingjiang and Huang, Shaoli and Han, Gaoge and Ning, Jifeng and Liu, Wei}, title = {Conditional GAN for Enhancing Diffusion Models in Efficient and Authentic Global Gesture Generation from Audios}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2164-2173} }
PK-YOLO: Pretrained Knowledge Guided YOLO for Brain Tumor Detection in Multiplanar MRI Slices: Ming Kang,

Fung Fung Ting,

Raphael C.-W. Phan,

Chee-Ming Ting; [pdf]
[bibtex]
@InProceedings{Kang_2025_WACV, author = {Kang, Ming and Ting, Fung Fung and Phan, Raphael C.-W. and Ting, Chee-Ming}, title = {PK-YOLO: Pretrained Knowledge Guided YOLO for Brain Tumor Detection in Multiplanar MRI Slices}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3732-3741} }
When Cars Meet Drones: Hyperbolic Federated Learning for Source-Free Domain Adaptation in Adverse Weather: Giulia Rizzoli,

Matteo Caligiuri,

Donald Shenaj,

Francesco Barbato,

Pietro Zanuttigh; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Rizzoli_2025_WACV, author = {Rizzoli, Giulia and Caligiuri, Matteo and Shenaj, Donald and Barbato, Francesco and Zanuttigh, Pietro}, title = {When Cars Meet Drones: Hyperbolic Federated Learning for Source-Free Domain Adaptation in Adverse Weather}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1587-1596} }
I3D-AE-LSTM: A 2-Stream Autoencoder for Action Quality Assessment using a Newly Created Cricket Batsman Video Dataset: Tevin Moodley,

Dustin Terence van der Haar; [pdf] [supp]
[bibtex]
@InProceedings{Moodley_2025_WACV, author = {Moodley, Tevin and van der Haar, Dustin Terence}, title = {I3D-AE-LSTM: A 2-Stream Autoencoder for Action Quality Assessment using a Newly Created Cricket Batsman Video Dataset}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5470-5478} }
DDPM-CD: Denoising Diffusion Probabilistic Models as Feature Extractors for Remote Sensing Change Detection: Wele Gedara Chaminda Bandara,

Nithin Gopalakrishnan Nair,

Vishal Patel; [pdf] [supp]
[bibtex]
@InProceedings{Bandara_2025_WACV, author = {Bandara, Wele Gedara Chaminda and Nair, Nithin Gopalakrishnan and Patel, Vishal}, title = {DDPM-CD: Denoising Diffusion Probabilistic Models as Feature Extractors for Remote Sensing Change Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5250-5262} }
Generative Model-Based Fusion for Improved Few-Shot Semantic Segmentation of Infrared Images: Junno Yun,

Mehmet Akçakaya; [pdf] [supp]
[bibtex]
@InProceedings{Yun_2025_WACV, author = {Yun, Junno and Ak\c{c}akaya, Mehmet}, title = {Generative Model-Based Fusion for Improved Few-Shot Semantic Segmentation of Infrared Images}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5479-5488} }
Similarity over Factuality: Are we Making Progress on Multimodal Out-of-Context Misinformation Detection?: Stefanos-Iordanis Papadopoulos,

Christos Koutlis,

Symeon Papadopoulos,

Panagiotis C. Petrantonakis; [pdf] [arXiv]
[bibtex]
@InProceedings{Papadopoulos_2025_WACV, author = {Papadopoulos, Stefanos-Iordanis and Koutlis, Christos and Papadopoulos, Symeon and Petrantonakis, Panagiotis C.}, title = {Similarity over Factuality: Are we Making Progress on Multimodal Out-of-Context Misinformation Detection?}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5570-5579} }
CRAFT: Designing Creative and Functional 3D Objects: Michelle Guo,

Mia Tang,

Hannah Cha,

Ruohan Zhang,

C. Karen Liu,

Jiajun Wu; [pdf]
[bibtex]
@InProceedings{Guo_2025_WACV, author = {Guo, Michelle and Tang, Mia and Cha, Hannah and Zhang, Ruohan and Liu, C. Karen and Wu, Jiajun}, title = {CRAFT: Designing Creative and Functional 3D Objects}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7215-7224} }
EfficientCrackNet: A Lightweight Model for Crack Segmentation: Abid Hasan Zim,

Aquib Iqbal,

Zaid Al-Huda,

Asad Malik,

Minoru Kuribayashi; [pdf] [arXiv]
[bibtex]
@InProceedings{Zim_2025_WACV, author = {Zim, Abid Hasan and Iqbal, Aquib and Al-Huda, Zaid and Malik, Asad and Kuribayashi, Minoru}, title = {EfficientCrackNet: A Lightweight Model for Crack Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6279-6289} }
Multi-Level Feature Distillation of Joint Teachers Trained on Distinct Image Datasets: Adrian Iordache,

Bogdan Alexe,

Radu Tudor Ionescu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Iordache_2025_WACV, author = {Iordache, Adrian and Alexe, Bogdan and Ionescu, Radu Tudor}, title = {Multi-Level Feature Distillation of Joint Teachers Trained on Distinct Image Datasets}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7133-7142} }
Learning Multiple Object States from Actions via Large Language Models: Masatoshi Tateno,

Takuma Yagi,

Ryosuke Furuta,

Yoichi Sato; [pdf] [arXiv]
[bibtex]
@InProceedings{Tateno_2025_WACV, author = {Tateno, Masatoshi and Yagi, Takuma and Furuta, Ryosuke and Sato, Yoichi}, title = {Learning Multiple Object States from Actions via Large Language Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9537-9547} }
Balancing Shared and Task-Specific Representations: A Hybrid Approach to Depth-Aware Video Panoptic Segmentation: Kurt H.W. Stolle; [pdf] [arXiv]
[bibtex]
@InProceedings{Stolle_2025_WACV, author = {Stolle, Kurt H.W.}, title = {Balancing Shared and Task-Specific Representations: A Hybrid Approach to Depth-Aware Video Panoptic Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3301-3309} }
Cross-Aligned Fusion for Multimodal Understanding: Abhishek Rajora,

Shubham Gupta,

Suman Kundu; [pdf] [supp]
[bibtex]
@InProceedings{Rajora_2025_WACV, author = {Rajora, Abhishek and Gupta, Shubham and Kundu, Suman}, title = {Cross-Aligned Fusion for Multimodal Understanding}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5730-5740} }
CorrFill: Enhancing Faithfulness in Reference-Based Inpainting with Correspondence Guidance in Diffusion Models: Kuan-Hung Liu,

Cheng-Kun Yang,

Min-Hung Chen,

Yu-Lun Liu,

Yen-Yu Lin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2025_WACV, author = {Liu, Kuan-Hung and Yang, Cheng-Kun and Chen, Min-Hung and Liu, Yu-Lun and Lin, Yen-Yu}, title = {CorrFill: Enhancing Faithfulness in Reference-Based Inpainting with Correspondence Guidance in Diffusion Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1618-1627} }
VIIS: Visible and Infrared Information Synthesis for Severe Low-Light Image Enhancement: Chen Zhao,

Mengyuan Yu,

Fan Yang,

Peiguang Jing; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2025_WACV, author = {Zhao, Chen and Yu, Mengyuan and Yang, Fan and Jing, Peiguang}, title = {VIIS: Visible and Infrared Information Synthesis for Severe Low-Light Image Enhancement}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2174-2184} }
Continual Learning of Personalized Generative Face Models with Experience Replay: Annie N. Wang,

Luchao Qi,

Roni Sengupta; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2025_WACV, author = {Wang, Annie N. and Qi, Luchao and Sengupta, Roni}, title = {Continual Learning of Personalized Generative Face Models with Experience Replay}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2942-2951} }
Decoupled PROB: Decoupled Query Initialization Tasks and Objectness-Class Learning for Open World Object Detection: Riku Inoue,

Masamitsu Tsuchiya,

Yuji Yasui; [pdf] [supp]
[bibtex]
@InProceedings{Inoue_2025_WACV, author = {Inoue, Riku and Tsuchiya, Masamitsu and Yasui, Yuji}, title = {Decoupled PROB: Decoupled Query Initialization Tasks and Objectness-Class Learning for Open World Object Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8196-8205} }
RT-DETRv3: Real-Time End-to-End Object Detection with Hierarchical Dense Positive Supervision: Shuo Wang,

Chunlong Xia,

Feng Lv,

Yifeng Shi; [pdf]
[bibtex]
@InProceedings{Wang_2025_WACV, author = {Wang, Shuo and Xia, Chunlong and Lv, Feng and Shi, Yifeng}, title = {RT-DETRv3: Real-Time End-to-End Object Detection with Hierarchical Dense Positive Supervision}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1628-1636} }
Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection: Wentao Bao,

Kai Li,

Yuxiao Chen,

Deep A Patel,

Martin Renqiang Min,

Yu Kong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bao_2025_WACV, author = {Bao, Wentao and Li, Kai and Chen, Yuxiao and A Patel, Deep and Min, Martin Renqiang and Kong, Yu}, title = {Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8280-8290} }
Dance Any Beat: Blending Beats with Visuals in Dance Video Generation: Xuanchen Wang,

Heng Wang,

Dongnan Liu,

Weidong Cai; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2025_WACV, author = {Wang, Xuanchen and Wang, Heng and Liu, Dongnan and Cai, Weidong}, title = {Dance Any Beat: Blending Beats with Visuals in Dance Video Generation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5136-5146} }
Context-Aware Optimal Transport Learning for Retinal Fundus Image Enhancement: Vamsi Krishna S Vasa,

Peijie Qiu,

Wenhui Zhu,

Yujian Xiong,

Oana Dumitrascu,

Yalin Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Vasa_2025_WACV, author = {Vasa, Vamsi Krishna S and Qiu, Peijie and Zhu, Wenhui and Xiong, Yujian and Dumitrascu, Oana and Wang, Yalin}, title = {Context-Aware Optimal Transport Learning for Retinal Fundus Image Enhancement}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4016-4025} }
Perceive Query & Reason: Enhancing Video QA with Question-Guided Temporal Queries: Roberto Amoroso,

Gengyuan Zhang,

Rajat Koner,

Lorenzo Baraldi,

Rita Cucchiara,

Volker Tresp; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Amoroso_2025_WACV, author = {Amoroso, Roberto and Zhang, Gengyuan and Koner, Rajat and Baraldi, Lorenzo and Cucchiara, Rita and Tresp, Volker}, title = {Perceive Query \& Reason: Enhancing Video QA with Question-Guided Temporal Queries}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8835-8844} }
Remote Blood Pressure Estimation from Facial Videos using Transfer Learning: Leveraging PPG to rPPG Conversion: Chun-Hong Cheng,

Jing Wei Chin,

Kwan Long Wong,

Tsz Tai Chan,

Hau Ching Lo,

Kwan Lok Pang,

Richard So,

Bryan Yan; [pdf] [supp]
[bibtex]
@InProceedings{Cheng_2025_WACV, author = {Cheng, Chun-Hong and Chin, Jing Wei and Wong, Kwan Long and Chan, Tsz Tai and Lo, Hau Ching and Pang, Kwan Lok and So, Richard and Yan, Bryan}, title = {Remote Blood Pressure Estimation from Facial Videos using Transfer Learning: Leveraging PPG to rPPG Conversion}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4225-4236} }
GStex: Per-Primitive Texturing of 2D Gaussian Splatting for Decoupled Appearance and Geometry Modeling: Victor Rong,

Jingxiang Chen,

Sherwin Bahmani,

Kiriakos Kutulakos,

David Lindell; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Rong_2025_WACV, author = {Rong, Victor and Chen, Jingxiang and Bahmani, Sherwin and Kutulakos, Kiriakos and Lindell, David}, title = {GStex: Per-Primitive Texturing of 2D Gaussian Splatting for Decoupled Appearance and Geometry Modeling}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3508-3518} }
Composed Image Retrieval for Training-Free Domain Conversion: Nikos Efthymiadis,

Bill Psomas,

Zakaria Laskar,

Konstantinos Karantzalos,

Yannis Avrithis,

Ondrej Chum,

Giorgos Tolias; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Efthymiadis_2025_WACV, author = {Efthymiadis, Nikos and Psomas, Bill and Laskar, Zakaria and Karantzalos, Konstantinos and Avrithis, Yannis and Chum, Ondrej and Tolias, Giorgos}, title = {Composed Image Retrieval for Training-Free Domain Conversion}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1723-1733} }
HSDA: High-Frequency Shuffle Data Augmentation for Bird's-Eye-View Map Segmentation: Calvin Glisson,

Qiuxiao Chen; [pdf]
[bibtex]
@InProceedings{Glisson_2025_WACV, author = {Glisson, Calvin and Chen, Qiuxiao}, title = {HSDA: High-Frequency Shuffle Data Augmentation for Bird's-Eye-View Map Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8816-8825} }
Unsupervised Denoising for Signal-Dependent and Row-Correlated Imaging Noise: Benjamin Salmon,

Alexander Krull; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Salmon_2025_WACV, author = {Salmon, Benjamin and Krull, Alexander}, title = {Unsupervised Denoising for Signal-Dependent and Row-Correlated Imaging Noise}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2379-2389} }
Mixed Patch Visible-Infrared Modality Agnostic Object Detection: Heitor R. Medeiros,

David Latortue,

Eric Granger,

Marco Pedersoli; [pdf] [supp]
[bibtex]
@InProceedings{Medeiros_2025_WACV, author = {Medeiros, Heitor R. and Latortue, David and Granger, Eric and Pedersoli, Marco}, title = {Mixed Patch Visible-Infrared Modality Agnostic Object Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9005-9014} }
Differentially Private Integrated Decision Gradients (IDG-DP) for Radar-Based Human Activity Recognition: Idris Zakariyya,

Linda Tran,

Kaushik Bhargav Sivangi,

Paul Henderson,

Fani Deligianni; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zakariyya_2025_WACV, author = {Zakariyya, Idris and Tran, Linda and Sivangi, Kaushik Bhargav and Henderson, Paul and Deligianni, Fani}, title = {Differentially Private Integrated Decision Gradients (IDG-DP) for Radar-Based Human Activity Recognition}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5611-5622} }
GeneralizeFormer: Layer-Adaptive Model Generation across Test-Time Distribution Shifts: Sameer Ambekar,

Zehao Xiao,

Xiantong Zhen,

Cees Snoek; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ambekar_2025_WACV, author = {Ambekar, Sameer and Xiao, Zehao and Zhen, Xiantong and Snoek, Cees}, title = {GeneralizeFormer: Layer-Adaptive Model Generation across Test-Time Distribution Shifts}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6548-6558} }
PICASSO: A Feed-Forward Framework for Parametric Inference of CAD Sketches via Rendering Self-Supervision: Ahmet Serdar Karadeniz,

Dimitrios Mallis,

Nesryne Mejri,

Kseniya Cherenkova,

Anis Kacem,

Djamila Aouada; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Karadeniz_2025_WACV, author = {Karadeniz, Ahmet Serdar and Mallis, Dimitrios and Mejri, Nesryne and Cherenkova, Kseniya and Kacem, Anis and Aouada, Djamila}, title = {PICASSO: A Feed-Forward Framework for Parametric Inference of CAD Sketches via Rendering Self-Supervision}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6475-6484} }
Counting Guidance for High Fidelity Text-to-Image Synthesis: Wonjun Kang,

Kevin Galim,

Hyung Il Koo,

Nam Ik Cho; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kang_2025_WACV, author = {Kang, Wonjun and Galim, Kevin and Koo, Hyung Il and Cho, Nam Ik}, title = {Counting Guidance for High Fidelity Text-to-Image Synthesis}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {899-908} }
AMNCutter: Affinity-Attention-Guided Multi-View Normalized Cutter for Unsupervised Surgical Instrument Segmentation: Mingyu Sheng,

Jianan Fan,

Dongnan Liu,

Ron Kikinis,

Weidong Cai; [pdf] [arXiv]
[bibtex]
@InProceedings{Sheng_2025_WACV, author = {Sheng, Mingyu and Fan, Jianan and Liu, Dongnan and Kikinis, Ron and Cai, Weidong}, title = {AMNCutter: Affinity-Attention-Guided Multi-View Normalized Cutter for Unsupervised Surgical Instrument Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4533-4544} }
Dynamic Attention-Guided Diffusion for Image Super-Resolution: Brian B. Moser,

Stanislav Frolov,

Federico Raue,

Sebastian Palacio,

Andreas Dengel; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Moser_2025_WACV, author = {Moser, Brian B. and Frolov, Stanislav and Raue, Federico and Palacio, Sebastian and Dengel, Andreas}, title = {Dynamic Attention-Guided Diffusion for Image Super-Resolution}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {451-460} }
SEMU-Net: A Segmentation-Based Corrector for Fabrication Process Variations of Nanophotonics with Microscopic Images: Rambod Azimi,

Yijian Kong,

Dusan Gostimirovic,

James J. Clark,

Odile Liboiron-Ladouceur; [pdf]
[bibtex]
@InProceedings{Azimi_2025_WACV, author = {Azimi, Rambod and Kong, Yijian and Gostimirovic, Dusan and Clark, James J. and Liboiron-Ladouceur, Odile}, title = {SEMU-Net: A Segmentation-Based Corrector for Fabrication Process Variations of Nanophotonics with Microscopic Images}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1528-1536} }
Frame by Familiar Frame: Understanding Replication in Video Diffusion Models: Aimon Rahman,

Malsha V. Perera,

Vishal M. Patel; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Rahman_2025_WACV, author = {Rahman, Aimon and Perera, Malsha V. and Patel, Vishal M.}, title = {Frame by Familiar Frame: Understanding Replication in Video Diffusion Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2766-2776} }
ReFu: Recursive Fusion for Exemplar-Free 3D Class-Incremental Learning: Yi Yang,

Lei Zhong,

Huiping Zhuang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2025_WACV, author = {Yang, Yi and Zhong, Lei and Zhuang, Huiping}, title = {ReFu: Recursive Fusion for Exemplar-Free 3D Class-Incremental Learning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3396-3405} }
Talking Head Anime 4: Distillation for Real-Time Performance: Pramook Khungurn; [pdf] [supp]
[bibtex]
@InProceedings{Khungurn_2025_WACV, author = {Khungurn, Pramook}, title = {Talking Head Anime 4: Distillation for Real-Time Performance}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5018-5029} }
NeRFs are Mirror Detectors: using Structural Similarity for Multi-View Mirror Scene Reconstruction with 3D Surface Primitives: Leif Van Holland,

Michael Weinmann,

Jan U. Müller,

Patrick Stotko,

Reinhard Klein; [pdf] [supp]
[bibtex]
@InProceedings{Van_Holland_2025_WACV, author = {Van Holland, Leif and Weinmann, Michael and M\"uller, Jan U. and Stotko, Patrick and Klein, Reinhard}, title = {NeRFs are Mirror Detectors: using Structural Similarity for Multi-View Mirror Scene Reconstruction with 3D Surface Primitives}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1795-1807} }
VortSDF: 3D Modeling with Centroidal Voronoi Tesselation on Signed Distance Field: Diego Thomas,

Briac Toussaint,

Jean-Sebastien Franco,

Edmond Boyer; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Thomas_2025_WACV, author = {Thomas, Diego and Toussaint, Briac and Franco, Jean-Sebastien and Boyer, Edmond}, title = {VortSDF: 3D Modeling with Centroidal Voronoi Tesselation on Signed Distance Field}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {495-504} }
ARTIST: Improving the Generation of Text-Rich Images with Disentangled Diffusion Models and Large Language Models: Jianyi Zhang,

Yufan Zhou,

Jiuxiang Gu,

Curtis Wigington,

Tong Yu,

Yiran Chen,

Tong Sun,

Ruiyi Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2025_WACV, author = {Zhang, Jianyi and Zhou, Yufan and Gu, Jiuxiang and Wigington, Curtis and Yu, Tong and Chen, Yiran and Sun, Tong and Zhang, Ruiyi}, title = {ARTIST: Improving the Generation of Text-Rich Images with Disentangled Diffusion Models and Large Language Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1268-1278} }
Advancing Weight and Channel Sparsification with Enhanced Saliency: Xinglong Sun,

Maying Shen,

Hongxu Yin,

Lei Mao,

Pavlo Molchanov,

Jose M. Alvarez; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sun_2025_WACV, author = {Sun, Xinglong and Shen, Maying and Yin, Hongxu and Mao, Lei and Molchanov, Pavlo and Alvarez, Jose M.}, title = {Advancing Weight and Channel Sparsification with Enhanced Saliency}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7244-7255} }
GMT: Guided Mask Transformer for Leaf Instance Segmentation: Feng Chen,

Sotirios A. Tsaftaris,

Mario Valerio Giuffrida; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2025_WACV, author = {Chen, Feng and Tsaftaris, Sotirios A. and Giuffrida, Mario Valerio}, title = {GMT: Guided Mask Transformer for Leaf Instance Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1217-1226} }
Realistic and Efficient Face Swapping: A Unified Approach with Diffusion Models: Sanoojan Baliah,

Qinliang Lin,

Shengcai Liao,

Xiaodan Liang,

Muhammad Haris Khan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Baliah_2025_WACV, author = {Baliah, Sanoojan and Lin, Qinliang and Liao, Shengcai and Liang, Xiaodan and Khan, Muhammad Haris}, title = {Realistic and Efficient Face Swapping: A Unified Approach with Diffusion Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1062-1071} }
Enhancing Visual Classification using Comparative Descriptors: Hankyeol Lee,

Gawon Seo,

Wonseok Choi,

Geunyoung Jung,

Kyungwoo Song,

Jiyoung Jung; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2025_WACV, author = {Lee, Hankyeol and Seo, Gawon and Choi, Wonseok and Jung, Geunyoung and Song, Kyungwoo and Jung, Jiyoung}, title = {Enhancing Visual Classification using Comparative Descriptors}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5274-5283} }
Dense Depth from Event Focal Stack: Kenta Horikawa,

Mariko Isogawa,

Hideo Saito,

Shohei Mori; [pdf] [arXiv]
[bibtex]
@InProceedings{Horikawa_2025_WACV, author = {Horikawa, Kenta and Isogawa, Mariko and Saito, Hideo and Mori, Shohei}, title = {Dense Depth from Event Focal Stack}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4545-4553} }
Elucidating the Solution Space of Extended Reverse-Time SDE for Diffusion Models: Qinpeng Cui,

Xinyi Zhang,

Qiqi Bao,

Qingmin Liao; [pdf] [supp]
[bibtex]
@InProceedings{Cui_2025_WACV, author = {Cui, Qinpeng and Zhang, Xinyi and Bao, Qiqi and Liao, Qingmin}, title = {Elucidating the Solution Space of Extended Reverse-Time SDE for Diffusion Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {243-252} }
AnomalyDINO: Boosting Patch-Based Few-Shot Anomaly Detection with DINOv2: Simon Damm,

Mike Laszkiewicz,

Johannes Lederer,

Asja Fischer; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Damm_2025_WACV, author = {Damm, Simon and Laszkiewicz, Mike and Lederer, Johannes and Fischer, Asja}, title = {AnomalyDINO: Boosting Patch-Based Few-Shot Anomaly Detection with DINOv2}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1319-1329} }
Tuned Contrastive Learning: Chaitanya Animesh,

Manmohan Chandraker; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Animesh_2025_WACV, author = {Animesh, Chaitanya and Chandraker, Manmohan}, title = {Tuned Contrastive Learning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7225-7234} }
EdgeGaussians - 3D Edge Mapping via Gaussian Splatting: Kunal Chelani,

Assia Benbihi,

Torsten Sattler,

Fredrik Kahl; [pdf] [supp]
[bibtex]
@InProceedings{Chelani_2025_WACV, author = {Chelani, Kunal and Benbihi, Assia and Sattler, Torsten and Kahl, Fredrik}, title = {EdgeGaussians - 3D Edge Mapping via Gaussian Splatting}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3268-3279} }
Guess Future Anomalies from Normalcy: Forecasting Abnormal Behavior in Real-World Videos: Snehashis Majhi,

Mohammed Guermal,

Antitza Dantcheva,

Quan Kong,

Lorenzo Garattoni,

Gianpiero Francesca,

François Brémond; [pdf] [supp]
[bibtex]
@InProceedings{Majhi_2025_WACV, author = {Majhi, Snehashis and Guermal, Mohammed and Dantcheva, Antitza and Kong, Quan and Garattoni, Lorenzo and Francesca, Gianpiero and Br\'emond, Fran\c{c}ois}, title = {Guess Future Anomalies from Normalcy: Forecasting Abnormal Behavior in Real-World Videos}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {388-398} }
Single-Layer Distillation with Fourier Convolutions for Texture Anomaly Detection: Simon Thomine,

Hichem Snoussi; [pdf] [supp]
[bibtex]
@InProceedings{Thomine_2025_WACV, author = {Thomine, Simon and Snoussi, Hichem}, title = {Single-Layer Distillation with Fourier Convolutions for Texture Anomaly Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8962-8971} }
Uni-SLAM: Uncertainty-Aware Neural Implicit SLAM for Real-Time Dense Indoor Scene Reconstruction: Shaoxiang Wang,

Yaxu Xie,

Chun-Peng Chang,

Christen Millerdurai,

Alain Pagani,

Didier Stricker; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2025_WACV, author = {Wang, Shaoxiang and Xie, Yaxu and Chang, Chun-Peng and Millerdurai, Christen and Pagani, Alain and Stricker, Didier}, title = {Uni-SLAM: Uncertainty-Aware Neural Implicit SLAM for Real-Time Dense Indoor Scene Reconstruction}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2228-2239} }
MS-Glance: Bio-Inspired Non-Semantic Context Vectors and their Applications in Supervising Image Reconstruction: Ziqi Gao,

Wendi Yang,

Yujia Li,

Lei Xing,

S. Kevin Zhou; [pdf] [supp]
[bibtex]
@InProceedings{Gao_2025_WACV, author = {Gao, Ziqi and Yang, Wendi and Li, Yujia and Xing, Lei and Zhou, S. Kevin}, title = {MS-Glance: Bio-Inspired Non-Semantic Context Vectors and their Applications in Supervising Image Reconstruction}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3084-3095} }
DAM: Dynamic Adapter Merging for Continual Video QA Learning: Feng Cheng,

Ziyang Wang,

Yi-Lin Sung,

Yan-Bo Lin,

Mohit Bansal,

Gedas Bertasius; [pdf] [arXiv]
[bibtex]
@InProceedings{Cheng_2025_WACV, author = {Cheng, Feng and Wang, Ziyang and Sung, Yi-Lin and Lin, Yan-Bo and Bansal, Mohit and Bertasius, Gedas}, title = {DAM: Dynamic Adapter Merging for Continual Video QA Learning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6805-6817} }
VG-SSL: Benchmarking Self-Supervised Representation Learning Approaches for Visual Geo-Localization: Jiuhong Xiao,

Gao Zhu,

Giuseppe Loianno; [pdf] [supp]
[bibtex]
@InProceedings{Xiao_2025_WACV, author = {Xiao, Jiuhong and Zhu, Gao and Loianno, Giuseppe}, title = {VG-SSL: Benchmarking Self-Supervised Representation Learning Approaches for Visual Geo-Localization}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6667-6677} }
Multi-Label Continual Learning for the Medical Domain: A Novel Benchmark: Marina Ceccon,

Davide Dalle Pezze,

Alessandro Fabris,

Gian Antonio Susto; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ceccon_2025_WACV, author = {Ceccon, Marina and Pezze, Davide Dalle and Fabris, Alessandro and Susto, Gian Antonio}, title = {Multi-Label Continual Learning for the Medical Domain: A Novel Benchmark}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7163-7172} }
Uniform Attention Maps: Boosting Image Fidelity in Reconstruction and Editing: Wenyi Mo,

Tianyu Zhang,

Yalong Bai,

Bing Su,

Ji-Rong Wen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mo_2025_WACV, author = {Mo, Wenyi and Zhang, Tianyu and Bai, Yalong and Su, Bing and Wen, Ji-Rong}, title = {Uniform Attention Maps: Boosting Image Fidelity in Reconstruction and Editing}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4420-4429} }
Design Principles of Multi-Scale J-Invariant Networks for Self-Supervised Image Denoising: Hayeong Yu,

Seungjae Han,

Young-Gyu Yoon; [pdf] [supp]
[bibtex]
@InProceedings{Yu_2025_WACV, author = {Yu, Hayeong and Han, Seungjae and Yoon, Young-Gyu}, title = {Design Principles of Multi-Scale J-Invariant Networks for Self-Supervised Image Denoising}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1309-1318} }
FMD: Comprehensive Data Compression in Medical Domain via Fused Matching Distillation: Ju Heon Son,

Jang-Hwan Choi; [pdf] [supp]
[bibtex]
@InProceedings{Son_2025_WACV, author = {Son, Ju Heon and Choi, Jang-Hwan}, title = {FMD: Comprehensive Data Compression in Medical Domain via Fused Matching Distillation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3406-3415} }
Inferring Past Human Actions in Homes with Abductive Reasoning: Clement Tan,

Chai Kiat Yeo,

Cheston Tan,

Basura Fernando; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tan_2025_WACV, author = {Tan, Clement and Yeo, Chai Kiat and Tan, Cheston and Fernando, Basura}, title = {Inferring Past Human Actions in Homes with Abductive Reasoning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8238-8247} }
J-Invariant Volume Shuffle for Self-Supervised Cryo-Electron Tomogram Denoising on Single Noisy Volume: Xiwei Liu,

Mohamad Kassab,

Min Xu,

Qirong Ho; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2025_WACV, author = {Liu, Xiwei and Kassab, Mohamad and Xu, Min and Ho, Qirong}, title = {J-Invariant Volume Shuffle for Self-Supervised Cryo-Electron Tomogram Denoising on Single Noisy Volume}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {568-577} }
CACE: Sim-to-Real Indoor 3D Semantic Segmentation via Context-Aware Augmentation and Consistency Enforcement: Tsung-Yu Chen,

Luyu Yang,

Tzu-Yu Chuang,

Shang-Hong Lai; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2025_WACV, author = {Chen, Tsung-Yu and Yang, Luyu and Chuang, Tzu-Yu and Lai, Shang-Hong}, title = {CACE: Sim-to-Real Indoor 3D Semantic Segmentation via Context-Aware Augmentation and Consistency Enforcement}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8345-8356} }
OmniDiffusion: Reformulating 360 Monocular Depth Estimation using Semantic and Surface Normal Conditioned Diffusion: Payal Mohadikar,

Ye Duan; [pdf] [supp]
[bibtex]
@InProceedings{Mohadikar_2025_WACV, author = {Mohadikar, Payal and Duan, Ye}, title = {OmniDiffusion: Reformulating 360 Monocular Depth Estimation using Semantic and Surface Normal Conditioned Diffusion}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8057-8067} }
Pre-Capture Privacy via Adaptive Single-Pixel Imaging: Yoko Sogabe,

Shiori Sugimoto,

Ayumi Matsumoto,

Masaki Kitahara; [pdf] [arXiv]
[bibtex]
@InProceedings{Sogabe_2025_WACV, author = {Sogabe, Yoko and Sugimoto, Shiori and Matsumoto, Ayumi and Kitahara, Masaki}, title = {Pre-Capture Privacy via Adaptive Single-Pixel Imaging}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9035-9044} }
Fairer Analysis and Demographically Balanced Face Generation for Fairer Face Verification: Alexandre Fournier-Montgieux,

Michaël Soumm,

Adrian Popescu,

Bertrand Luvison,

Hervé Le Borgne; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fournier-Montgieux_2025_WACV, author = {Fournier-Montgieux, Alexandre and Soumm, Micha\"el and Popescu, Adrian and Luvison, Bertrand and Le Borgne, Herv\'e}, title = {Fairer Analysis and Demographically Balanced Face Generation for Fairer Face Verification}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2788-2798} }
Towards Utilising a Range of Neural Activations for Comprehending Representational Associations: Laura O'Mahony,

Nikola S. Nikolov,

David JP O'Sullivan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{O'Mahony_2025_WACV, author = {O'Mahony, Laura and Nikolov, Nikola S. and O'Sullivan, David JP}, title = {Towards Utilising a Range of Neural Activations for Comprehending Representational Associations}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2495-2506} }
Vision-Based Landing Guidance through Tracking and Orientation Estimation: João P. K. Ferreira,

João P. Pinto,

Júlia Moura,

Yi Li,

Cristiano L. Castro,

Plamen Angelov; [pdf]
[bibtex]
@InProceedings{Ferreira_2025_WACV, author = {Ferreira, Jo\~ao P. K. and Pinto, Jo\~ao P. and Moura, J\'ulia and Li, Yi and Castro, Cristiano L. and Angelov, Plamen}, title = {Vision-Based Landing Guidance through Tracking and Orientation Estimation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9663-9671} }
A Video is Worth 10000 Words: Training and Benchmarking with Diverse Captions for Better Long Video Retrieval: Matthew Gwilliam,

Michael Cogswell,

Meng Ye,

Karan Sikka,

Abhinav Shrivastava,

Ajay Divakaran; [pdf] [supp]
[bibtex]
@InProceedings{Gwilliam_2025_WACV, author = {Gwilliam, Matthew and Cogswell, Michael and Ye, Meng and Sikka, Karan and Shrivastava, Abhinav and Divakaran, Ajay}, title = {A Video is Worth 10000 Words: Training and Benchmarking with Diverse Captions for Better Long Video Retrieval}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6591-6601} }
WeedsGalore: A Multispectral and Multitemporal UAV-Based Dataset for Crop and Weed Segmentation in Agricultural Maize Fields: Ekin Celikkan,

Timo Kunzmann,

Yertay Yeskaliyev,

Sibylle Itzerott,

Nadja Klein,

Martin Herold; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Celikkan_2025_WACV, author = {Celikkan, Ekin and Kunzmann, Timo and Yeskaliyev, Yertay and Itzerott, Sibylle and Klein, Nadja and Herold, Martin}, title = {WeedsGalore: A Multispectral and Multitemporal UAV-Based Dataset for Crop and Weed Segmentation in Agricultural Maize Fields}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4767-4777} }
Generalist YOLO: Towards Real-Time End-to-End Multi-Task Visual Language Models: Hung-Shuo Chang,

Chien-Yao Wang,

Richard Robert Wang,

Gene Chou,

Hong-Yuan Mark Liao; [pdf]
[bibtex]
@InProceedings{Chang_2025_WACV, author = {Chang, Hung-Shuo and Wang, Chien-Yao and Wang, Richard Robert and Chou, Gene and Liao, Hong-Yuan Mark}, title = {Generalist YOLO: Towards Real-Time End-to-End Multi-Task Visual Language Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6217-6227} }
Event-Guided Low-Light Video Semantic Segmentation: Zhen Yao,

Mooi Choo Chuah; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yao_2025_WACV, author = {Yao, Zhen and Chuah, Mooi Choo}, title = {Event-Guided Low-Light Video Semantic Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3330-3341} }
VADet: Multi-Frame LiDAR 3D Object Detection using Variable Aggregation: Chengjie Huang,

Vahdat Abdelzad,

Sean Sedwards,

Krzysztof Czarnecki; [pdf] [arXiv]
[bibtex]
@InProceedings{Huang_2025_WACV, author = {Huang, Chengjie and Abdelzad, Vahdat and Sedwards, Sean and Czarnecki, Krzysztof}, title = {VADet: Multi-Frame LiDAR 3D Object Detection using Variable Aggregation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {711-720} }
CL-Cross VQA: A Continual Learning Benchmark for Cross-Domain Visual Question Answering: Yao Zhang,

Haokun Chen,

Ahmed Frikha,

Denis Krompass,

Gengyuan Zhang,

Jindong Gu,

Volker Tresp; [pdf]
[bibtex]
@InProceedings{Zhang_2025_WACV, author = {Zhang, Yao and Chen, Haokun and Frikha, Ahmed and Krompass, Denis and Zhang, Gengyuan and Gu, Jindong and Tresp, Volker}, title = {CL-Cross VQA: A Continual Learning Benchmark for Cross-Domain Visual Question Answering}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6269-6278} }
LogicNet: A Logical Consistency Embedded Face Attribute Learning Network: Haiyu Wu,

Sicong Tian,

Huayu Li,

Kevin W. Bowyer; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2025_WACV, author = {Wu, Haiyu and Tian, Sicong and Li, Huayu and Bowyer, Kevin W.}, title = {LogicNet: A Logical Consistency Embedded Face Attribute Learning Network}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5791-5800} }
EgoPoints: Advancing Point Tracking for Egocentric Videos: Ahmad Darkhalil,

Rhodri Guerrier,

Adam W. Harley,

Dima Damen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Darkhalil_2025_WACV, author = {Darkhalil, Ahmad and Guerrier, Rhodri and Harley, Adam W. and Damen, Dima}, title = {EgoPoints: Advancing Point Tracking for Egocentric Videos}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8545-8554} }
Optimizing Vision-Language Model for Road Crossing Intention Estimation: Roy Uziel,

Oded Bialer; [pdf] [supp]
[bibtex]
@InProceedings{Uziel_2025_WACV, author = {Uziel, Roy and Bialer, Oded}, title = {Optimizing Vision-Language Model for Road Crossing Intention Estimation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1702-1712} }
Loose Social-Interaction Recognition in Real-World Therapy Scenarios: Abid Ali,

Rui Dai,

Ashish Marisetty,

Guillaume Astruc,

Monique Thonnat,

Jean-Marc Odobez,

Susanne Thummler,

Francois Bremond; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ali_2025_WACV, author = {Ali, Abid and Dai, Rui and Marisetty, Ashish and Astruc, Guillaume and Thonnat, Monique and Odobez, Jean-Marc and Thummler, Susanne and Bremond, Francois}, title = {Loose Social-Interaction Recognition in Real-World Therapy Scenarios}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5156-5165} }
Semantic Segmentation Method for Automated Indoor 3D Reconstruction Based on Architectural-Knowledge-Aware Features: Yahan Chen,

Wenzheng Liu,

Xiaowei Luo; [pdf]
[bibtex]
@InProceedings{Chen_2025_WACV, author = {Chen, Yahan and Liu, Wenzheng and Luo, Xiaowei}, title = {Semantic Segmentation Method for Automated Indoor 3D Reconstruction Based on Architectural-Knowledge-Aware Features}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2715-2724} }
AdQuestA: Knowledge-Guided Visual Question Answer Framework for Advertisements: Neha Choudhary,

Poonam Goyal,

Devashish Siwatch,

Atharva Chandak,

Harsh Mahajan,

Varun Khurana,

Yaman Kumar; [pdf] [supp]
[bibtex]
@InProceedings{Choudhary_2025_WACV, author = {Choudhary, Neha and Goyal, Poonam and Siwatch, Devashish and Chandak, Atharva and Mahajan, Harsh and Khurana, Varun and Kumar, Yaman}, title = {AdQuestA: Knowledge-Guided Visual Question Answer Framework for Advertisements}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5812-5821} }
Generating Long-Take Videos via Effective Keyframes and Guidance: Hsin-Ping Huang,

Yu-Chuan Su,

Ming-Hsuan Yang; [pdf]
[bibtex]
@InProceedings{Huang_2025_WACV, author = {Huang, Hsin-Ping and Su, Yu-Chuan and Yang, Ming-Hsuan}, title = {Generating Long-Take Videos via Effective Keyframes and Guidance}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3709-3720} }
RGB-D Video Mirror Detection: Mingchen Xu,

Peter Herbert,

Yu-Kun Lai,

Ze Ji,

Jing Wu; [pdf]
[bibtex]
@InProceedings{Xu_2025_WACV, author = {Xu, Mingchen and Herbert, Peter and Lai, Yu-Kun and Ji, Ze and Wu, Jing}, title = {RGB-D Video Mirror Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9622-9631} }
PostoMETRO: Pose Token Enhanced Mesh Transformer for Robust 3D Human Mesh Recovery: Wendi Yang,

Zi-Hang Jiang,

Shang Zhao,

S. Kevin Zhou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2025_WACV, author = {Yang, Wendi and Jiang, Zi-Hang and Zhao, Shang and Zhou, S. Kevin}, title = {PostoMETRO: Pose Token Enhanced Mesh Transformer for Robust 3D Human Mesh Recovery}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4746-4756} }
Beyond Grids: Exploring Elastic Input Sampling for Vision Transformers: Adam Pardyl,

Grzegorz Kurzejamski,

Jan Olszewski,

Tomasz Trzcinski,

Bartosz Zielinski; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pardyl_2025_WACV, author = {Pardyl, Adam and Kurzejamski, Grzegorz and Olszewski, Jan and Trzcinski, Tomasz and Zielinski, Bartosz}, title = {Beyond Grids: Exploring Elastic Input Sampling for Vision Transformers}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8525-8534} }
Pruning One More Token is Enough: Leveraging Latency-Workload Non-Linearities for Vision Transformers on the Edge: Nicholas John Eliopoulos,

Purvish Jajal,

James C. Davis,

Gaowen Liu,

George K. Thiruvathukal,

Yung-Hsiang Lu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Eliopoulos_2025_WACV, author = {Eliopoulos, Nicholas John and Jajal, Purvish and Davis, James C. and Liu, Gaowen and Thiruvathukal, George K. and Lu, Yung-Hsiang}, title = {Pruning One More Token is Enough: Leveraging Latency-Workload Non-Linearities for Vision Transformers on the Edge}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7153-7162} }
Reframing Image Difference Captioning with BLIP2IDC and Synthetic Augmentation: Gautier Evennou,

Antoine Chaffin,

Vivien Chappelier,

Ewa Kijak; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Evennou_2025_WACV, author = {Evennou, Gautier and Chaffin, Antoine and Chappelier, Vivien and Kijak, Ewa}, title = {Reframing Image Difference Captioning with BLIP2IDC and Synthetic Augmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1392-1402} }
EfficientMorph: Parameter-Efficient Transformer-Based Architecture for 3D Image Registration: Abu Zahid Bin Aziz,

Mokshagna Sai Teja Karanam,

Tushar Kataria,

Shireen Y. Elhabian; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bin_Aziz_2025_WACV, author = {Bin Aziz, Abu Zahid and Karanam, Mokshagna Sai Teja and Kataria, Tushar and Elhabian, Shireen Y.}, title = {EfficientMorph: Parameter-Efficient Transformer-Based Architecture for 3D Image Registration}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1330-1341} }
PrevPredMap: Exploring Temporal Modeling with Previous Predictions for Online Vectorized HD Map Construction: Nan Peng,

Xun Zhou,

Mingming Wang,

Xiaojun Yang,

Songming Chen,

Guisong Chen; [pdf] [arXiv]
[bibtex]
@InProceedings{Peng_2025_WACV, author = {Peng, Nan and Zhou, Xun and Wang, Mingming and Yang, Xiaojun and Chen, Songming and Chen, Guisong}, title = {PrevPredMap: Exploring Temporal Modeling with Previous Predictions for Online Vectorized HD Map Construction}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8123-8132} }
GHOST: Grounded Human Motion Generation with Open Vocabulary Scene-and-Text Contexts: Zoltán Á. Milacski,

Koichiro Niinuma,

Ryosuke Kawamura,

Fernando de la Torre,

László A. Jeni; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Milacski_2025_WACV, author = {Milacski, Zolt\'an \'A. and Niinuma, Koichiro and Kawamura, Ryosuke and de la Torre, Fernando and Jeni, L\'aszl\'o A.}, title = {GHOST: Grounded Human Motion Generation with Open Vocabulary Scene-and-Text Contexts}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4108-4118} }
Unified Framework for Open-World Compositional Zero-Shot Learning: Hirunima Jayasekara,

Khoi Pham,

Nirat Saini,

Abhinav Shrivastava; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jayasekara_2025_WACV, author = {Jayasekara, Hirunima and Pham, Khoi and Saini, Nirat and Shrivastava, Abhinav}, title = {Unified Framework for Open-World Compositional Zero-Shot Learning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7826-7835} }
An Image is Worth Multiple Words: Multi-Attribute Inversion for Constrained Text-to-Image Synthesis: Aishwarya Agarwal,

Srikrishna Karanam,

Tripti Shukla,

Balaji Vasan Srinivasan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Agarwal_2025_WACV, author = {Agarwal, Aishwarya and Karanam, Srikrishna and Shukla, Tripti and Srinivasan, Balaji Vasan}, title = {An Image is Worth Multiple Words: Multi-Attribute Inversion for Constrained Text-to-Image Synthesis}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6053-6062} }
Learning to Visually Connect Actions and their Effects: Paritosh Parmar,

Eric Peh,

Basura Fernando; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Parmar_2025_WACV, author = {Parmar, Paritosh and Peh, Eric and Fernando, Basura}, title = {Learning to Visually Connect Actions and their Effects}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1477-1487} }
SwinIA: Self-Supervised Blind-Spot Image Denoising without Convolutions: Mikhail Papkov,

Pavel Chizhov,

Leopold Parts; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Papkov_2025_WACV, author = {Papkov, Mikhail and Chizhov, Pavel and Parts, Leopold}, title = {SwinIA: Self-Supervised Blind-Spot Image Denoising without Convolutions}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7071-7080} }
NarrAD: Automatic Generation of Audio Descriptions for Movies with Rich Narrative Context: Jaehyeong Park,

Junchel Ye,

Seungkook Lee,

Hyun W. Ka,

Dongsu Han; [pdf] [supp]
[bibtex]
@InProceedings{Park_2025_WACV, author = {Park, Jaehyeong and Ye, Junchel and Lee, Seungkook and Ka, Hyun W. and Han, Dongsu}, title = {NarrAD: Automatic Generation of Audio Descriptions for Movies with Rich Narrative Context}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {409-419} }
Anchored Diffusion for Video Face Reenactment: Idan Kligvasser,

Regev Cohen,

George Leifman,

Ehud Rivlin,

Michael Elad; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kligvasser_2025_WACV, author = {Kligvasser, Idan and Cohen, Regev and Leifman, George and Rivlin, Ehud and Elad, Michael}, title = {Anchored Diffusion for Video Face Reenactment}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4087-4097} }
Blind Image Deblurring with FFT-ReLU Sparsity Prior: Abdul Mohaimen Al Radi,

Prothito Shovon Majumder,

Md. Mosaddek Khan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Al_Radi_2025_WACV, author = {Al Radi, Abdul Mohaimen and Majumder, Prothito Shovon and Khan, Md. Mosaddek}, title = {Blind Image Deblurring with FFT-ReLU Sparsity Prior}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3447-3456} }
MIP-GAF: A MLLM-Annotated Benchmark for Most Important Person Localization and Group Context Understanding: S. Madan,

S. Ghosh,

L. R. Sookha,

M.A. Ganaie,

R. Subramanian,

A. Dhall,

T. Gedeon; [pdf] [supp]
[bibtex]
@InProceedings{Madan_2025_WACV, author = {Madan, S. and Ghosh, S. and Sookha, L. R. and Ganaie, M.A. and Subramanian, R. and Dhall, A. and Gedeon, T.}, title = {MIP-GAF: A MLLM-Annotated Benchmark for Most Important Person Localization and Group Context Understanding}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1467-1476} }
Difficulty Diversity and Plausibility: Dynamic Data-Free Quantization: Cheeun Hong,

Sungyong Baik,

Junghun Oh,

Kyoung Mu Lee; [pdf] [supp]
[bibtex]
@InProceedings{Hong_2025_WACV, author = {Hong, Cheeun and Baik, Sungyong and Oh, Junghun and Lee, Kyoung Mu}, title = {Difficulty Diversity and Plausibility: Dynamic Data-Free Quantization}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7531-7540} }
Uncertainty and Energy Based Loss Guided Semi-Supervised Semantic Segmentation: Rini Smita Thakur,

Vinod K Kurmi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Thakur_2025_WACV, author = {Thakur, Rini Smita and Kurmi, Vinod K}, title = {Uncertainty and Energy Based Loss Guided Semi-Supervised Semantic Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8024-8034} }
BIV-Priv-Seg: Locating Private Content in Images Taken by People with Visual Impairments: Yu-Yun Tseng,

Tanusree Sharma,

Lotus Zhang,

Abigale Stangl,

Leah Findlater,

Yang Wang,

Danna Gurari; [pdf] [supp]
[bibtex]
@InProceedings{Tseng_2025_WACV, author = {Tseng, Yu-Yun and Sharma, Tanusree and Zhang, Lotus and Stangl, Abigale and Findlater, Leah and Wang, Yang and Gurari, Danna}, title = {BIV-Priv-Seg: Locating Private Content in Images Taken by People with Visual Impairments}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {430-440} }
CrowdMAC: Masked Crowd Density Completion for Robust Crowd Density Forecasting: Ryo Fujii,

Ryo Hachiuma,

Hideo Saito; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fujii_2025_WACV, author = {Fujii, Ryo and Hachiuma, Ryo and Saito, Hideo}, title = {CrowdMAC: Masked Crowd Density Completion for Robust Crowd Density Forecasting}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8218-8227} }
SEED4D: A Synthetic Ego-Exo Dynamic 4D Data Generator Driving Dataset and Benchmark: Marius Kästingschäfer,

Théo Gieruc,

Sebastian Bernhard,

Dylan Campbell,

Eldar Insafutdinov,

Eyvaz Najafli,

Thomas Brox; [pdf] [supp]
[bibtex]
@InProceedings{Kastingschafer_2025_WACV, author = {K\"astingsch\"afer, Marius and Gieruc, Th\'eo and Bernhard, Sebastian and Campbell, Dylan and Insafutdinov, Eldar and Najafli, Eyvaz and Brox, Thomas}, title = {SEED4D: A Synthetic Ego-Exo Dynamic 4D Data Generator Driving Dataset and Benchmark}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7741-7753} }
The FineView Dataset:A 3D Scanned Multi-View Object Dataset of Fine-Grained Category Instances: Suguru Onda,

Ryan Farrell; [pdf] [supp]
[bibtex]
@InProceedings{Onda_2025_WACV, author = {Onda, Suguru and Farrell, Ryan}, title = {The FineView Dataset:A 3D Scanned Multi-View Object Dataset of Fine-Grained Category Instances}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5623-5634} }
Incorporating Task Progress Knowledge for Subgoal Generation in Robotic Manipulation through Image Edits: Xuhui Kang,

Yen-Ling Kuo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kang_2025_WACV, author = {Kang, Xuhui and Kuo, Yen-Ling}, title = {Incorporating Task Progress Knowledge for Subgoal Generation in Robotic Manipulation through Image Edits}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7490-7499} }
Enhancing Zero-Shot Facial Expression Recognition by LLM Knowledge Transfer: Zengqun Zhao,

Yu Cao,

Shaogang Gong,

Ioannis Patras; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2025_WACV, author = {Zhao, Zengqun and Cao, Yu and Gong, Shaogang and Patras, Ioannis}, title = {Enhancing Zero-Shot Facial Expression Recognition by LLM Knowledge Transfer}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {815-824} }
Non-Cross Diffusion for Semantic Consistency: Ziyang Zheng,

Ruiyuan Gao,

Qiang Xu; [pdf] [arXiv]
[bibtex]
@InProceedings{Zheng_2025_WACV, author = {Zheng, Ziyang and Gao, Ruiyuan and Xu, Qiang}, title = {Non-Cross Diffusion for Semantic Consistency}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3897-3906} }
Semantic Clustering of Image Retrieval Databases used for Visual Localization: Henry Hölzemann,

Torsten Fiolka; [pdf]
[bibtex]
@InProceedings{Holzemann_2025_WACV, author = {H\"olzemann, Henry and Fiolka, Torsten}, title = {Semantic Clustering of Image Retrieval Databases used for Visual Localization}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6998-7007} }
FDS: Feedback-Guided Domain Synthesis with Multi-Source Conditional Diffusion Models for Domain Generalization: Mehrdad Noori,

Milad Cheraghalikhani,

Ali Bahri,

Gustavo A Vargas Hakim,

David Osowiechi,

Moslem Yazdanpanah,

Ismail Ben Ayed,

Christian Desrosiers; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Noori_2025_WACV, author = {Noori, Mehrdad and Cheraghalikhani, Milad and Bahri, Ali and A Vargas Hakim, Gustavo and Osowiechi, David and Yazdanpanah, Moslem and Ben Ayed, Ismail and Desrosiers, Christian}, title = {FDS: Feedback-Guided Domain Synthesis with Multi-Source Conditional Diffusion Models for Domain Generalization}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8493-8503} }
LatteCLIP: Unsupervised CLIP Fine-Tuning via LMM-Synthetic Texts: Anh-Quan Cao,

Maximilian Jaritz,

Matthieu Guillaumin,

Raoul de Charette,

Loris Bazzani; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cao_2025_WACV, author = {Cao, Anh-Quan and Jaritz, Maximilian and Guillaumin, Matthieu and de Charette, Raoul and Bazzani, Loris}, title = {LatteCLIP: Unsupervised CLIP Fine-Tuning via LMM-Synthetic Texts}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5030-5040} }
GANFusion: Feed-Forward Text-to-3D with Diffusion in GAN Space: Souhaib Attaiki,

Paul Guerrero,

Duygu Ceylan,

Niloy Mitra,

Maks Ovsjanikov; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Attaiki_2025_WACV, author = {Attaiki, Souhaib and Guerrero, Paul and Ceylan, Duygu and Mitra, Niloy and Ovsjanikov, Maks}, title = {GANFusion: Feed-Forward Text-to-3D with Diffusion in GAN Space}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3985-3995} }
Zero-Shot Detection of Out-of-Context Objects using Foundation Models: Anirban Roy,

Adam Cobb,

Ramneet Kaur,

Sumit Jha,

Nathaniel Bastian,

Alexander Berenbeim,

Robert Thomson,

Iain Cruickshank,

Alvaro Velasquez,

Susmit Jha; [pdf]
[bibtex]
@InProceedings{Roy_2025_WACV, author = {Roy, Anirban and Cobb, Adam and Kaur, Ramneet and Jha, Sumit and Bastian, Nathaniel and Berenbeim, Alexander and Thomson, Robert and Cruickshank, Iain and Velasquez, Alvaro and Jha, Susmit}, title = {Zero-Shot Detection of Out-of-Context Objects using Foundation Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9168-9177} }
RefVSR++: Exploiting Reference Inputs for Reference-Based Video Super-Resolution: Han Zou,

Masanori Suganuma,

Takayuki Okatani; [pdf]
[bibtex]
@InProceedings{Zou_2025_WACV, author = {Zou, Han and Suganuma, Masanori and Okatani, Takayuki}, title = {RefVSR++: Exploiting Reference Inputs for Reference-Based Video Super-Resolution}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2756-2765} }
LLM-Generated Rewrite and Context Modulation for Enhanced Vision Language Models in Digital Pathology: Cagla Deniz Bahadir,

Gozde B. Akar,

Mert R. Sabuncu; [pdf] [supp]
[bibtex]
@InProceedings{Bahadir_2025_WACV, author = {Bahadir, Cagla Deniz and Akar, Gozde B. and Sabuncu, Mert R.}, title = {LLM-Generated Rewrite and Context Modulation for Enhanced Vision Language Models in Digital Pathology}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {327-336} }
HEX: Hierarchical Emergence Exploitation in Self-Supervised Algorithms: Kiran Kokilepersaud,

Seulgi Kim,

Mohit Prabhushankar,

Ghassan AlRegib; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kokilepersaud_2025_WACV, author = {Kokilepersaud, Kiran and Kim, Seulgi and Prabhushankar, Mohit and AlRegib, Ghassan}, title = {HEX: Hierarchical Emergence Exploitation in Self-Supervised Algorithms}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1111-1121} }
ElasticLaneNet: An Efficient Geometry-Flexible Lane Detection Framework: Yaxin Feng,

Yuan Lan,

Luchan Zhang,

Yang Xiang; [pdf] [supp]
[bibtex]
@InProceedings{Feng_2025_WACV, author = {Feng, Yaxin and Lan, Yuan and Zhang, Luchan and Xiang, Yang}, title = {ElasticLaneNet: An Efficient Geometry-Flexible Lane Detection Framework}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8733-8742} }
Federated-Continual Dynamic Segmentation of Histopathology Guided by Barlow Continuity: Niklas Babendererde,

Haozhe Zhu,

Moritz Fuchs,

Jonathan Stieber,

Anirban Mukhopadhyay; [pdf] [arXiv]
[bibtex]
@InProceedings{Babendererde_2025_WACV, author = {Babendererde, Niklas and Zhu, Haozhe and Fuchs, Moritz and Stieber, Jonathan and Mukhopadhyay, Anirban}, title = {Federated-Continual Dynamic Segmentation of Histopathology Guided by Barlow Continuity}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3752-3761} }
NCAP: Scene Text Image Super-Resolution with Non-CAtegorical Prior: Dongwoo Park,

Suk Pil Ko; [pdf] [supp]
[bibtex]
@InProceedings{Park_2025_WACV, author = {Park, Dongwoo and Ko, Suk Pil}, title = {NCAP: Scene Text Image Super-Resolution with Non-CAtegorical Prior}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2432-2441} }
Image-Level Regression for Uncertainty-Aware Retinal Image Segmentation: Trung D. Q. Dang,

Huy Hoang Nguyen,

Aleksei Tiulpin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dang_2025_WACV, author = {Dang, Trung D. Q. and Nguyen, Huy Hoang and Tiulpin, Aleksei}, title = {Image-Level Regression for Uncertainty-Aware Retinal Image Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4194-4204} }
Test-Time Adaptation of 3D Point Clouds via Denoising Diffusion Models: Hamidreza Dastmalchi,

Aijun An,

Ali Cheraghian,

Shafin Rahman,

Sameera Ramasinghe; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dastmalchi_2025_WACV, author = {Dastmalchi, Hamidreza and An, Aijun and Cheraghian, Ali and Rahman, Shafin and Ramasinghe, Sameera}, title = {Test-Time Adaptation of 3D Point Clouds via Denoising Diffusion Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1566-1576} }
Task Configuration Impacts Annotation Quality and Model Training Performance in Crowdsourced Image Segmentation: Benjamin R Bauchwitz,

Mary Cummings; [pdf] [supp]
[bibtex]
@InProceedings{Bauchwitz_2025_WACV, author = {Bauchwitz, Benjamin R and Cummings, Mary}, title = {Task Configuration Impacts Annotation Quality and Model Training Performance in Crowdsourced Image Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6646-6656} }
Hausdorff Distance Matching with Adaptive Query Denoising for Rotated Detection Transformer: Hakjin Lee,

MinKi Song,

Jamyoung Koo,

Junghoon Seo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2025_WACV, author = {Lee, Hakjin and Song, MinKi and Koo, Jamyoung and Seo, Junghoon}, title = {Hausdorff Distance Matching with Adaptive Query Denoising for Rotated Detection Transformer}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1872-1882} }
3D Shape Completion using Multi-Resolution Spectral Encoding: Pallabjyoti Deka,

Saumik Bhattacharya,

Debashis Sen,

Prabir Kumar Biswas; [pdf] [supp]
[bibtex]
@InProceedings{Deka_2025_WACV, author = {Deka, Pallabjyoti and Bhattacharya, Saumik and Sen, Debashis and Biswas, Prabir Kumar}, title = {3D Shape Completion using Multi-Resolution Spectral Encoding}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {54-63} }
Enhancing Embodied Object Detection with Spatial Feature Memory: Nicolas Harvey Chapman,

Christopher Lehnert,

Will Browne,

Feras Dayoub; [pdf] [supp]
[bibtex]
@InProceedings{Chapman_2025_WACV, author = {Chapman, Nicolas Harvey and Lehnert, Christopher and Browne, Will and Dayoub, Feras}, title = {Enhancing Embodied Object Detection with Spatial Feature Memory}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6921-6931} }
ROSA: Reconstructing Object Shape and Appearance Textures by Adaptive Detail Transfer: Julian Kaltheuner,

Patrick Stotko,

Reinhard Klein; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kaltheuner_2025_WACV, author = {Kaltheuner, Julian and Stotko, Patrick and Klein, Reinhard}, title = {ROSA: Reconstructing Object Shape and Appearance Textures by Adaptive Detail Transfer}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2910-2920} }
Interactive Object Detection for Tiny Objects in Large Remotely Sensed Images: Marvin Burges,

Sebastian Zambanini,

Robert Sablatnig; [pdf]
[bibtex]
@InProceedings{Burges_2025_WACV, author = {Burges, Marvin and Zambanini, Sebastian and Sablatnig, Robert}, title = {Interactive Object Detection for Tiny Objects in Large Remotely Sensed Images}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4704-4713} }
Cross-Task Affinity Learning for Multitask Dense Scene Predictions: Dimitrios Sinodinos,

Narges Armanfard; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sinodinos_2025_WACV, author = {Sinodinos, Dimitrios and Armanfard, Narges}, title = {Cross-Task Affinity Learning for Multitask Dense Scene Predictions}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1546-1555} }
LORD: Large Models Based Opposite Reward Design for Autonomous Driving: Xin Ye,

Feng Tao,

Abhirup Mallik,

Burhaneddin Yaman,

Liu Ren; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ye_2025_WACV, author = {Ye, Xin and Tao, Feng and Mallik, Abhirup and Yaman, Burhaneddin and Ren, Liu}, title = {LORD: Large Models Based Opposite Reward Design for Autonomous Driving}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5072-5081} }
Moment of Untruth: Dealing with Negative Queries in Video Moment Retrieval: Kevin Flanagan,

Dima Damen,

Michael Wray; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Flanagan_2025_WACV, author = {Flanagan, Kevin and Damen, Dima and Wray, Michael}, title = {Moment of Untruth: Dealing with Negative Queries in Video Moment Retrieval}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5336-5345} }
Sparse-View 3D Reconstruction of Clothed Humans via Normal Maps: Jane Wu,

Diego Thomas,

Ronald Fedkiw; [pdf] [supp]
[bibtex]
@InProceedings{Wu_2025_WACV, author = {Wu, Jane and Thomas, Diego and Fedkiw, Ronald}, title = {Sparse-View 3D Reconstruction of Clothed Humans via Normal Maps}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {11-22} }
Optimizing Neural Network Effectiveness via Non-Monotonicity Refinement: Koushik Biswas,

Amit Reza,

Meghana Karri,

Debesh Jha,

Hongyi Pan,

Nikhil Tomar,

Aliza Subedi,

Smriti Regmi,

Ulas Bagci; [pdf] [supp]
[bibtex]
@InProceedings{Biswas_2025_WACV, author = {Biswas, Koushik and Reza, Amit and Karri, Meghana and Jha, Debesh and Pan, Hongyi and Tomar, Nikhil and Subedi, Aliza and Regmi, Smriti and Bagci, Ulas}, title = {Optimizing Neural Network Effectiveness via Non-Monotonicity Refinement}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4300-4309} }
STRIDE: Single-Video Based Temporally Continuous Occlusion-Robust 3D Pose Estimation: Rohit Lal,

Saketh Bachu,

Yash Garg,

Arindam Dutta,

Calvin-Khang Ta,

Hannah Dela Cruz,

Dripta S. Raychaudhuri,

M. Salman Asif,

Amit Roy-Chowdhury; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lal_2025_WACV, author = {Lal, Rohit and Bachu, Saketh and Garg, Yash and Dutta, Arindam and Ta, Calvin-Khang and Cruz, Hannah Dela and Raychaudhuri, Dripta S. and Asif, M. Salman and Roy-Chowdhury, Amit}, title = {STRIDE: Single-Video Based Temporally Continuous Occlusion-Robust 3D Pose Estimation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {794-803} }
Multi-HexPlanes: A Lightweight Map Representation for Rendering and 3D Reconstruction: Jianhao Zheng,

Gábor Valasek,

Daniel Barath,

Iro Armeni; [pdf] [supp]
[bibtex]
@InProceedings{Zheng_2025_WACV, author = {Zheng, Jianhao and Valasek, G\'abor and Barath, Daniel and Armeni, Iro}, title = {Multi-HexPlanes: A Lightweight Map Representation for Rendering and 3D Reconstruction}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2021-2031} }
MLLM-Tool: A Multimodal Large Language Model for Tool Agent Learning: Chenyu Wang,

Weixin Luo,

Sixun Dong,

Xiaohua Xuan,

Zhengxin Li,

Lin Ma,

Shenghua Gao; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2025_WACV, author = {Wang, Chenyu and Luo, Weixin and Dong, Sixun and Xuan, Xiaohua and Li, Zhengxin and Ma, Lin and Gao, Shenghua}, title = {MLLM-Tool: A Multimodal Large Language Model for Tool Agent Learning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6678-6687} }
Skyeyes: Ground Roaming using Aerial View Images: Zhiyuan Gao,

Wenbin Teng,

Gonglin Chen,

Jinsen Wu,

Ningli Xu,

Rongjun Qin,

Andrew Feng,

Yajie Zhao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gao_2025_WACV, author = {Gao, Zhiyuan and Teng, Wenbin and Chen, Gonglin and Wu, Jinsen and Xu, Ningli and Qin, Rongjun and Feng, Andrew and Zhao, Yajie}, title = {Skyeyes: Ground Roaming using Aerial View Images}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3045-3054} }
Closing the Domain Gap in Manga Colorization via Aligned Paired Dataset: Maksim Golyadkin,

Ianis Plevokas,

Ilya Makarov; [pdf] [supp]
[bibtex]
@InProceedings{Golyadkin_2025_WACV, author = {Golyadkin, Maksim and Plevokas, Ianis and Makarov, Ilya}, title = {Closing the Domain Gap in Manga Colorization via Aligned Paired Dataset}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5580-5590} }
VaLID: Variable-Length Input Diffusion for Novel View Synthesis: Shijie Li,

Farhad G. Zanjani,

Haitam Ben Yahia,

Yuki Asano,

Juergen Gall,

Amirhossein Habibian; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2025_WACV, author = {Li, Shijie and Zanjani, Farhad G. and Ben Yahia, Haitam and Asano, Yuki and Gall, Juergen and Habibian, Amirhossein}, title = {VaLID: Variable-Length Input Diffusion for Novel View Synthesis}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2240-2249} }
Divergent Domains Convergent Grading: Enhancing Generalization in Diabetic Retinopathy Grading: Sharon Chokuwa,

Muhammad Haris Khan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chokuwa_2025_WACV, author = {Chokuwa, Sharon and Khan, Muhammad Haris}, title = {Divergent Domains Convergent Grading: Enhancing Generalization in Diabetic Retinopathy Grading}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3667-3677} }
Relational Self-Supervised Distillation with Compact Descriptors for Image Copy Detection: Juntae Kim,

Sungwon Woo,

Jongho Nang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2025_WACV, author = {Kim, Juntae and Woo, Sungwon and Nang, Jongho}, title = {Relational Self-Supervised Distillation with Compact Descriptors for Image Copy Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7316-7325} }
FlashMix: Fast Map-Free LiDAR Localization via Feature Mixing and Contrastive-Constrained Accelerated Training: Raktim Gautam Goswami,

Naman Patel,

Prashanth Krishnamurthy,

Farshad Khorrami; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Goswami_2025_WACV, author = {Goswami, Raktim Gautam and Patel, Naman and Krishnamurthy, Prashanth and Khorrami, Farshad}, title = {FlashMix: Fast Map-Free LiDAR Localization via Feature Mixing and Contrastive-Constrained Accelerated Training}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2011-2020} }
EI-Nexus: Towards Unmediated and Flexible Inter-Modality Local Feature Extraction and Matching for Event-Image Data: Zhonghua Yi,

Hao Shi,

Qi Jiang,

Kailun Yang,

Ze Wang,

Diyang Gu,

Yufan Zhang,

Kaiwei Wang; [pdf] [supp]
[bibtex]
@InProceedings{Yi_2025_WACV, author = {Yi, Zhonghua and Shi, Hao and Jiang, Qi and Yang, Kailun and Wang, Ze and Gu, Diyang and Zhang, Yufan and Wang, Kaiwei}, title = {EI-Nexus: Towards Unmediated and Flexible Inter-Modality Local Feature Extraction and Matching for Event-Image Data}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1979-1988} }
Towards Robust Training via Gradient-Diversified Backpropagation: Xilin He,

Cheng Luo,

Qinliang Lin,

Weicheng Xie,

Muhammad Haris Khan,

Siyang Song,

Linlin Shen; [pdf]
[bibtex]
@InProceedings{He_2025_WACV, author = {He, Xilin and Luo, Cheng and Lin, Qinliang and Xie, Weicheng and Khan, Muhammad Haris and Song, Siyang and Shen, Linlin}, title = {Towards Robust Training via Gradient-Diversified Backpropagation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7836-7845} }
A Spatio-Temporal Representation Learning as an Alternative to Traditional Glosses in Sign Language Translation and Production: Eui Jun Hwang,

Sukmin Cho,

Huije Lee,

Youngwoo Yoon,

Jong C. Park; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hwang_2025_WACV, author = {Hwang, Eui Jun and Cho, Sukmin and Lee, Huije and Yoon, Youngwoo and Park, Jong C.}, title = {A Spatio-Temporal Representation Learning as an Alternative to Traditional Glosses in Sign Language Translation and Production}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3352-3362} }
Benchmarking VLMs' Reasoning About Persuasive Atypical Images: Sina Malakouti,

Aysan Aghazadeh,

Ashmit Khandelwal,

Adriana Kovashka; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Malakouti_2025_WACV, author = {Malakouti, Sina and Aghazadeh, Aysan and Khandelwal, Ashmit and Kovashka, Adriana}, title = {Benchmarking VLMs' Reasoning About Persuasive Atypical Images}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4788-4798} }
Uncertainty Awareness Enables Efficient Labeling for Cancer Subtyping in Digital Pathology: Nirhoshan Sivaroopan,

Chamuditha Jayanga Galappaththige,

Chalani Ekanayake,

Hasindri Watawana,

Ranga Rodrigo,

Chamira U.S. Edussooriya,

Dushan N. Wadduwage; [pdf]
[bibtex]
@InProceedings{Sivaroopan_2025_WACV, author = {Sivaroopan, Nirhoshan and Galappaththige, Chamuditha Jayanga and Ekanayake, Chalani and Watawana, Hasindri and Rodrigo, Ranga and Edussooriya, Chamira U.S. and Wadduwage, Dushan N.}, title = {Uncertainty Awareness Enables Efficient Labeling for Cancer Subtyping in Digital Pathology}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {589-598} }
3D Part Segmentation via Geometric Aggregation of 2D Visual Features: Marco Garosi,

Riccardo Tedoldi,

Davide Boscaini,

Massimiliano Mancini,

Nicu Sebe,

Fabio Poiesi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Garosi_2025_WACV, author = {Garosi, Marco and Tedoldi, Riccardo and Boscaini, Davide and Mancini, Massimiliano and Sebe, Nicu and Poiesi, Fabio}, title = {3D Part Segmentation via Geometric Aggregation of 2D Visual Features}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3257-3267} }
BioPose: Biomechanically-Accurate 3D Pose Estimation from Monocular Videos: Farnoosh Koleini,

Muhammad Usama Saleem,

Pu Wang,

Hongfei Xue,

Ahmed Helmy,

Abbey Fenwick; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Koleini_2025_WACV, author = {Koleini, Farnoosh and Saleem, Muhammad Usama and Wang, Pu and Xue, Hongfei and Helmy, Ahmed and Fenwick, Abbey}, title = {BioPose: Biomechanically-Accurate 3D Pose Estimation from Monocular Videos}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6330-6339} }
DPA: Dual Prototypes Alignment for Unsupervised Adaptation of Vision-Language Models: Eman Ali,

Sathira Silva,

Muhammad Haris Khan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ali_2025_WACV, author = {Ali, Eman and Silva, Sathira and Khan, Muhammad Haris}, title = {DPA: Dual Prototypes Alignment for Unsupervised Adaptation of Vision-Language Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6083-6093} }
Re-Evaluating Group Robustness via Adaptive Class-Specific Scaling: Seonguk Seo,

Bohyung Han; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Seo_2025_WACV, author = {Seo, Seonguk and Han, Bohyung}, title = {Re-Evaluating Group Robustness via Adaptive Class-Specific Scaling}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8368-8377} }
Ego-VPA: Egocentric Video Understanding with Parameter-Efficient Adaptation: Tz-Ying Wu,

Kyle Min,

Subarna Tripathi,

Nuno Vasconcelos; [pdf] [supp]
[bibtex]
@InProceedings{Wu_2025_WACV, author = {Wu, Tz-Ying and Min, Kyle and Tripathi, Subarna and Vasconcelos, Nuno}, title = {Ego-VPA: Egocentric Video Understanding with Parameter-Efficient Adaptation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9240-9250} }
Weight Copy and Low-Rank Adaptation for Few-Shot Distillation of Vision Transformers: Diana-Nicoleta Grigore,

Mariana-Iuliana Georgescu,

Jon Alvarez Justo,

Tor Johansen,

Andreea Iuliana Ionescu,

Radu Tudor Ionescu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Grigore_2025_WACV, author = {Grigore, Diana-Nicoleta and Georgescu, Mariana-Iuliana and Justo, Jon Alvarez and Johansen, Tor and Ionescu, Andreea Iuliana and Ionescu, Radu Tudor}, title = {Weight Copy and Low-Rank Adaptation for Few-Shot Distillation of Vision Transformers}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7368-7378} }
FAIR-TAT: Improving Model Fairness using Targeted Adversarial Training: Tejaswini Medi,

Steffen Jung,

Margret Keuper; [pdf] [supp]
[bibtex]
@InProceedings{Medi_2025_WACV, author = {Medi, Tejaswini and Jung, Steffen and Keuper, Margret}, title = {FAIR-TAT: Improving Model Fairness using Targeted Adversarial Training}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7816-7825} }
Semantic Prompting with Image Token for Continual Learning: Jisu Han,

Jaemin Na,

Wonjun Hwang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Han_2025_WACV, author = {Han, Jisu and Na, Jaemin and Hwang, Wonjun}, title = {Semantic Prompting with Image Token for Continual Learning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6987-6997} }
EmoVOCA: Speech-Driven Emotional 3D Talking Heads: Federico Nocentini,

Claudio Ferrari,

Stefano Berretti; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nocentini_2025_WACV, author = {Nocentini, Federico and Ferrari, Claudio and Berretti, Stefano}, title = {EmoVOCA: Speech-Driven Emotional 3D Talking Heads}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2859-2868} }
Sun Off Lights On: Photorealistic Monocular Nighttime Simulation for Robust Semantic Perception: Konstantinos Tzevelekakis,

Shutong Zhang,

Luc Van Gool,

Christos Sakaridis; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tzevelekakis_2025_WACV, author = {Tzevelekakis, Konstantinos and Zhang, Shutong and Van Gool, Luc and Sakaridis, Christos}, title = {Sun Off Lights On: Photorealistic Monocular Nighttime Simulation for Robust Semantic Perception}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1818-1828} }
Online-LoRA: Task-Free Online Continual Learning via Low Rank Adaptation: Xiwen Wei,

Guihong Li,

Radu Marculescu; [pdf] [supp]
[bibtex]
@InProceedings{Wei_2025_WACV, author = {Wei, Xiwen and Li, Guihong and Marculescu, Radu}, title = {Online-LoRA: Task-Free Online Continual Learning via Low Rank Adaptation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6634-6645} }
Improving Zero-Shot Object-Level Change Detection by Incorporating Visual Correspondence: Hung Huy Nguyen,

Pooyan Rahmanzadehgervi,

Long Mai,

Anh Totti Nguyen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nguyen_2025_WACV, author = {Nguyen, Hung Huy and Rahmanzadehgervi, Pooyan and Mai, Long and Nguyen, Anh Totti}, title = {Improving Zero-Shot Object-Level Change Detection by Incorporating Visual Correspondence}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8815-8815} }
FASTER: A Font-Agnostic Scene Text Editing and Rendering Framework: Alloy Das,

Sanket Biswas,

Prasun Roy,

Subhankar Ghosh,

Umapada Pal,

Michael Blumenstein,

Josep Lladós,

Saumik Bhattacharya; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Das_2025_WACV, author = {Das, Alloy and Biswas, Sanket and Roy, Prasun and Ghosh, Subhankar and Pal, Umapada and Blumenstein, Michael and Llad\'os, Josep and Bhattacharya, Saumik}, title = {FASTER: A Font-Agnostic Scene Text Editing and Rendering Framework}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1944-1954} }
DragText: Rethinking Text Embedding in Point-Based Image Editing: Gayoon Choi,

Taejin Jeong,

Sujung Hong,

Seong Jae Hwang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Choi_2025_WACV, author = {Choi, Gayoon and Jeong, Taejin and Hong, Sujung and Hwang, Seong Jae}, title = {DragText: Rethinking Text Embedding in Point-Based Image Editing}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {441-450} }
Reversing the Damage: A QP-Aware Transformer-Diffusion Approach for 8K Video Restoration under Codec Compression: Ali Mollaahmadi Dehaghi,

Reza Razavi,

Mohammad Moshirpour; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dehaghi_2025_WACV, author = {Dehaghi, Ali Mollaahmadi and Razavi, Reza and Moshirpour, Mohammad}, title = {Reversing the Damage: A QP-Aware Transformer-Diffusion Approach for 8K Video Restoration under Codec Compression}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1258-1267} }
Lifting by Gaussians: A Simple Fast and Flexible Method for 3D Instance Segmentation: Rohan Chacko,

Nicolai Häeni,

Eldar Khaliullin,

Lin Sun,

Douglas Lee; [pdf] [supp]
[bibtex]
@InProceedings{Chacko_2025_WACV, author = {Chacko, Rohan and H\"aeni, Nicolai and Khaliullin, Eldar and Sun, Lin and Lee, Douglas}, title = {Lifting by Gaussians: A Simple Fast and Flexible Method for 3D Instance Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3497-3507} }
TimberVision: A Multi-Task Dataset and Framework for Log-Component Segmentation and Tracking in Autonomous Forestry Operations: Daniel Steininger,

Julia Simon,

Andreas Trondl,

Markus Murschitz; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Steininger_2025_WACV, author = {Steininger, Daniel and Simon, Julia and Trondl, Andreas and Murschitz, Markus}, title = {TimberVision: A Multi-Task Dataset and Framework for Log-Component Segmentation and Tracking in Autonomous Forestry Operations}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5601-5610} }
MimicGait: A Model Agnostic Approach for Occluded Gait Recognition using Correlational Knowledge Distillation: Ayush Gupta,

Rama Chellappa; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gupta_2025_WACV, author = {Gupta, Ayush and Chellappa, Rama}, title = {MimicGait: A Model Agnostic Approach for Occluded Gait Recognition using Correlational Knowledge Distillation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4757-4766} }
PoolAtnRes: Towards Generalisable Differential Morphing Attack Detection: Raghavendra Ramachandra,

Sushma Krupa Venkatesh,

Guoqiang Li; [pdf]
[bibtex]
@InProceedings{Ramachandra_2025_WACV, author = {Ramachandra, Raghavendra and Venkatesh, Sushma Krupa and Li, Guoqiang}, title = {PoolAtnRes: Towards Generalisable Differential Morphing Attack Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9294-9303} }
DMRN: A Dynamical Multi-Order Response Network for the Robust Lung Airway Segmentation: Sheng Zhang,

Jinge Wu,

Junzhi Ning,

Guang Yang; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2025_WACV, author = {Zhang, Sheng and Wu, Jinge and Ning, Junzhi and Yang, Guang}, title = {DMRN: A Dynamical Multi-Order Response Network for the Robust Lung Airway Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4036-4045} }
Self-Supervised Learning with Spectral Low-Rank Prior for Hyperspectral Image Reconstruction: Zijun He,

Lishun Wang,

Ziyi Meng,

Xin Yuan; [pdf]
[bibtex]
@InProceedings{He_2025_WACV, author = {He, Zijun and Wang, Lishun and Meng, Ziyi and Yuan, Xin}, title = {Self-Supervised Learning with Spectral Low-Rank Prior for Hyperspectral Image Reconstruction}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9118-9127} }
Improving Deep Detector Robustness via Detection-Related Discriminant Maximization and Reorganization: Jung Im Choi,

Qizhen Lan,

Qing Tian; [pdf]
[bibtex]
@InProceedings{Choi_2025_WACV, author = {Choi, Jung Im and Lan, Qizhen and Tian, Qing}, title = {Improving Deep Detector Robustness via Detection-Related Discriminant Maximization and Reorganization}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1518-1527} }
MAISI: Medical AI for Synthetic Imaging: Pengfei Guo,

Can Zhao,

Dong Yang,

Ziyue Xu,

Vishwesh Nath,

Yucheng Tang,

Benjamin Simon,

Mason Belue,

Stephanie Harmon,

Baris Turkbey,

Daguang Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guo_2025_WACV, author = {Guo, Pengfei and Zhao, Can and Yang, Dong and Xu, Ziyue and Nath, Vishwesh and Tang, Yucheng and Simon, Benjamin and Belue, Mason and Harmon, Stephanie and Turkbey, Baris and Xu, Daguang}, title = {MAISI: Medical AI for Synthetic Imaging}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4430-4441} }
Attribute Diffusion: Diffusion Driven Diverse Attribute Editing: Rishubh Parihar,

Prasanna Balaji,

Raghav Magazine,

Sarthak Vora,

Varun Jampani,

Venkatesh Babu Radhakrishnan; [pdf] [supp]
[bibtex]
@InProceedings{Parihar_2025_WACV, author = {Parihar, Rishubh and Balaji, Prasanna and Magazine, Raghav and Vora, Sarthak and Jampani, Varun and Radhakrishnan, Venkatesh Babu}, title = {Attribute Diffusion: Diffusion Driven Diverse Attribute Editing}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3721-3731} }
Recoverable Anonymization for Pose Estimation: A Privacy-Enhancing Approach: Wenjun Huang,

Yang Ni,

Arghavan Rezvani Dehaghani,

SungHeon Evan Jeong,

Hanning Chen,

Yezi Liu,

Fei Wen,

Mohsen Imani; [pdf]
[bibtex]
@InProceedings{Huang_2025_WACV, author = {Huang, Wenjun and Ni, Yang and Dehaghani, Arghavan Rezvani and Jeong, SungHeon Evan and Chen, Hanning and Liu, Yezi and Wen, Fei and Imani, Mohsen}, title = {Recoverable Anonymization for Pose Estimation: A Privacy-Enhancing Approach}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5239-5249} }
DreamBlend: Advancing Personalized Fine-Tuning of Text-to-Image Diffusion Models: Shwetha Ram,

Tal Neiman,

Qianli Feng,

Andrew M Stuart,

Son Tran,

Trishul A Chilimbi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ram_2025_WACV, author = {Ram, Shwetha and Neiman, Tal and Feng, Qianli and Stuart, Andrew M and Tran, Son and A Chilimbi, Trishul}, title = {DreamBlend: Advancing Personalized Fine-Tuning of Text-to-Image Diffusion Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3614-3623} }
MonoPP: Metric-Scaled Self-Supervised Monocular Depth Estimation by Planar-Parallax Geometry in Automotive Applications: Gasser Elazab,

Torben Gräber,

Michael Unterreiner,

Olaf Hellwich; [pdf] [supp]
[bibtex]
@InProceedings{Elazab_2025_WACV, author = {Elazab, Gasser and Gr\"aber, Torben and Unterreiner, Michael and Hellwich, Olaf}, title = {MonoPP: Metric-Scaled Self-Supervised Monocular Depth Estimation by Planar-Parallax Geometry in Automotive Applications}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2777-2787} }
Feasibility of Federated Learning from Client Databases with Different Brain Diseases and MRI Modalities: Felix Wagner,

Wentian Xu,

Pramit Saha,

Ziyun Liang,

Daniel Whitehouse,

David Menon,

Virginia Newcombe,

Natalie Voets,

J. Alison Noble,

Konstantinos Kamnitsas; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wagner_2025_WACV, author = {Wagner, Felix and Xu, Wentian and Saha, Pramit and Liang, Ziyun and Whitehouse, Daniel and Menon, David and Newcombe, Virginia and Voets, Natalie and Noble, J. Alison and Kamnitsas, Konstantinos}, title = {Feasibility of Federated Learning from Client Databases with Different Brain Diseases and MRI Modalities}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {357-367} }
A Generic Vehicle-to-Sensor Calibration Framework: Sumin Hu,

Youngmin Yoo,

Jeeseong Kim,

Changsoo Lim,

Doohyun Cho,

Bongnam Kang; [pdf] [supp]
[bibtex]
@InProceedings{Hu_2025_WACV, author = {Hu, Sumin and Yoo, Youngmin and Kim, Jeeseong and Lim, Changsoo and Cho, Doohyun and Kang, Bongnam}, title = {A Generic Vehicle-to-Sensor Calibration Framework}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5980-5989} }
Learning Deep Illumination-Robust Features from Multispectral Filter Array Images: Anis Amziane; [pdf] [arXiv]
[bibtex]
@InProceedings{Amziane_2025_WACV, author = {Amziane, Anis}, title = {Learning Deep Illumination-Robust Features from Multispectral Filter Array Images}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8877-8886} }
Point-GN: A Non-Parametric Network using Gaussian Positional Encoding for Point Cloud Classification: Marzieh Mohammadi,

Amir Salarpour; [pdf]
[bibtex]
@InProceedings{Mohammadi_2025_WACV, author = {Mohammadi, Marzieh and Salarpour, Amir}, title = {Point-GN: A Non-Parametric Network using Gaussian Positional Encoding for Point Cloud Classification}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3487-3496} }
Skip-and-Play: Depth-Driven Pose-Preserved Image Generation for Any Objects: Kyungmin Jo,

Jaegul Choo; [pdf] [supp]
[bibtex]
@InProceedings{Jo_2025_WACV, author = {Jo, Kyungmin and Choo, Jaegul}, title = {Skip-and-Play: Depth-Driven Pose-Preserved Image Generation for Any Objects}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {690-699} }
Generating Visual Explanations from Deep Networks using Implicit Neural Representations: Michal Byra,

Henrik Skibbe; [pdf] [arXiv]
[bibtex]
@InProceedings{Byra_2025_WACV, author = {Byra, Michal and Skibbe, Henrik}, title = {Generating Visual Explanations from Deep Networks using Implicit Neural Representations}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3310-3319} }
Label Calibration in Source Free Domain Adaptation: Shivangi Rai,

Rini Smita Thakur,

Kunal Jangid,

Vinod K Kurmi; [pdf] [arXiv]
[bibtex]
@InProceedings{Rai_2025_WACV, author = {Rai, Shivangi and Thakur, Rini Smita and Jangid, Kunal and Kurmi, Vinod K}, title = {Label Calibration in Source Free Domain Adaptation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6446-6455} }
Debiasify: Self-Distillation for Unsupervised Bias Mitigation: Nourhan Bayasi,

Jamil Fayyad,

Ghassan Hamarneh,

Rafeef Garbi,

Homayoun Najjaran; [pdf] [arXiv]
[bibtex]
@InProceedings{Bayasi_2025_WACV, author = {Bayasi, Nourhan and Fayyad, Jamil and Hamarneh, Ghassan and Garbi, Rafeef and Najjaran, Homayoun}, title = {Debiasify: Self-Distillation for Unsupervised Bias Mitigation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3227-3236} }
DashCop: Automated E-Ticket Generation for Two-Wheeler Traffic Violations using Dashcam Videos: Deepti Rawat,

Keshav Gupta,

Aryamaan Basu Roy,

Ravi Kiran Sarvadevabhatla; [pdf]
[bibtex]
@InProceedings{Rawat_2025_WACV, author = {Rawat, Deepti and Gupta, Keshav and Roy, Aryamaan Basu and Sarvadevabhatla, Ravi Kiran}, title = {DashCop: Automated E-Ticket Generation for Two-Wheeler Traffic Violations using Dashcam Videos}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5387-5397} }
Enhancing Image Layout Control with Loss-Guided Diffusion Models: Zakaria Patel,

Kirill Serkh; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Patel_2025_WACV, author = {Patel, Zakaria and Serkh, Kirill}, title = {Enhancing Image Layout Control with Loss-Guided Diffusion Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3916-3924} }
LiCamPose: Combining Multi-View LiDAR and RGB Cameras for Robust Single-Timestamp 3D Human Pose Estimation: Zhiyu Pan,

Zhicheng Zhong,

Wenxuan Guo,

Yifan Chen,

Jianjiang Feng,

Jie Zhou; [pdf] [supp]
[bibtex]
@InProceedings{Pan_2025_WACV, author = {Pan, Zhiyu and Zhong, Zhicheng and Guo, Wenxuan and Chen, Yifan and Feng, Jianjiang and Zhou, Jie}, title = {LiCamPose: Combining Multi-View LiDAR and RGB Cameras for Robust Single-Timestamp 3D Human Pose Estimation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2484-2494} }
FluoNeRF: Fluorescent Novel-View Synthesis under Novel Light Source Colors: Lin Shi,

Kengo Matsufuji,

Ryo Kawahara,

Takahiro Okabe; [pdf] [supp]
[bibtex]
@InProceedings{Shi_2025_WACV, author = {Shi, Lin and Matsufuji, Kengo and Kawahara, Ryo and Okabe, Takahiro}, title = {FluoNeRF: Fluorescent Novel-View Synthesis under Novel Light Source Colors}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2032-2041} }
Planar Gaussian Splatting: Farhad G. Zanjani,

Hong Cai,

Hanno Ackermann,

Leila Mirvakhabova,

Fatih Porikli; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zanjani_2025_WACV, author = {Zanjani, Farhad G. and Cai, Hong and Ackermann, Hanno and Mirvakhabova, Leila and Porikli, Fatih}, title = {Planar Gaussian Splatting}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8887-8896} }
Importance-Guided Interpretability and Pruning for Video Transformers in Driver Action Recognition: Raquel Panadero Palenzuela,

Dominik Schörkhuber,

Margrit Gelautz; [pdf] [supp]
[bibtex]
@InProceedings{Palenzuela_2025_WACV, author = {Palenzuela, Raquel Panadero and Sch\"orkhuber, Dominik and Gelautz, Margrit}, title = {Importance-Guided Interpretability and Pruning for Video Transformers in Driver Action Recognition}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5295-5304} }
McCaD: Multi-Contrast MRI Conditioned Adaptive Adversarial Diffusion Model for High-Fidelity MRI Synthesis: Sanuwani Dayarathna,

Kh Tohidul Islam,

Bohan Zhuang,

Guang Yang,

Jianfei Cai,

Meng Law,

Zhaolin Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dayarathna_2025_WACV, author = {Dayarathna, Sanuwani and Islam, Kh Tohidul and Zhuang, Bohan and Yang, Guang and Cai, Jianfei and Law, Meng and Chen, Zhaolin}, title = {McCaD: Multi-Contrast MRI Conditioned Adaptive Adversarial Diffusion Model for High-Fidelity MRI Synthesis}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {670-679} }
Detecting Wildfires on UAVs with Real-Time Segmentation Trained by Larger Teacher Models: Julius Pesonen,

Teemu Hakala,

Väinö Karjalainen,

Niko Koivumäki,

Lauri Markelin,

Anna-Maria Raita-Hakola,

Juha Suomalainen,

Ilkka Pölönen,

Eija Honkavaara; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pesonen_2025_WACV, author = {Pesonen, Julius and Hakala, Teemu and Karjalainen, V\"ain\"o and Koivum\"aki, Niko and Markelin, Lauri and Raita-Hakola, Anna-Maria and Suomalainen, Juha and P\"ol\"onen, Ilkka and Honkavaara, Eija}, title = {Detecting Wildfires on UAVs with Real-Time Segmentation Trained by Larger Teacher Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5166-5176} }
Multi-Class Textual-Inversion Secretly Yields a Semantic-Agnostic Classifier: Kai Wang,

Fei Yang,

Bogdan Raducanu,

Joost van de Weijer; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2025_WACV, author = {Wang, Kai and Yang, Fei and Raducanu, Bogdan and van de Weijer, Joost}, title = {Multi-Class Textual-Inversion Secretly Yields a Semantic-Agnostic Classifier}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4400-4409} }
FaVoR: Features via Voxel Rendering for Camera Relocalization: Vincenzo Polizzi,

Marco Cannici,

Davide Scaramuzza,

Jonathan Kelly; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Polizzi_2025_WACV, author = {Polizzi, Vincenzo and Cannici, Marco and Scaramuzza, Davide and Kelly, Jonathan}, title = {FaVoR: Features via Voxel Rendering for Camera Relocalization}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {44-53} }
Label Augmented Dataset Distillation: Seoungyoon Kang,

Youngsun Lim,

Hyunjung Shim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kang_2025_WACV, author = {Kang, Seoungyoon and Lim, Youngsun and Shim, Hyunjung}, title = {Label Augmented Dataset Distillation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1457-1466} }
Towards Privacy-Preserving Split Learning for ControlNet: Dixi Yao; [pdf] [supp]
[bibtex]
@InProceedings{Yao_2025_WACV, author = {Yao, Dixi}, title = {Towards Privacy-Preserving Split Learning for ControlNet}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {139-148} }
Solar Multimodal Transformer: Intraday Solar Irradiance Predictor using Public Cameras and Time Series: Yanan Niu,

Roy Sarkis,

Demetri Psaltis,

Mario Paolone,

Christophe Moser,

Luisa Lambertini; [pdf] [supp]
[bibtex]
@InProceedings{Niu_2025_WACV, author = {Niu, Yanan and Sarkis, Roy and Psaltis, Demetri and Paolone, Mario and Moser, Christophe and Lambertini, Luisa}, title = {Solar Multimodal Transformer: Intraday Solar Irradiance Predictor using Public Cameras and Time Series}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5051-5060} }
Finding Dino: A Plug-and-Play Framework for Zero-Shot Detection of Out-of-Distribution Objects using Prototypes: Poulami Sinhamahapatra,

Franziska Schwaiger,

Shirsha Bose,

Huiyu Wang,

Karsten Roscher,

Stephan Günnemann; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sinhamahapatra_2025_WACV, author = {Sinhamahapatra, Poulami and Schwaiger, Franziska and Bose, Shirsha and Wang, Huiyu and Roscher, Karsten and G\"unnemann, Stephan}, title = {Finding Dino: A Plug-and-Play Framework for Zero-Shot Detection of Out-of-Distribution Objects using Prototypes}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8463-8472} }
Semantic Prompt Learning for Weakly-Supervised Semantic Segmentation: Ci-Siang Lin,

Chien-Yi Wang,

Yu-Chiang Frank Wang,

Min-Hung Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lin_2025_WACV, author = {Lin, Ci-Siang and Wang, Chien-Yi and Wang, Yu-Chiang Frank and Chen, Min-Hung}, title = {Semantic Prompt Learning for Weakly-Supervised Semantic Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8753-8763} }
Evaluating Sensitivity Consistency of Explanations: Hanxiao Tan; [pdf] [supp]
[bibtex]
@InProceedings{Tan_2025_WACV, author = {Tan, Hanxiao}, title = {Evaluating Sensitivity Consistency of Explanations}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {182-191} }
EgoSonics: Generating Synchronized Audio for Silent Egocentric Videos: Aashish Rai,

Srinath Sridhar; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Rai_2025_WACV, author = {Rai, Aashish and Sridhar, Srinath}, title = {EgoSonics: Generating Synchronized Audio for Silent Egocentric Videos}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4935-4946} }
DiaMond: Dementia Diagnosis with Multi-Modal Vision Transformers using MRI and PET: Yitong Li,

Morteza Ghahremani,

Youssef Wally,

Christian Wachinger; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2025_WACV, author = {Li, Yitong and Ghahremani, Morteza and Wally, Youssef and Wachinger, Christian}, title = {DiaMond: Dementia Diagnosis with Multi-Modal Vision Transformers using MRI and PET}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {107-116} }
Deep Metric Learning for Unsupervised Remote Sensing Change Detection: Wele Gedara Chaminda Bandara,

Vishal M. Patel; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bandara_2025_WACV, author = {Bandara, Wele Gedara Chaminda and Patel, Vishal M.}, title = {Deep Metric Learning for Unsupervised Remote Sensing Change Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5125-5135} }
Learning Semi-Supervised Medical Image Segmentation from Spatial Registration: Qianying Liu,

Paul Henderson,

Xiao Gu,

Hang Dai,

Fani Deligianni; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2025_WACV, author = {Liu, Qianying and Henderson, Paul and Gu, Xiao and Dai, Hang and Deligianni, Fani}, title = {Learning Semi-Supervised Medical Image Segmentation from Spatial Registration}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6383-6393} }
Towards High-Fidelity Head Blending with Chroma Keying for Industrial Applications: Hah Min Lew,

Sahng-Min Yoo,

Hyunwoo Kang,

Gyeong-Moon Park; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lew_2025_WACV, author = {Lew, Hah Min and Yoo, Sahng-Min and Kang, Hyunwoo and Park, Gyeong-Moon}, title = {Towards High-Fidelity Head Blending with Chroma Keying for Industrial Applications}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6188-6196} }
LiGAR: LiDAR-Guided Hierarchical Transformer for Multi-Modal Group Activity Recognition: Naga Venkata Sai Raviteja Chappa,

Khoa Luu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chappa_2025_WACV, author = {Chappa, Naga Venkata Sai Raviteja and Luu, Khoa}, title = {LiGAR: LiDAR-Guided Hierarchical Transformer for Multi-Modal Group Activity Recognition}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3035-3044} }
Unsupervised Video Highlight Detection by Learning from Audio and Visual Recurrence: Zahidul Islam,

Sujoy Paul,

Mrigank Rochan; [pdf] [arXiv]
[bibtex]
@InProceedings{Islam_2025_WACV, author = {Islam, Zahidul and Paul, Sujoy and Rochan, Mrigank}, title = {Unsupervised Video Highlight Detection by Learning from Audio and Visual Recurrence}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8691-8700} }
Attention-Based Class-Conditioned Alignment for Multi-Source Domain Adaptation of Object Detectors: Atif Belal,

Akhil Meethal,

Francisco Perdigon Romero,

Marco Pedersoli,

Eric Granger; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Belal_2025_WACV, author = {Belal, Atif and Meethal, Akhil and Romero, Francisco Perdigon and Pedersoli, Marco and Granger, Eric}, title = {Attention-Based Class-Conditioned Alignment for Multi-Source Domain Adaptation of Object Detectors}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8555-8564} }
Stable Autofocus with Focal Consistency Loss: Sangwon Lee,

Myungsub Choi,

Nagyeong Lee,

Hyong-Euk Lee; [pdf] [supp]
[bibtex]
@InProceedings{Lee_2025_WACV, author = {Lee, Sangwon and Choi, Myungsub and Lee, Nagyeong and Lee, Hyong-Euk}, title = {Stable Autofocus with Focal Consistency Loss}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {640-649} }
Bandit Based Attention Mechanism in Vision Transformers: Amartya Roy Chowdhury,

Raghuram Bharadwaj Diddigi,

Prabuchandran K J,

Achyut Mani Tripathi; [pdf] [supp]
[bibtex]
@InProceedings{Chowdhury_2025_WACV, author = {Chowdhury, Amartya Roy and Diddigi, Raghuram Bharadwaj and J, Prabuchandran K and Tripathi, Achyut Mani}, title = {Bandit Based Attention Mechanism in Vision Transformers}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9579-9588} }
Semantically Conditioned Prompts for Visual Recognition under Missing Modality Scenarios: Vittorio Pipoli,

Federico Bolelli,

Sara Sarto,

Marcella Cornia,

Lorenzo Baraldi,

Costantino Grana,

Rita Cucchiara,

Elisa Ficarra; [pdf] [supp]
[bibtex]
@InProceedings{Pipoli_2025_WACV, author = {Pipoli, Vittorio and Bolelli, Federico and Sarto, Sara and Cornia, Marcella and Baraldi, Lorenzo and Grana, Costantino and Cucchiara, Rita and Ficarra, Elisa}, title = {Semantically Conditioned Prompts for Visual Recognition under Missing Modality Scenarios}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4968-4977} }
OccFlowNet: Occupancy Estimation via Differentiable Rendering and Occupancy Flow: Simon Boeder,

Benjamin Risse; [pdf] [supp]
[bibtex]
@InProceedings{Boeder_2025_WACV, author = {Boeder, Simon and Risse, Benjamin}, title = {OccFlowNet: Occupancy Estimation via Differentiable Rendering and Occupancy Flow}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {306-316} }
Cross-Domain Multi-Modal Few-Shot Object Detection via Rich Text: Zeyu Shangguan,

Daniel Seita,

Mohammad Rostami; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shangguan_2025_WACV, author = {Shangguan, Zeyu and Seita, Daniel and Rostami, Mohammad}, title = {Cross-Domain Multi-Modal Few-Shot Object Detection via Rich Text}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6570-6580} }
Local Masked Reconstruction for Efficient Self-Supervised Learning on High-Resolution Images: Jun Chen,

Faizan Farooq Khan,

Ming Hu,

Ammar Sherif,

Zongyuan Ge,

Boyang Li,

Mohamed Elhoseiny; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2025_WACV, author = {Chen, Jun and Khan, Faizan Farooq and Hu, Ming and Sherif, Ammar and Ge, Zongyuan and Li, Boyang and Elhoseiny, Mohamed}, title = {Local Masked Reconstruction for Efficient Self-Supervised Learning on High-Resolution Images}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8035-8045} }
PureForest: A Large-Scale Aerial Lidar and Aerial Imagery Dataset for Tree Species Classification in Monospecific Forests: Charles Gaydon,

Floryne Roche; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gaydon_2025_WACV, author = {Gaydon, Charles and Roche, Floryne}, title = {PureForest: A Large-Scale Aerial Lidar and Aerial Imagery Dataset for Tree Species Classification in Monospecific Forests}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5895-5904} }
ACE: Anatomically Consistent Embeddings in Composition and Decomposition: Ziyu Zhou,

Haozhe Luo,

Mohammad Reza Hosseinzadeh Taher,

Jiaxuan Pang,

Xiaowei Ding,

Michael Gotway,

Jianming Liang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2025_WACV, author = {Zhou, Ziyu and Luo, Haozhe and Taher, Mohammad Reza Hosseinzadeh and Pang, Jiaxuan and Ding, Xiaowei and Gotway, Michael and Liang, Jianming}, title = {ACE: Anatomically Consistent Embeddings in Composition and Decomposition}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3823-3833} }
Q-TempFusion: Quantization-Aware Temporal Multi-Sensor Fusion on Bird's-Eye View Representation: Pinrui Yu,

Zhenglun Kong,

Pu Zhao,

Peiyan Dong,

Hao Tang,

Fei Sun,

Xue Lin,

Yanzhi Wang; [pdf] [supp]
[bibtex]
@InProceedings{Yu_2025_WACV, author = {Yu, Pinrui and Kong, Zhenglun and Zhao, Pu and Dong, Peiyan and Tang, Hao and Sun, Fei and Lin, Xue and Wang, Yanzhi}, title = {Q-TempFusion: Quantization-Aware Temporal Multi-Sensor Fusion on Bird's-Eye View Representation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5489-5499} }
RD-DPP: Rate-Distortion Theory Meets Determinantal Point Process to Diversify Learning Data Samples: Xiwen Chen,

Huayu Li,

Peijie Qiu,

Wenhui Zhu,

Rahul Amin,

Abolfazl Razi; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2025_WACV, author = {Chen, Xiwen and Li, Huayu and Qiu, Peijie and Zhu, Wenhui and Amin, Rahul and Razi, Abolfazl}, title = {RD-DPP: Rate-Distortion Theory Meets Determinantal Point Process to Diversify Learning Data Samples}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6911-6920} }
D2FP: Learning Implicit Prior for Human Parsing: Junyoung Hong,

Hyeri Yang,

Ye Ju Kim,

Haerim Kim,

Shinwoong Kim,

Euna Shim,

Kyungjae Lee; [pdf]
[bibtex]
@InProceedings{Hong_2025_WACV, author = {Hong, Junyoung and Yang, Hyeri and Kim, Ye Ju and Kim, Haerim and Kim, Shinwoong and Shim, Euna and Lee, Kyungjae}, title = {D2FP: Learning Implicit Prior for Human Parsing}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9096-9106} }
ELBA: Learning by Asking for Embodied Visual Navigation and Task Completion: Ying Shen,

Daniel Bis,

Cynthia Lu,

Ismini Lourentzou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shen_2025_WACV, author = {Shen, Ying and Bis, Daniel and Lu, Cynthia and Lourentzou, Ismini}, title = {ELBA: Learning by Asking for Embodied Visual Navigation and Task Completion}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5177-5186} }
DisFlowEm : One-Shot Emotional Talking Head Generation using Disentangled Pose and Expression Flow-Guidance: Sanjana Sinha,

Brojeshwar Bhowmick,

Lokender Tiwari,

Sushovan Chanda; [pdf] [supp]
[bibtex]
@InProceedings{Sinha_2025_WACV, author = {Sinha, Sanjana and Bhowmick, Brojeshwar and Tiwari, Lokender and Chanda, Sushovan}, title = {DisFlowEm : One-Shot Emotional Talking Head Generation using Disentangled Pose and Expression Flow-Guidance}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4841-4851} }
Modality-Incremental Learning with Disjoint Relevance Mapping Networks for Image-Based Semantic Segmentation: Niharika Hegde,

Shishir Muralidhara,

René Schuster,

Didier Stricker; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hegde_2025_WACV, author = {Hegde, Niharika and Muralidhara, Shishir and Schuster, Ren\'e and Stricker, Didier}, title = {Modality-Incremental Learning with Disjoint Relevance Mapping Networks for Image-Based Semantic Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5540-5549} }
Uncertainty-Guided Cross Attention Ensemble Mean Teacher for Semi-Supervised Medical Image Segmentation: Meghana Karri,

Amit Soni Arya,

Koushik Biswas,

Nicolo Gennaro,

Vedat Cicek,

Gorkem Durak,

Yury S. Velichko,

Ulas Bagci; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Karri_2025_WACV, author = {Karri, Meghana and Arya, Amit Soni and Biswas, Koushik and Gennaro, Nicolo and Cicek, Vedat and Durak, Gorkem and Velichko, Yury S. and Bagci, Ulas}, title = {Uncertainty-Guided Cross Attention Ensemble Mean Teacher for Semi-Supervised Medical Image Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7039-7048} }
FUN-AD: Fully Unsupervised Learning for Anomaly Detection with Noisy Training Data: Jiin Im,

Yongho Son,

Je Hyeong Hong; [pdf] [supp]
[bibtex]
@InProceedings{Im_2025_WACV, author = {Im, Jiin and Son, Yongho and Hong, Je Hyeong}, title = {FUN-AD: Fully Unsupervised Learning for Anomaly Detection with Noisy Training Data}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9429-9438} }
Predicting Event Memorability using Personalized Federated Learning: Sourasekhar Banerjee,

Debaditya Roy,

Vigneshwaran Subbaraju,

Monowar Bhuyan; [pdf] [supp]
[bibtex]
@InProceedings{Banerjee_2025_WACV, author = {Banerjee, Sourasekhar and Roy, Debaditya and Subbaraju, Vigneshwaran and Bhuyan, Monowar}, title = {Predicting Event Memorability using Personalized Federated Learning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1556-1565} }
Contrastive Learning of Image Representations Guided by Spatial Relations: Logan Servant,

Michaël Clément,

Laurent Wendling,

Camille Kurtz; [pdf]
[bibtex]
@InProceedings{Servant_2025_WACV, author = {Servant, Logan and Cl\'ement, Micha\"el and Wendling, Laurent and Kurtz, Camille}, title = {Contrastive Learning of Image Representations Guided by Spatial Relations}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2124-2133} }
TAM-VT: Transformation-Aware Multi-Scale Video Transformer for Segmentation and Tracking: Raghav Goyal,

Wan-Cyuan Fan,

Mennatullah Siam,

Leonid Sigal; [pdf] [supp]
[bibtex]
@InProceedings{Goyal_2025_WACV, author = {Goyal, Raghav and Fan, Wan-Cyuan and Siam, Mennatullah and Sigal, Leonid}, title = {TAM-VT: Transformation-Aware Multi-Scale Video Transformer for Segmentation and Tracking}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8325-8334} }
V-MIND: Building Versatile Monocular Indoor 3D Detector with Diverse 2D Annotations: Jin-Cheng Jhang,

Tao Tu,

Fu-En Wang,

Ke Zhang,

Min Sun,

Cheng-Hao Kuo; [pdf]
[bibtex]
@InProceedings{Jhang_2025_WACV, author = {Jhang, Jin-Cheng and Tu, Tao and Wang, Fu-En and Zhang, Ke and Sun, Min and Kuo, Cheng-Hao}, title = {V-MIND: Building Versatile Monocular Indoor 3D Detector with Diverse 2D Annotations}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9559-9568} }
Multi-Surrogate-Teacher Assistance for Representation Alignment in Fingerprint-Based Indoor Localization: Son Minh Nguyen,

Linh Duy Tran,

Duc Le,

Paul Havinga; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nguyen_2025_WACV, author = {Nguyen, Son Minh and Tran, Linh Duy and Le, Duc and Havinga, Paul}, title = {Multi-Surrogate-Teacher Assistance for Representation Alignment in Fingerprint-Based Indoor Localization}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6818-6827} }
FALCON: Fair Face Recognition via Local Optimal Feature Normalization: Rouqaiah Al-Refai,

Philipp Hempel,

Clara Biagi,

Philipp Terhörst; [pdf]
[bibtex]
@InProceedings{Al-Refai_2025_WACV, author = {Al-Refai, Rouqaiah and Hempel, Philipp and Biagi, Clara and Terh\"orst, Philipp}, title = {FALCON: Fair Face Recognition via Local Optimal Feature Normalization}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3416-3426} }
Self-Aligning Depth-Regularized Radiance Fields for Asynchronous RGB-D Sequences: Yuxin Huang,

Andong Yang,

Yuantao Chen,

Runyi Yang,

Zhenxin Zhu,

Chao Hou,

Hao Zhao,

Guyue Zhou; [pdf] [supp]
[bibtex]
@InProceedings{Huang_2025_WACV, author = {Huang, Yuxin and Yang, Andong and Chen, Yuantao and Yang, Runyi and Zhu, Zhenxin and Hou, Chao and Zhao, Hao and Zhou, Guyue}, title = {Self-Aligning Depth-Regularized Radiance Fields for Asynchronous RGB-D Sequences}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {525-534} }
CLIP-Fusion: A Spatio-Temporal Quality Metric for Frame Interpolation: Goksel Mert Çökmez,

Yang Zhang,

Christopher Schroers,

Tunç Ozan Aydin; [pdf] [supp]
[bibtex]
@InProceedings{Cokmez_2025_WACV, author = {\c{C}\"okmez, Goksel Mert and Zhang, Yang and Schroers, Christopher and Aydin, Tun\c{c} Ozan}, title = {CLIP-Fusion: A Spatio-Temporal Quality Metric for Frame Interpolation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7450-7459} }
Dual-Representation Interaction Driven Image Quality Assessment with Restoration Assistance: Jingtong Yue,

Xin Lin,

Zijiu Yang,

Chao Ren; [pdf] [arXiv]
[bibtex]
@InProceedings{Yue_2025_WACV, author = {Yue, Jingtong and Lin, Xin and Yang, Zijiu and Ren, Chao}, title = {Dual-Representation Interaction Driven Image Quality Assessment with Restoration Assistance}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3138-3147} }
Gaussian Deja-vu: Creating Controllable 3D Gaussian Head-Avatars with Enhanced Generalization and Personalization Abilities: Peizhi Yan,

Rabab Ward,

Qiang Tang,

Shan Du; [pdf] [supp]
[bibtex]
@InProceedings{Yan_2025_WACV, author = {Yan, Peizhi and Ward, Rabab and Tang, Qiang and Du, Shan}, title = {Gaussian Deja-vu: Creating Controllable 3D Gaussian Head-Avatars with Enhanced Generalization and Personalization Abilities}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {276-286} }
No Annotations for Object Detection in Art through Stable Diffusion: Patrick Ramos,

Nicolas Gonthier,

Selina Khan,

Yuta Nakashima,

Noa Garcia; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ramos_2025_WACV, author = {Ramos, Patrick and Gonthier, Nicolas and Khan, Selina and Nakashima, Yuta and Garcia, Noa}, title = {No Annotations for Object Detection in Art through Stable Diffusion}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6228-6237} }
Unifying Low-Resolution and High-Resolution Alignment by Event Cameras for Space-Time Video Super-Resolution: Hoonhee Cho,

Jae-Young Kang,

Taewoo Kim,

Yuhwan Jeong,

Kuk-Jin Yoon; [pdf]
[bibtex]
@InProceedings{Cho_2025_WACV, author = {Cho, Hoonhee and Kang, Jae-Young and Kim, Taewoo and Jeong, Yuhwan and Yoon, Kuk-Jin}, title = {Unifying Low-Resolution and High-Resolution Alignment by Event Cameras for Space-Time Video Super-Resolution}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9491-9502} }
GeoPos: A Minimal Positional Encoding for Enhanced Fine-Grained Details in Image Synthesis using Convolutional Neural Networks: Mehran Hosseini,

Peyman Hosseini; [pdf] [arXiv]
[bibtex]
@InProceedings{Hosseini_2025_WACV, author = {Hosseini, Mehran and Hosseini, Peyman}, title = {GeoPos: A Minimal Positional Encoding for Enhanced Fine-Grained Details in Image Synthesis using Convolutional Neural Networks}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7287-7297} }
Diffusion-Based Visual Anagram as Multi-Task Learning: Zhiyuan Xu,

Yinhe Chen,

Huan-ang Gao,

Weiyan Zhao,

Guiyu Zhang,

Hao Zhao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2025_WACV, author = {Xu, Zhiyuan and Chen, Yinhe and Gao, Huan-ang and Zhao, Weiyan and Zhang, Guiyu and Zhao, Hao}, title = {Diffusion-Based Visual Anagram as Multi-Task Learning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {919-928} }
MambaRecon: MRI Reconstruction with Structured State Space Models: Yilmaz Korkmaz,

Vishal M. Patel; [pdf] [arXiv]
[bibtex]
@InProceedings{Korkmaz_2025_WACV, author = {Korkmaz, Yilmaz and Patel, Vishal M.}, title = {MambaRecon: MRI Reconstruction with Structured State Space Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4142-4152} }
LoSA: Long-Short-Range Adapter for Scaling End-to-End Temporal Action Localization: Akshita Gupta,

Gaurav Mittal,

Ahmed Magooda,

Ye Yu,

Graham Taylor,

Mei Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gupta_2025_WACV, author = {Gupta, Akshita and Mittal, Gaurav and Magooda, Ahmed and Yu, Ye and Taylor, Graham and Chen, Mei}, title = {LoSA: Long-Short-Range Adapter for Scaling End-to-End Temporal Action Localization}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2092-2102} }
Investigating Imaging Annotation and Self-Supervision for the Classification of Continuously Developing Cells in Histological Whole Slide Images: Sebastian Thiele,

Jacqueline Kockwelp,

Joachim Wistuba,

Sabine Kliesch,

Jörg Gromoll,

Benjamin Risse; [pdf] [supp]
[bibtex]
@InProceedings{Thiele_2025_WACV, author = {Thiele, Sebastian and Kockwelp, Jacqueline and Wistuba, Joachim and Kliesch, Sabine and Gromoll, J\"org and Risse, Benjamin}, title = {Investigating Imaging Annotation and Self-Supervision for the Classification of Continuously Developing Cells in Histological Whole Slide Images}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4442-4451} }
Spatio-Temporal Context Prompting for Zero-Shot Action Detection: Wei-Jhe Huang,

Min-Hung Chen,

Shang-Hong Lai; [pdf] [arXiv]
[bibtex]
@InProceedings{Huang_2025_WACV, author = {Huang, Wei-Jhe and Chen, Min-Hung and Lai, Shang-Hong}, title = {Spatio-Temporal Context Prompting for Zero-Shot Action Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9065-9074} }
COSNet: A Novel Semantic Segmentation Network using Enhanced Boundaries in Cluttered Scenes: Muhammad Ali,

Mamoona Javaid,

Mubashir Noman,

Mustansar Fiaz,

Salman Khan; [pdf] [arXiv]
[bibtex]
@InProceedings{Ali_2025_WACV, author = {Ali, Muhammad and Javaid, Mamoona and Noman, Mubashir and Fiaz, Mustansar and Khan, Salman}, title = {COSNet: A Novel Semantic Segmentation Network using Enhanced Boundaries in Cluttered Scenes}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1363-1372} }
Learning Instance-Specific Parameters of Black-Box Models using Differentiable Surrogates: Arnisha Khondaker,

Nilanjan Ray; [pdf] [arXiv]
[bibtex]
@InProceedings{Khondaker_2025_WACV, author = {Khondaker, Arnisha and Ray, Nilanjan}, title = {Learning Instance-Specific Parameters of Black-Box Models using Differentiable Surrogates}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7429-7438} }
Swap Path Network for Robust Person Search Pre-Training: Lucas Jaffe,

Avideh Zakhor; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jaffe_2025_WACV, author = {Jaffe, Lucas and Zakhor, Avideh}, title = {Swap Path Network for Robust Person Search Pre-Training}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9273-9283} }
Dropout Connects Transformers and CNNs: Transfer General Knowledge for Knowledge Distillation: Bokyeung Lee,

Jonghwan Hong,

Hyunuk Shin,

Bonwha Ku,

Hanseok Ko; [pdf] [supp]
[bibtex]
@InProceedings{Lee_2025_WACV, author = {Lee, Bokyeung and Hong, Jonghwan and Shin, Hyunuk and Ku, Bonwha and Ko, Hanseok}, title = {Dropout Connects Transformers and CNNs: Transfer General Knowledge for Knowledge Distillation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8335-8344} }
Feature Design for Bridging SAM and CLIP toward Referring Image Segmentation: Koichiro Ito; [pdf] [supp]
[bibtex]
@InProceedings{Ito_2025_WACV, author = {Ito, Koichiro}, title = {Feature Design for Bridging SAM and CLIP toward Referring Image Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8357-8367} }
Heterogeneous Datasets for Unsupervised Image Anomaly Detection: Juan Lagos,

Haider Ali,

Adnan Faroque,

Esa Rahtu; [pdf]
[bibtex]
@InProceedings{Lagos_2025_WACV, author = {Lagos, Juan and Ali, Haider and Faroque, Adnan and Rahtu, Esa}, title = {Heterogeneous Datasets for Unsupervised Image Anomaly Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7266-7276} }
A Parametric Approach to Adversarial Augmentation for Cross-Domain Iris Presentation Attack Detection: Debasmita Pal,

Redwan Sony,

Arun Ross; [pdf] [arXiv]
[bibtex]
@InProceedings{Pal_2025_WACV, author = {Pal, Debasmita and Sony, Redwan and Ross, Arun}, title = {A Parametric Approach to Adversarial Augmentation for Cross-Domain Iris Presentation Attack Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5719-5729} }
OPTIMUS: Observing Persistent Transformations in Multi-Temporal Unlabeled Satellite-Data: Raymond Yu,

Paul Han,

Piper Wolters,

Favyen Bastani; [pdf] [supp]
[bibtex]
@InProceedings{Yu_2025_WACV, author = {Yu, Raymond and Han, Paul and Wolters, Piper and Bastani, Favyen}, title = {OPTIMUS: Observing Persistent Transformations in Multi-Temporal Unlabeled Satellite-Data}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5822-5830} }
Copy or Not? Reference-Based Face Image Restoration with Fine Details: Min Jin Chong,

Dejia Xu,

Yi Zhang,

Zhangyang Wang,

David Forsyth,

Gurunandan Krishnan,

Yicheng Wu,

Jian Wang; [pdf]
[bibtex]
@InProceedings{Chong_2025_WACV, author = {Chong, Min Jin and Xu, Dejia and Zhang, Yi and Wang, Zhangyang and Forsyth, David and Krishnan, Gurunandan and Wu, Yicheng and Wang, Jian}, title = {Copy or Not? Reference-Based Face Image Restoration with Fine Details}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9642-9651} }
PVT: An Implicit Surface Reconstruction Framework via Point Voxel Geometric-Aware Transformer: Chuanmao Fan,

Chenxi Zhao,

Ye Duan; [pdf] [supp]
[bibtex]
@InProceedings{Fan_2025_WACV, author = {Fan, Chuanmao and Zhao, Chenxi and Duan, Ye}, title = {PVT: An Implicit Surface Reconstruction Framework via Point Voxel Geometric-Aware Transformer}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3013-3023} }
SyncDiff: Diffusion-Based Talking Head Synthesis with Bottlenecked Temporal Visual Prior for Improved Synchronization: Xulin Fan,

Heting Gao,

Ziyi Chen,

Peng Chang,

Mei Han,

Mark Hasegawa-Johnson; [pdf]
[bibtex]
@InProceedings{Fan_2025_WACV, author = {Fan, Xulin and Gao, Heting and Chen, Ziyi and Chang, Peng and Han, Mei and Hasegawa-Johnson, Mark}, title = {SyncDiff: Diffusion-Based Talking Head Synthesis with Bottlenecked Temporal Visual Prior for Improved Synchronization}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4554-4563} }
AgroGPT: Efficient Agricultural Vision-Language Model with Expert Tuning: Muhammad Awais,

Ali Husain Salem Abdulla Alharthi,

Amandeep Kumar,

Hisham Cholakkal,

Rao Muhammad Anwer; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Awais_2025_WACV, author = {Awais, Muhammad and Alharthi, Ali Husain Salem Abdulla and Kumar, Amandeep and Cholakkal, Hisham and Anwer, Rao Muhammad}, title = {AgroGPT: Efficient Agricultural Vision-Language Model with Expert Tuning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5687-5696} }
Can Location Embeddings Enhance Super-Resolution of Satellite Imagery?: Daniel Panangian,

Ksenia Bittner; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Panangian_2025_WACV, author = {Panangian, Daniel and Bittner, Ksenia}, title = {Can Location Embeddings Enhance Super-Resolution of Satellite Imagery?}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6136-6145} }
TFM^2: Training-Free Mask Matching for Open-Vocabulary Semantic Segmentation: Yaoxin Zhuo,

Zachary Bessinger,

Lichen Wang,

Naji Khosravan,

Baoxin Li,

Sing Bing Kang; [pdf] [supp]
[bibtex]
@InProceedings{Zhuo_2025_WACV, author = {Zhuo, Yaoxin and Bessinger, Zachary and Wang, Lichen and Khosravan, Naji and Li, Baoxin and Kang, Sing Bing}, title = {TFM{\textasciicircum}2: Training-Free Mask Matching for Open-Vocabulary Semantic Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4693-4703} }
Visual Robustness Benchmark for Visual Question Answering (VQA): Farhan Ishmam,

Ishmam Tashdeed,

Talukder Asir Saadat,

Hamjajul Ashmafee,

Abu Raihan Mostofa Kamal,

Azam Hossain; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ishmam_2025_WACV, author = {Ishmam, Farhan and Tashdeed, Ishmam and Saadat, Talukder Asir and Ashmafee, Hamjajul and Kamal, Abu Raihan Mostofa and Hossain, Azam}, title = {Visual Robustness Benchmark for Visual Question Answering (VQA)}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6623-6633} }
NCAdapt: Dynamic Adaptation with Domain-Specific Neural Cellular Automata for Continual Hippocampus Segmentation: Amin Ranem,

John Orlando Kalkhof,

Anirban Mukhopadhyay; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ranem_2025_WACV, author = {Ranem, Amin and Kalkhof, John Orlando and Mukhopadhyay, Anirban}, title = {NCAdapt: Dynamic Adaptation with Domain-Specific Neural Cellular Automata for Continual Hippocampus Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3834-3843} }
Inverse Problems with Diffusion Models: A MAP Estimation Perspective: Sai Bharath Chandra Gutha,

Ricardo Vinuesa,

Hossein Azizpour; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gutha_2025_WACV, author = {Gutha, Sai Bharath Chandra and Vinuesa, Ricardo and Azizpour, Hossein}, title = {Inverse Problems with Diffusion Models: A MAP Estimation Perspective}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4153-4162} }
Temporally Grounding Instructional Diagrams in Unconstrained Videos: Jiahao Zhang,

Frederic Z. Zhang,

Cristian Rodriguez,

Yizhak Ben-Shabat,

Anoop Cherian,

Stephen Gould; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2025_WACV, author = {Zhang, Jiahao and Zhang, Frederic Z. and Rodriguez, Cristian and Ben-Shabat, Yizhak and Cherian, Anoop and Gould, Stephen}, title = {Temporally Grounding Instructional Diagrams in Unconstrained Videos}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8090-8100} }
A Data Perspective on Enhanced Identity Preservation for Diffusion Personalization: Xingzhe He,

Zhiwen Cao,

Nick Kolkin,

Lantao Yu,

Kun Wan,

Helge Rhodin,

Ratheesh Kalarot; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{He_2025_WACV, author = {He, Xingzhe and Cao, Zhiwen and Kolkin, Nick and Yu, Lantao and Wan, Kun and Rhodin, Helge and Kalarot, Ratheesh}, title = {A Data Perspective on Enhanced Identity Preservation for Diffusion Personalization}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3782-3791} }
Multimodal Interpretable Depression Analysis using Visual Physiological Audio and Textual Data: Puneet Kumar,

Shreshtha Misra,

Zhuhong Shao,

Bin Zhu,

Balasubramanian Raman,

Xiaobai Li; [pdf]
[bibtex]
@InProceedings{Kumar_2025_WACV, author = {Kumar, Puneet and Misra, Shreshtha and Shao, Zhuhong and Zhu, Bin and Raman, Balasubramanian and Li, Xiaobai}, title = {Multimodal Interpretable Depression Analysis using Visual Physiological Audio and Textual Data}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5305-5315} }
Seeing Eye to AI: Comparing Human Gaze and Model Attention in Video Memorability: Prajneya Kumar,

Eshika Khandelwal,

Makarand Tapaswi,

Vishnu Sreekumar; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kumar_2025_WACV, author = {Kumar, Prajneya and Khandelwal, Eshika and Tapaswi, Makarand and Sreekumar, Vishnu}, title = {Seeing Eye to AI: Comparing Human Gaze and Model Attention in Video Memorability}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2082-2091} }
Conceptual Learning via Embedding Approximations for Reinforcing Interpretability and Transparency: Maor Dikter,

Tsachi Blau,

Chaim Baskin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dikter_2025_WACV, author = {Dikter, Maor and Blau, Tsachi and Baskin, Chaim}, title = {Conceptual Learning via Embedding Approximations for Reinforcing Interpretability and Transparency}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3185-3195} }
Detective Networks: Enhancing Disaster Recognition in Images Through Attention Shifting using Optimal Masking: Narongthat Thanyawet,

Photchara Ratsamee,

Yuki Uranishi,

Haruo Takemura; [pdf] [supp]
[bibtex]
@InProceedings{Thanyawet_2025_WACV, author = {Thanyawet, Narongthat and Ratsamee, Photchara and Uranishi, Yuki and Takemura, Haruo}, title = {Detective Networks: Enhancing Disaster Recognition in Images Through Attention Shifting using Optimal Masking}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8723-8732} }
CRAAC: Consistency Regularised Active Learning with Automatic Corrections for Real-Life Road Image Annotations: Percy Lam,

Sooyong Park,

Weiwei Chen,

Lavindra de Silva,

Ioannis Brilakis; [pdf] [supp]
[bibtex]
@InProceedings{Lam_2025_WACV, author = {Lam, Percy and Park, Sooyong and Chen, Weiwei and de Silva, Lavindra and Brilakis, Ioannis}, title = {CRAAC: Consistency Regularised Active Learning with Automatic Corrections for Real-Life Road Image Annotations}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4778-4787} }
Navigating Heterogeneity and Privacy in One-Shot Federated Learning with Diffusion Models: Matias Mendieta,

Guangyu Sun,

Chen Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mendieta_2025_WACV, author = {Mendieta, Matias and Sun, Guangyu and Chen, Chen}, title = {Navigating Heterogeneity and Privacy in One-Shot Federated Learning with Diffusion Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2601-2610} }
Separating Direct and Global Components from Novel Viewpoints: Kengo Matsufuji,

Lin Shi,

Ryo Kawahara,

Takahiro Okabe; [pdf] [supp]
[bibtex]
@InProceedings{Matsufuji_2025_WACV, author = {Matsufuji, Kengo and Shi, Lin and Kawahara, Ryo and Okabe, Takahiro}, title = {Separating Direct and Global Components from Novel Viewpoints}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1829-1838} }
ReMix: Training Generalized Person Re-Identification on a Mixture of Data: Timur Mamedov,

Anton Konushin,

Vadim Konushin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mamedov_2025_WACV, author = {Mamedov, Timur and Konushin, Anton and Konushin, Vadim}, title = {ReMix: Training Generalized Person Re-Identification on a Mixture of Data}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8175-8185} }
Phaseformer: Phase-Based Attention Mechanism for Underwater Image Restoration and Beyond: Raqib Khan,

Anshul Negi,

Ashutosh Kulkarni,

Shruti S. Phutke,

Santosh Kumar Vipparthi,

Subrahmanyam Murala; [pdf] [arXiv]
[bibtex]
@InProceedings{Khan_2025_WACV, author = {Khan, Raqib and Negi, Anshul and Kulkarni, Ashutosh and Phutke, Shruti S. and Vipparthi, Santosh Kumar and Murala, Subrahmanyam}, title = {Phaseformer: Phase-Based Attention Mechanism for Underwater Image Restoration and Beyond}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9600-9611} }
CamoFA: A Learnable Fourier-Based Augmentation for Camouflage Segmentation: Minh-Quan Le,

Minh-Triet Tran,

Trung-Nghia Le,

Tam V. Nguyen,

Thanh-Toan Do; [pdf] [arXiv]
[bibtex]
@InProceedings{Le_2025_WACV, author = {Le, Minh-Quan and Tran, Minh-Triet and Le, Trung-Nghia and Nguyen, Tam V. and Do, Thanh-Toan}, title = {CamoFA: A Learnable Fourier-Based Augmentation for Camouflage Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3427-3436} }
Federated Voxel Scene Graph for Intracranial Hemorrhage: Antoine P. Sanner,

Jonathan Stieber,

Nils F. Grauhan,

Suam Kim,

Marc A. Brockmann,

Ahmed E. Othman,

Anirban Mukhopadhyay; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sanner_2025_WACV, author = {Sanner, Antoine P. and Stieber, Jonathan and Grauhan, Nils F. and Kim, Suam and Brockmann, Marc A. and Othman, Ahmed E. and Mukhopadhyay, Anirban}, title = {Federated Voxel Scene Graph for Intracranial Hemorrhage}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4410-4419} }
Hyperdimensional Representation for Adaptive Information Association and Memorization: Zhuowen Zou,

Prathyush Poduval,

Narayan Srinivasa,

Mohsen Imani; [pdf] [supp]
[bibtex]
@InProceedings{Zou_2025_WACV, author = {Zou, Zhuowen and Poduval, Prathyush and Srinivasa, Narayan and Imani, Mohsen}, title = {Hyperdimensional Representation for Adaptive Information Association and Memorization}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5666-5675} }
HandCraft: Anatomically Correct Restoration of Malformed Hands in Diffusion Generated Images: Zhenyue Qin,

Yiqun Zhang,

Yang Liu,

Dylan Campbell; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Qin_2025_WACV, author = {Qin, Zhenyue and Zhang, Yiqun and Liu, Yang and Campbell, Dylan}, title = {HandCraft: Anatomically Correct Restoration of Malformed Hands in Diffusion Generated Images}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3925-3933} }
SCOT: Self-Supervised Contrastive Pretraining for Zero-Shot Compositional Retrieval: Bhavin Jawade,

João V. B. Soares,

Kapil Thadani,

Deen Dayal Mohan,

Amir Erfan Eshratifar,

Benjamin Culpepper,

Paloma de Juan,

Srirangaraj Setlur,

Venu Govindaraju; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jawade_2025_WACV, author = {Jawade, Bhavin and Soares, Jo\~ao V. B. and Thadani, Kapil and Mohan, Deen Dayal and Eshratifar, Amir Erfan and Culpepper, Benjamin and de Juan, Paloma and Setlur, Srirangaraj and Govindaraju, Venu}, title = {SCOT: Self-Supervised Contrastive Pretraining for Zero-Shot Compositional Retrieval}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5509-5519} }
ROADS: Robust Prompt-Driven Multi-Class Anomaly Detection under Domain Shift: Hossein Kashiani,

Niloufar Alipour Talemi,

Fatemeh Afghah; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kashiani_2025_WACV, author = {Kashiani, Hossein and Talemi, Niloufar Alipour and Afghah, Fatemeh}, title = {ROADS: Robust Prompt-Driven Multi-Class Anomaly Detection under Domain Shift}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7897-7906} }
Memory-Efficient Continual Learning with Neural Collapse Contrastive: Trung-Anh Dang,

Vincent Nguyen,

Ngoc-Son Vu,

Christel Vrain; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dang_2025_WACV, author = {Dang, Trung-Anh and Nguyen, Vincent and Vu, Ngoc-Son and Vrain, Christel}, title = {Memory-Efficient Continual Learning with Neural Collapse Contrastive}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7939-7948} }
Towards Real-Time Open-Vocabulary Video Instance Segmentation: Bin Yan,

Martin Sundermeyer,

David Joseph Tan,

Huchuan Lu,

Federico Tombari; [pdf] [arXiv]
[bibtex]
@InProceedings{Yan_2025_WACV, author = {Yan, Bin and Sundermeyer, Martin and Tan, David Joseph and Lu, Huchuan and Tombari, Federico}, title = {Towards Real-Time Open-Vocabulary Video Instance Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1861-1871} }
Dataset Augmentation by Mixing Visual Concepts: Md Abdullah Al Rahat Kutubi,

Hemanth Venkateswara; [pdf] [supp]
[bibtex]
@InProceedings{Al_Rahat_Kutubi_2025_WACV, author = {Al Rahat Kutubi, Md Abdullah and Venkateswara, Hemanth}, title = {Dataset Augmentation by Mixing Visual Concepts}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3866-3875} }
DMPT: Decoupled Modality-Aware Prompt Tuning for Multi-Modal Object Re-Identification: Minghui Lin,

Shu Wang,

Xiang Wang,

Jianhua Tang,

Longbin Fu,

Zhengrong Zuo,

Nong Sang; [pdf]
[bibtex]
@InProceedings{Lin_2025_WACV, author = {Lin, Minghui and Wang, Shu and Wang, Xiang and Tang, Jianhua and Fu, Longbin and Zuo, Zhengrong and Sang, Nong}, title = {DMPT: Decoupled Modality-Aware Prompt Tuning for Multi-Modal Object Re-Identification}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2103-2112} }
Image-Caption Encoding for Improving Zero-Shot Generalization: Eric Yu,

Christopher Liao,

Sathvik Ravi,

Theodoros Tsiligkaridis,

Brian Kulis; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2025_WACV, author = {Yu, Eric and Liao, Christopher and Ravi, Sathvik and Tsiligkaridis, Theodoros and Kulis, Brian}, title = {Image-Caption Encoding for Improving Zero-Shot Generalization}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6977-6986} }
FT2TF: First-Person Statement Text-To-Talking Face Generation: Xingjian Diao,

Ming Cheng,

Wayner Barrios,

SouYoung Jin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Diao_2025_WACV, author = {Diao, Xingjian and Cheng, Ming and Barrios, Wayner and Jin, SouYoung}, title = {FT2TF: First-Person Statement Text-To-Talking Face Generation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4821-4830} }
ARD-VAE: A Statistical Formulation to Find the Relevant Latent Dimensions of Variational Autoencoders: Surojit Saha,

Sarang Joshi,

Ross Whitaker; [pdf] [supp]
[bibtex]
@InProceedings{Saha_2025_WACV, author = {Saha, Surojit and Joshi, Sarang and Whitaker, Ross}, title = {ARD-VAE: A Statistical Formulation to Find the Relevant Latent Dimensions of Variational Autoencoders}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {889-898} }
MatSpectNet: Material Segmentation Network with Domain-Aware and Physically-Constrained Hyperspectral Reconstruction: Yuwen Heng,

Yihong Wu,

Srinandan Dasmahapatra,

Hansung Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Heng_2025_WACV, author = {Heng, Yuwen and Wu, Yihong and Dasmahapatra, Srinandan and Kim, Hansung}, title = {MatSpectNet: Material Segmentation Network with Domain-Aware and Physically-Constrained Hyperspectral Reconstruction}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8079-8089} }
ALSTER: A Local Spatio-Temporal Expert for Online 3D Semantic Reconstruction: Silvan Weder,

Francis Engelmann,

Johannes L. Schönberger,

Akihito Seki,

Marc Pollefeys,

Martin R. Oswald; [pdf]
[bibtex]
@InProceedings{Weder_2025_WACV, author = {Weder, Silvan and Engelmann, Francis and Sch\"onberger, Johannes L. and Seki, Akihito and Pollefeys, Marc and Oswald, Martin R.}, title = {ALSTER: A Local Spatio-Temporal Expert for Online 3D Semantic Reconstruction}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3519-3528} }
Joint Co-Speech Gesture and Expressive Talking Face Generation using Diffusion with Adapters: Steven Hogue,

Chenxu Zhang,

Yapeng Tian,

Xiaohu Guo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hogue_2025_WACV, author = {Hogue, Steven and Zhang, Chenxu and Tian, Yapeng and Guo, Xiaohu}, title = {Joint Co-Speech Gesture and Expressive Talking Face Generation using Diffusion with Adapters}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4163-4172} }
UnDIVE: Generalized Underwater Video Enhancement using Generative Priors: Suhas Srinath,

Aditya Chandrasekar,

Hemang Jamadagni,

Rajiv Soundararajan,

Prathosh A P; [pdf] [arXiv]
[bibtex]
@InProceedings{Srinath_2025_WACV, author = {Srinath, Suhas and Chandrasekar, Aditya and Jamadagni, Hemang and Soundararajan, Rajiv and A P, Prathosh}, title = {UnDIVE: Generalized Underwater Video Enhancement using Generative Priors}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8983-8994} }
Automated Patient Positioning with Learned 3D Hand Gestures: Zhongpai Gao,

Abhishek Sharma,

Meng Zheng,

Benjamin Planche,

Terrence Chen,

Ziyan Wu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gao_2025_WACV, author = {Gao, Zhongpai and Sharma, Abhishek and Zheng, Meng and Planche, Benjamin and Chen, Terrence and Wu, Ziyan}, title = {Automated Patient Positioning with Learned 3D Hand Gestures}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3772-3781} }
Class-Conditioned Transformation for Enhanced Robust Image Classification: Tsachi Blau,

Roy Ganz,

Chaim Baskin,

Michael Elad,

Alex Bronstein; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Blau_2025_WACV, author = {Blau, Tsachi and Ganz, Roy and Baskin, Chaim and Elad, Michael and Bronstein, Alex}, title = {Class-Conditioned Transformation for Enhanced Robust Image Classification}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6538-6547} }
ColFigPhotoAttnNet: Reliable Finger Photo Presentation Attack Detection Leveraging Window-Attention on Color Spaces: Anudeep Vurity,

Emanuela Marasco,

Raghavendra Ramachandra,

Jongwoo Park; [pdf] [supp]
[bibtex]
@InProceedings{Vurity_2025_WACV, author = {Vurity, Anudeep and Marasco, Emanuela and Ramachandra, Raghavendra and Park, Jongwoo}, title = {ColFigPhotoAttnNet: Reliable Finger Photo Presentation Attack Detection Leveraging Window-Attention on Color Spaces}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5316-5325} }
Cap2Aug: Caption Guided Image Data Augmentation: Aniket Roy,

Anshul Shah,

Ketul Shah,

Anirban Roy,

Rama Chellappa; [pdf]
[bibtex]
@InProceedings{Roy_2025_WACV, author = {Roy, Aniket and Shah, Anshul and Shah, Ketul and Roy, Anirban and Chellappa, Rama}, title = {Cap2Aug: Caption Guided Image Data Augmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9107-9117} }
Meta-Learning for Color-to-Infrared Cross-Modal Style Transfer: Evelyn A. Stump,

Francesco Luzi,

Leslie M. Collins,

Jordan M. Malof; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Stump_2025_WACV, author = {Stump, Evelyn A. and Luzi, Francesco and Collins, Leslie M. and Malof, Jordan M.}, title = {Meta-Learning for Color-to-Infrared Cross-Modal Style Transfer}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5460-5469} }
Improving Pelvic MR-CT Image Alignment with Self-Supervised Reference-Augmented Pseudo-CT Generation Framework: Daniel Kim,

Mohammed A. Al-masni,

Jaehun Lee,

Dong-Hyun Kim,

Kanghyun Ryu; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2025_WACV, author = {Kim, Daniel and Al-masni, Mohammed A. and Lee, Jaehun and Kim, Dong-Hyun and Ryu, Kanghyun}, title = {Improving Pelvic MR-CT Image Alignment with Self-Supervised Reference-Augmented Pseudo-CT Generation Framework}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {347-356} }
ActionDiffusion: An Action-Aware Diffusion Model for Procedure Planning in Instructional Videos: Lei Shi,

Paul-Christian Bürkner,

Andreas Bulling; [pdf]
[bibtex]
@InProceedings{Shi_2025_WACV, author = {Shi, Lei and B\"urkner, Paul-Christian and Bulling, Andreas}, title = {ActionDiffusion: An Action-Aware Diffusion Model for Procedure Planning in Instructional Videos}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8805-8814} }
SGD: Street View Synthesis with Gaussian Splatting and Diffusion Prior: Zhongrui Yu,

Haoran Wang,

Jinze Yang,

Hanzhang Wang,

Jiale Cao,

Zhong Ji,

Mingming Sun; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2025_WACV, author = {Yu, Zhongrui and Wang, Haoran and Yang, Jinze and Wang, Hanzhang and Cao, Jiale and Ji, Zhong and Sun, Mingming}, title = {SGD: Street View Synthesis with Gaussian Splatting and Diffusion Prior}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3812-3822} }
MSI-NeRF: Linking Omni-Depth with View Synthesis through Multi-Sphere Image Aided Generalizable Neural Radiance Field: Dongyu Yan,

Guanyu Huang,

Fengyu Quan,

Haoyao Chen; [pdf] [supp]
[bibtex]
@InProceedings{Yan_2025_WACV, author = {Yan, Dongyu and Huang, Guanyu and Quan, Fengyu and Chen, Haoyao}, title = {MSI-NeRF: Linking Omni-Depth with View Synthesis through Multi-Sphere Image Aided Generalizable Neural Radiance Field}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2517-2526} }
ARTeFACT: Benchmarking Segmentation Models on Diverse Analogue Media Damage: Daniela Ivanova,

Marco Aversa,

Paul Henderson,

John Williamson; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ivanova_2025_WACV, author = {Ivanova, Daniela and Aversa, Marco and Henderson, Paul and Williamson, John}, title = {ARTeFACT: Benchmarking Segmentation Models on Diverse Analogue Media Damage}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7439-7449} }
Analyzing and Improving the Skin Tone Consistency and Bias in Implicit 3D Relightable Face Generators: Libing Zeng,

Nima Khademi Kalantari; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zeng_2025_WACV, author = {Zeng, Libing and Kalantari, Nima Khademi}, title = {Analyzing and Improving the Skin Tone Consistency and Bias in Implicit 3D Relightable Face Generators}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4026-4035} }
TLDR: Text Based Last-Layer Retraining for Debiasing Image Classifiers: Juhyeon Park,

Seokhyeon Jeong,

Taesup Moon; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Park_2025_WACV, author = {Park, Juhyeon and Jeong, Seokhyeon and Moon, Taesup}, title = {TLDR: Text Based Last-Layer Retraining for Debiasing Image Classifiers}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2538-2547} }
Fair Domain Generalization with Heterogeneous Sensitive Attributes Across Domains: Ragja Palakkadavath,

Hung Le,

Thanh Nguyen-Tang,

Sunil Gupta,

Svetha Venkatesh; [pdf] [supp]
[bibtex]
@InProceedings{Palakkadavath_2025_WACV, author = {Palakkadavath, Ragja and Le, Hung and Nguyen-Tang, Thanh and Gupta, Sunil and Venkatesh, Svetha}, title = {Fair Domain Generalization with Heterogeneous Sensitive Attributes Across Domains}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7389-7398} }
Infant Action Generative Modeling: Xiaofei Huang,

Elaheh Hatamimajoumerd,

Amal Mathew,

Sarah Ostadabbas; [pdf] [supp]
[bibtex]
@InProceedings{Huang_2025_WACV, author = {Huang, Xiaofei and Hatamimajoumerd, Elaheh and Mathew, Amal and Ostadabbas, Sarah}, title = {Infant Action Generative Modeling}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {253-265} }
CAMS: Convolution and Attention-Free Mamba-Based Cardiac Image Segmentation: Abbas Khan,

Muhammad Asad,

Martin Benning,

Caroline Roney,

Gregory Slabaugh; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Khan_2025_WACV, author = {Khan, Abbas and Asad, Muhammad and Benning, Martin and Roney, Caroline and Slabaugh, Gregory}, title = {CAMS: Convolution and Attention-Free Mamba-Based Cardiac Image Segmentation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1893-1903} }
VipDiff: Towards Coherent and Diverse Video Inpainting via Training-Free Denoising Diffusion Models: Chaohao Xie,

Kai Han,

Kwan-Yee K. Wong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xie_2025_WACV, author = {Xie, Chaohao and Han, Kai and Wong, Kwan-Yee K.}, title = {VipDiff: Towards Coherent and Diverse Video Inpainting via Training-Free Denoising Diffusion Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2411-2420} }
ColorizeDiffusion: Improving Reference-Based Sketch Colorization with Latent Diffusion Model: Dingkun Yan,

Liang Yuan,

Erwin Wu,

Yuma Nishioka,

Issei Fujishiro,

Suguru Saito; [pdf] [supp]
[bibtex]
@InProceedings{Yan_2025_WACV, author = {Yan, Dingkun and Yuan, Liang and Wu, Erwin and Nishioka, Yuma and Fujishiro, Issei and Saito, Suguru}, title = {ColorizeDiffusion: Improving Reference-Based Sketch Colorization with Latent Diffusion Model}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5092-5102} }
My3DGen: A Scalable Personalized 3D Generative Model: Luchao Qi,

Jiaye Wu,

Annie N. Wang,

Shengze Wang,

Roni Sengupta; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Qi_2025_WACV, author = {Qi, Luchao and Wu, Jiaye and Wang, Annie N. and Wang, Shengze and Sengupta, Roni}, title = {My3DGen: A Scalable Personalized 3D Generative Model}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {961-972} }
Discriminative Score Suppression for Weakly Supervised Video Anomaly Detection: Chen Xu,

Chunguo Li,

Hongjie Xing; [pdf]
[bibtex]
@InProceedings{Xu_2025_WACV, author = {Xu, Chen and Li, Chunguo and Xing, Hongjie}, title = {Discriminative Score Suppression for Weakly Supervised Video Anomaly Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9569-9578} }
Semiotic-Based Construction of a Large Emotional Image Dataset with Neutral Samples: Marco Blanchini,

Giovanna Dimitri,

Lydia Abady,

Benedetta Tondi,

Tarcisio Lancioni,

Mauro Barni; [pdf] [supp]
[bibtex]
@InProceedings{Blanchini_2025_WACV, author = {Blanchini, Marco and Dimitri, Giovanna and Abady, Lydia and Tondi, Benedetta and Lancioni, Tarcisio and Barni, Mauro}, title = {Semiotic-Based Construction of a Large Emotional Image Dataset with Neutral Samples}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7541-7550} }
SADDLe: Sharpness-Aware Decentralized Deep Learning with Heterogeneous Data: Sakshi Choudhary,

Sai Aparna Aketi,

Kaushik Roy; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Choudhary_2025_WACV, author = {Choudhary, Sakshi and Aketi, Sai Aparna and Roy, Kaushik}, title = {SADDLe: Sharpness-Aware Decentralized Deep Learning with Heterogeneous Data}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7720-7730} }
DiffPAD: Denoising Diffusion-Based Adversarial Patch Decontamination: Jia Fu,

Xiao Zhang,

Sepideh Pashami,

Fatemeh Rahimian,

Anders Holst; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fu_2025_WACV, author = {Fu, Jia and Zhang, Xiao and Pashami, Sepideh and Rahimian, Fatemeh and Holst, Anders}, title = {DiffPAD: Denoising Diffusion-Based Adversarial Patch Decontamination}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6602-6611} }
Data-Efficient Alignment in Medical Imaging via Reconfigurable Generative Networks: Divya Saxena,

Jiannong Cao,

Jiahao Xu,

Tarun Kulshrestha; [pdf] [supp]
[bibtex]
@InProceedings{Saxena_2025_WACV, author = {Saxena, Divya and Cao, Jiannong and Xu, Jiahao and Kulshrestha, Tarun}, title = {Data-Efficient Alignment in Medical Imaging via Reconfigurable Generative Networks}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7399-7408} }
A Rapid Test for Accuracy and Bias of Face Recognition Technology: Manuel Knott,

Ignacio Serna,

Ethan Mann,

Pietro Perona; [pdf] [supp]
[bibtex]
@InProceedings{Knott_2025_WACV, author = {Knott, Manuel and Serna, Ignacio and Mann, Ethan and Perona, Pietro}, title = {A Rapid Test for Accuracy and Bias of Face Recognition Technology}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7731-7740} }
FineControlNet: Fine-Level Text Control for Image Generation with Spatially Aligned Text Control Injection: Hongsuk Choi,

Isaac Kasahara,

Selim Engin,

Moritz A. Graule,

Nikhil Chavan-Dafle,

Volkan Isler; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Choi_2025_WACV, author = {Choi, Hongsuk and Kasahara, Isaac and Engin, Selim and Graule, Moritz A. and Chavan-Dafle, Nikhil and Isler, Volkan}, title = {FineControlNet: Fine-Level Text Control for Image Generation with Spatially Aligned Text Control Injection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3975-3984} }
F2FLDM: Latent Diffusion Models with Histopathology Pre-Trained Embeddings for Unpaired Frozen Section to FFPE Translation: Man M. Ho,

Shikha Dubey,

Yosep Chong,

Beatrice Knudsen,

Tolga Tasdizen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ho_2025_WACV, author = {Ho, Man M. and Dubey, Shikha and Chong, Yosep and Knudsen, Beatrice and Tasdizen, Tolga}, title = {F2FLDM: Latent Diffusion Models with Histopathology Pre-Trained Embeddings for Unpaired Frozen Section to FFPE Translation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4382-4391} }
Wavelength- and Depth-Aware Deep Image Prior for Blind Hyperspectral Imagery Deblurring with Coarse Depth Guidance: Jiahuan Li,

Xiaoyu Dong,

Wei He,

Naoto Yokoya; [pdf] [supp]
[bibtex]
@InProceedings{Li_2025_WACV, author = {Li, Jiahuan and Dong, Xiaoyu and He, Wei and Yokoya, Naoto}, title = {Wavelength- and Depth-Aware Deep Image Prior for Blind Hyperspectral Imagery Deblurring with Coarse Depth Guidance}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3162-3171} }
Disentangling Subject-Irrelevant Elements in Personalized Text-to-Image Diffusion via Filtered Self-Distillation: Seunghwan Choi,

Jooyeol Yun,

Jeonghoon Park,

Jaegul Choo; [pdf]
[bibtex]
@InProceedings{Choi_2025_WACV, author = {Choi, Seunghwan and Yun, Jooyeol and Park, Jeonghoon and Choo, Jaegul}, title = {Disentangling Subject-Irrelevant Elements in Personalized Text-to-Image Diffusion via Filtered Self-Distillation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9055-9064} }
Domain-Guided Weight Modulation for Semi-Supervised Domain Generalization: Chamuditha Jayanga Galappaththige,

Zachary Izzo,

Xilin He,

Honglu Zhou,

Muhammad Haris Khan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Galappaththige_2025_WACV, author = {Galappaththige, Chamuditha Jayanga and Izzo, Zachary and He, Xilin and Zhou, Honglu and Khan, Muhammad Haris}, title = {Domain-Guided Weight Modulation for Semi-Supervised Domain Generalization}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6495-6505} }
ContextIQ: A Multimodal Expert-Based Video Retrieval System for Contextual Advertising: Ashutosh Chaubey,

Anoubhav Agarwaal,

Sartaki Sinha Roy,

Aayush Agrawal,

Susmita Ghose; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chaubey_2025_WACV, author = {Chaubey, Ashutosh and Agarwaal, Anoubhav and Roy, Sartaki Sinha and Agrawal, Aayush and Ghose, Susmita}, title = {ContextIQ: A Multimodal Expert-Based Video Retrieval System for Contextual Advertising}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6042-6052} }
CLASS: Conditional Latent Architecture for Search and Synthesis of Design Layouts: Dipu Manandhar,

Paul Guerrero,

Zhaowen Wang,

John Collomosse; [pdf] [supp]
[bibtex]
@InProceedings{Manandhar_2025_WACV, author = {Manandhar, Dipu and Guerrero, Paul and Wang, Zhaowen and Collomosse, John}, title = {CLASS: Conditional Latent Architecture for Search and Synthesis of Design Layouts}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5520-5529} }
High-Pass Kernel Prediction for Efficient Video Deblurring: Bo Ji,

Angela Yao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ji_2025_WACV, author = {Ji, Bo and Yao, Angela}, title = {High-Pass Kernel Prediction for Efficient Video Deblurring}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2442-2452} }
AnonyNoise: Anonymizing Event Data with Smart Noise to Outsmart Re-Identification and Preserve Privacy: Katharina Bendig,

René Schuster,

Nicole Thiemer,

Karen Joisten,

Didier Stricker; [pdf] [arXiv]
[bibtex]
@InProceedings{Bendig_2025_WACV, author = {Bendig, Katharina and Schuster, Ren\'e and Thiemer, Nicole and Joisten, Karen and Stricker, Didier}, title = {AnonyNoise: Anonymizing Event Data with Smart Noise to Outsmart Re-Identification and Preserve Privacy}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3159-3161} }
Diffusion-Based Conditional Image Editing through Optimized Inference with Guidance: Hyunsoo Lee,

Minsoo Kang,

Bohyung Han; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2025_WACV, author = {Lee, Hyunsoo and Kang, Minsoo and Han, Bohyung}, title = {Diffusion-Based Conditional Image Editing through Optimized Inference with Guidance}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4472-4480} }
Frequency-Domain Refinement of Vision Transformers for Robust Medical Image Segmentation under Degradation: Sanaz Karimijafarbigloo,

Sina Ghorbani Kolahi,

Reza Azad,

Ulas Bagci,

Dorit Merhof; [pdf]
[bibtex]
@InProceedings{Karimijafarbigloo_2025_WACV, author = {Karimijafarbigloo, Sanaz and Kolahi, Sina Ghorbani and Azad, Reza and Bagci, Ulas and Merhof, Dorit}, title = {Frequency-Domain Refinement of Vision Transformers for Robust Medical Image Segmentation under Degradation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9158-9167} }
Leveraging CLIP Encoder for Multimodal Emotion Recognition: Yehun Song,

Sunyoung Cho; [pdf] [supp]
[bibtex]
@InProceedings{Song_2025_WACV, author = {Song, Yehun and Cho, Sunyoung}, title = {Leveraging CLIP Encoder for Multimodal Emotion Recognition}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6115-6124} }
MAGMA: Manifold Regularization for MAEs: Alin-Eugen Dondera,

Anuj R Singh,

Hadi Jamali-Rad; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dondera_2025_WACV, author = {Dondera, Alin-Eugen and Singh, Anuj R and Jamali-Rad, Hadi}, title = {MAGMA: Manifold Regularization for MAEs}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6890-6899} }
DeepMIM: Deep Supervision for Masked Image Modeling: Sucheng Ren,

Fangyun Wei,

Samuel Albanie,

Zheng Zhang,

Han Hu; [pdf] [arXiv]
[bibtex]
@InProceedings{Ren_2025_WACV, author = {Ren, Sucheng and Wei, Fangyun and Albanie, Samuel and Zhang, Zheng and Hu, Han}, title = {DeepMIM: Deep Supervision for Masked Image Modeling}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {879-888} }
Assessing the Quality of 3D Reconstruction in the Absence of Ground Truth: Application to a Multimodal Archaeological Dataset: Benjamin Coupry,

Baptiste Brument,

Antoine Laurent,

Jean Mélou,

Yvain Quéau,

Jean-Denis Durou; [pdf] [supp]
[bibtex]
@InProceedings{Coupry_2025_WACV, author = {Coupry, Benjamin and Brument, Baptiste and Laurent, Antoine and M\'elou, Jean and Qu\'eau, Yvain and Durou, Jean-Denis}, title = {Assessing the Quality of 3D Reconstruction in the Absence of Ground Truth: Application to a Multimodal Archaeological Dataset}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3457-3466} }
LQ-Adapter: ViT-Adapter with Learnable Queries for Gallbladder Cancer Detection from Ultrasound Images: Chetan Madan,

Mayuna Gupta,

Soumen Basu,

Pankaj Gupta,

Chetan Arora; [pdf]
[bibtex]
@InProceedings{Madan_2025_WACV, author = {Madan, Chetan and Gupta, Mayuna and Basu, Soumen and Gupta, Pankaj and Arora, Chetan}, title = {LQ-Adapter: ViT-Adapter with Learnable Queries for Gallbladder Cancer Detection from Ultrasound Images}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {557-567} }
CE-VAE: Capsule Enhanced Variational AutoEncoderfor Underwater Image Enhancement: Rita Pucci,

Niki Martinel; [pdf]
[bibtex]
@InProceedings{Pucci_2025_WACV, author = {Pucci, Rita and Martinel, Niki}, title = {CE-VAE: Capsule Enhanced Variational AutoEncoderfor Underwater Image Enhancement}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2113-2123} }
Information Theoretic Pruning of Coupled Channels in Deep Neural Networks: Peyman Rostami,

Nilotpal Sinha,

Nidhaleddine Chenni,

Anis Kacem,

Abd El Rahman Shabayek,

Carl Shneider,

Djamila Aouada; [pdf] [supp]
[bibtex]
@InProceedings{Rostami_2025_WACV, author = {Rostami, Peyman and Sinha, Nilotpal and Chenni, Nidhaleddine and Kacem, Anis and El Rahman Shabayek, Abd and Shneider, Carl and Aouada, Djamila}, title = {Information Theoretic Pruning of Coupled Channels in Deep Neural Networks}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7765-7775} }
Deep Geometric Moments Promote Shape Consistency in Text-to-3D Generation: Utkarsh Nath,

Rajeev Goel,

Eun Som Jeon,

Changhoon Kim,

Kyle Min,

Yezhou Yang,

Yingzhen Yang,

Pavan Turaga; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nath_2025_WACV, author = {Nath, Utkarsh and Goel, Rajeev and Jeon, Eun Som and Kim, Changhoon and Min, Kyle and Yang, Yezhou and Yang, Yingzhen and Turaga, Pavan}, title = {Deep Geometric Moments Promote Shape Consistency in Text-to-3D Generation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4331-4341} }
Dropout the High-Rate Downsampling: A Novel Design Paradigm for UHD Image Restoration: Chen Wu,

Ling Wang,

Long Peng,

Dianjie Lu,

Zhuoran Zheng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2025_WACV, author = {Wu, Chen and Wang, Ling and Peng, Long and Lu, Dianjie and Zheng, Zhuoran}, title = {Dropout the High-Rate Downsampling: A Novel Design Paradigm for UHD Image Restoration}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2390-2399} }
Multimodal Fusion Learning with Dual Attention for Medical Imaging: Joy Dhar,

Nayyar Zaidi,

Maryam Haghighat,

Sudipta Roy,

Puneet Goyal,

Azadeh Alavi,

Vikas Kumar; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dhar_2025_WACV, author = {Dhar, Joy and Zaidi, Nayyar and Haghighat, Maryam and Roy, Sudipta and Goyal, Puneet and Alavi, Azadeh and Kumar, Vikas}, title = {Multimodal Fusion Learning with Dual Attention for Medical Imaging}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4362-4371} }
Sign Language Recognition: A Large-Scale Multi-View Dataset and Comprehensive Evaluation: Nguyen Son Dinh,

Tuan Dung Nguyen,

Duc Tri Tran,

Nguyen Dang Huy Pham,

Thuan Hieu Tran,

Ngoc Anh Tong,

Quang Huy Hoang,

Phi Le Nguyen; [pdf] [supp]
[bibtex]
@InProceedings{Dinh_2025_WACV, author = {Dinh, Nguyen Son and Nguyen, Tuan Dung and Tran, Duc Tri and Pham, Nguyen Dang Huy and Tran, Thuan Hieu and Tong, Ngoc Anh and Hoang, Quang Huy and Le Nguyen, Phi}, title = {Sign Language Recognition: A Large-Scale Multi-View Dataset and Comprehensive Evaluation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7876-7886} }
Enhancing Skin Disease Diagnosis: Interpretable Visual Concept Discovery with SAM: Xin Hu,

Janet Wang,

Jihun Hamm,

Rie R Yotsu,

Zhengming Ding; [pdf] [arXiv]
[bibtex]
@InProceedings{Hu_2025_WACV, author = {Hu, Xin and Wang, Janet and Hamm, Jihun and Yotsu, Rie R and Ding, Zhengming}, title = {Enhancing Skin Disease Diagnosis: Interpretable Visual Concept Discovery with SAM}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {172-181} }
uLayout: Unified Room Layout Estimation for Perspective and Panoramic Images: Jonathan Lee,

Bolivar E Solarte,

Chin-Hsuan Wu,

Jin-Cheng Jhang,

Fu-En Wang,

Yi-Hsuan Tsai,

Min Sun; [pdf] [supp]
[bibtex]
@InProceedings{Lee_2025_WACV, author = {Lee, Jonathan and E Solarte, Bolivar and Wu, Chin-Hsuan and Jhang, Jin-Cheng and Wang, Fu-En and Tsai, Yi-Hsuan and Sun, Min}, title = {uLayout: Unified Room Layout Estimation for Perspective and Panoramic Images}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8399-8408} }
RayGauss: Volumetric Gaussian-Based Ray Casting for Photorealistic Novel View Synthesis: Hugo Blanc,

Jean-Emmanuel Deschaud,

Alexis Paljic; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Blanc_2025_WACV, author = {Blanc, Hugo and Deschaud, Jean-Emmanuel and Paljic, Alexis}, title = {RayGauss: Volumetric Gaussian-Based Ray Casting for Photorealistic Novel View Synthesis}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1808-1817} }
To Ask or Not to Ask? Detecting Absence of Information in Vision and Language Navigation: Savitha Sam Abraham,

Sourav Garg,

Feras Dayoub; [pdf] [arXiv]
[bibtex]
@InProceedings{Abraham_2025_WACV, author = {Abraham, Savitha Sam and Garg, Sourav and Dayoub, Feras}, title = {To Ask or Not to Ask? Detecting Absence of Information in Vision and Language Navigation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7480-7489} }
F2former: When Fractional Fourier Meets Deep Wiener Deconvolution and Selective Frequency Transformer for Image Deblurring: Subhajit Paul,

Sahil Kumawat,

Ashutosh Gupta,

Deepak Mishra; [pdf] [arXiv]
[bibtex]
@InProceedings{Paul_2025_WACV, author = {Paul, Subhajit and Kumawat, Sahil and Gupta, Ashutosh and Mishra, Deepak}, title = {F2former: When Fractional Fourier Meets Deep Wiener Deconvolution and Selective Frequency Transformer for Image Deblurring}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9439-9449} }
A Simple-but-Effective Baseline for Training-Free Class-Agnostic Counting: Yuhao Lin,

Haiming Xu,

Lingqiao Liu,

Javen Qinfeng Shi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lin_2025_WACV, author = {Lin, Yuhao and Xu, Haiming and Liu, Lingqiao and Shi, Javen Qinfeng}, title = {A Simple-but-Effective Baseline for Training-Free Class-Agnostic Counting}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8144-8153} }
DiffuCE: Expert-Level CBCT Image Enhancement using a Novel Conditional Denoising Diffusion Model with Latent Alignment: Fang-Yi Su,

Tzu-Hung Chang,

Jung-Hsien Chiang; [pdf] [supp]
[bibtex]
@InProceedings{Su_2025_WACV, author = {Su, Fang-Yi and Chang, Tzu-Hung and Chiang, Jung-Hsien}, title = {DiffuCE: Expert-Level CBCT Image Enhancement using a Novel Conditional Denoising Diffusion Model with Latent Alignment}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4635-4644} }
CoVLA: Comprehensive Vision-Language-Action Dataset for Autonomous Driving: Hidehisa Arai,

Keita Miwa,

Kento Sasaki,

Kohei Watanabe,

Yu Yamaguchi,

Shunsuke Aoki,

Issei Yamamoto; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Arai_2025_WACV, author = {Arai, Hidehisa and Miwa, Keita and Sasaki, Kento and Watanabe, Kohei and Yamaguchi, Yu and Aoki, Shunsuke and Yamamoto, Issei}, title = {CoVLA: Comprehensive Vision-Language-Action Dataset for Autonomous Driving}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1933-1943} }
Reducing the Content Bias for AI-Generated Image Detection: Seoyeon Gye,

Junwon Ko,

Hyounguk Shon,

Minchan Kwon,

Junmo Kim; [pdf] [supp]
[bibtex]
@InProceedings{Gye_2025_WACV, author = {Gye, Seoyeon and Ko, Junwon and Shon, Hyounguk and Kwon, Minchan and Kim, Junmo}, title = {Reducing the Content Bias for AI-Generated Image Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {399-408} }
Structure-Aware Human Body Reshaping with Adaptive Affinity-Graph Network: Qiwen Deng,

Yangcen Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Deng_2025_WACV, author = {Deng, Qiwen and Liu, Yangcen}, title = {Structure-Aware Human Body Reshaping with Adaptive Affinity-Graph Network}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4452-4461} }
UW-GS: Distractor-Aware 3D Gaussian Splatting for Enhanced Underwater Scene Reconstruction: Haoran Wang,

Nantheera Anantrasirichai,

Fan Zhang,

David Bull; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2025_WACV, author = {Wang, Haoran and Anantrasirichai, Nantheera and Zhang, Fan and Bull, David}, title = {UW-GS: Distractor-Aware 3D Gaussian Splatting for Enhanced Underwater Scene Reconstruction}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3280-3289} }
ConvMixFormer- A Resource-Efficient Convolution Mixer for Transformer-Based Dynamic Hand Gesture Recognition: Mallika Garg,

Debashis Ghosh,

Pyari Mohan Pradhan; [pdf]
[bibtex]
@InProceedings{Garg_2025_WACV, author = {Garg, Mallika and Ghosh, Debashis and Pradhan, Pyari Mohan}, title = {ConvMixFormer- A Resource-Efficient Convolution Mixer for Transformer-Based Dynamic Hand Gesture Recognition}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6156-6166} }
Deep Joint Unrolling for Deblurring and Low-Light Image Enhancement (JUDE): Tu Vo,

Chan Y. Park; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Vo_2025_WACV, author = {Vo, Tu and Park, Chan Y.}, title = {Deep Joint Unrolling for Deblurring and Low-Light Image Enhancement (JUDE)}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2696-2705} }
VM-Gait: Multi-Modal 3D Representation Based on Virtual Marker for Gait Recognition: Zhao-Yang Wang,

Jiang Liu,

Jieneng Chen,

Rama Chellappa; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2025_WACV, author = {Wang, Zhao-Yang and Liu, Jiang and Chen, Jieneng and Chellappa, Rama}, title = {VM-Gait: Multi-Modal 3D Representation Based on Virtual Marker for Gait Recognition}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5326-5335} }
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud: Ayumu Saito,

Prachi Kudeshia,

Jiju Poovvancheri; [pdf] [supp]
[bibtex]
@InProceedings{Saito_2025_WACV, author = {Saito, Ayumu and Kudeshia, Prachi and Poovvancheri, Jiju}, title = {Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7348-7357} }
CM3T: Framework for Efficient Multimodal Learning for Inhomogeneous Interaction Datasets: Tanay Agrawal,

Mohammed Guermal,

Michal Balazia,

Francois Bremond; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Agrawal_2025_WACV, author = {Agrawal, Tanay and Guermal, Mohammed and Balazia, Michal and Bremond, Francois}, title = {CM3T: Framework for Efficient Multimodal Learning for Inhomogeneous Interaction Datasets}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7379-7388} }
CTIP: Towards Accurate Tabular-to-Image Generation for Tire Footprint Generation: Daeyoung Roh,

Donghee Han,

Jihyun Nam,

Jungsoo Oh,

Youngbin You,

Jeongheon Park,

Mun Yi; [pdf] [supp]
[bibtex]
@InProceedings{Roh_2025_WACV, author = {Roh, Daeyoung and Han, Donghee and Nam, Jihyun and Oh, Jungsoo and You, Youngbin and Park, Jeongheon and Yi, Mun}, title = {CTIP: Towards Accurate Tabular-to-Image Generation for Tire Footprint Generation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1166-1175} }
CIRCOD: Co-Saliency Inspired Referring Camouflaged Object Discovery: Avi Gupta,

Koteswar Rao Jerripothula,

Tammam Tillo; [pdf]
[bibtex]
@InProceedings{Gupta_2025_WACV, author = {Gupta, Avi and Jerripothula, Koteswar Rao and Tillo, Tammam}, title = {CIRCOD: Co-Saliency Inspired Referring Camouflaged Object Discovery}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8302-8312} }
Dense Scene Reconstruction from Light-Field Images Affected by Rolling Shutter: Hermes McGriff,

Renato Martins,

Nicolas Andreff,

Cedric Demonceaux; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{McGriff_2025_WACV, author = {McGriff, Hermes and Martins, Renato and Andreff, Nicolas and Demonceaux, Cedric}, title = {Dense Scene Reconstruction from Light-Field Images Affected by Rolling Shutter}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2622-2630} }
GauFRe: Gaussian Deformation Fields for Real-Time Dynamic Novel View Synthesis: Yiqing Liang,

Numair Khan,

Zhengqin Li,

Thu H Nguyen-Phuoc,

Douglas Lanman,

James Tompkin,

Lei Xiao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liang_2025_WACV, author = {Liang, Yiqing and Khan, Numair and Li, Zhengqin and Nguyen-Phuoc, Thu H and Lanman, Douglas and Tompkin, James and Xiao, Lei}, title = {GauFRe: Gaussian Deformation Fields for Real-Time Dynamic Novel View Synthesis}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2642-2652} }
AC-IND: Sparse CT Reconstruction Based on Attenuation Coefficient Estimation and Implicit Neural Distribution: Wangduo Xie,

Richard Schoonhoven,

Tristan van Leeuwen,

Matthew B. Blaschko; [pdf] [supp]
[bibtex]
@InProceedings{Xie_2025_WACV, author = {Xie, Wangduo and Schoonhoven, Richard and van Leeuwen, Tristan and Blaschko, Matthew B.}, title = {AC-IND: Sparse CT Reconstruction Based on Attenuation Coefficient Estimation and Implicit Neural Distribution}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3074-3083} }
ORID: Organ-Regional Information Driven Framework for Radiology Report Generation: Tiancheng Gu,

Kaicheng Yang,

Xiang An,

Ziyong Feng,

Dongnan Liu,

Weidong Cai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gu_2025_WACV, author = {Gu, Tiancheng and Yang, Kaicheng and An, Xiang and Feng, Ziyong and Liu, Dongnan and Cai, Weidong}, title = {ORID: Organ-Regional Information Driven Framework for Radiology Report Generation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {378-387} }
Rubric-Constrained Figure Skating Scoring: Arushi Rai,

Adriana Kovashka; [pdf]
[bibtex]
@InProceedings{Rai_2025_WACV, author = {Rai, Arushi and Kovashka, Adriana}, title = {Rubric-Constrained Figure Skating Scoring}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {9087-9095} }
A Reality Check on Pre-training for Exemplar-free Class-Incremental Learning: Eva Feillet,

Adrian Popescu,

Céline Hudelot; [pdf] [supp]
[bibtex]
@InProceedings{Feillet_2025_WACV, author = {Feillet, Eva and Popescu, Adrian and Hudelot, C\'eline}, title = {A Reality Check on Pre-training for Exemplar-free Class-Incremental Learning}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7614-7625} }
Polarization as Texture: Microscale 3D Shape from Polarized Light Focus: Ren Matsumoto,

Takahiro Okabe,

Ryo Kawahara; [pdf] [supp]
[bibtex]
@InProceedings{Matsumoto_2025_WACV, author = {Matsumoto, Ren and Okabe, Takahiro and Kawahara, Ryo}, title = {Polarization as Texture: Microscale 3D Shape from Polarized Light Focus}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {515-524} }
Fine-Grained Controllable Video Generation via Object Appearance and Context: Hsin-Ping Huang,

Yu-Chuan Su,

Deqing Sun,

Lu Jiang,

Xuhui Jia,

Yukun Zhu,

Ming-Hsuan Yang; [pdf] [arXiv]
[bibtex]
@InProceedings{Huang_2025_WACV, author = {Huang, Hsin-Ping and Su, Yu-Chuan and Sun, Deqing and Jiang, Lu and Jia, Xuhui and Zhu, Yukun and Yang, Ming-Hsuan}, title = {Fine-Grained Controllable Video Generation via Object Appearance and Context}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3698-3708} }
Exploiting Inter-Sample Information for Long-Tailed Out-of-Distribution Detection: Nimeshika Udayangani,

Hadi Mohaghegh Dolatabadi,

Sarah Erfani,

Christopher Leckie; [pdf] [supp]
[bibtex]
@InProceedings{Udayangani_2025_WACV, author = {Udayangani, Nimeshika and Dolatabadi, Hadi Mohaghegh and Erfani, Sarah and Leckie, Christopher}, title = {Exploiting Inter-Sample Information for Long-Tailed Out-of-Distribution Detection}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8535-8544} }
Transferable-Guided Attention is All You Need for Video Domain Adaptation: André Sacilotti,

Samuel Felipe dos Santos,

Nicu Sebe,

Jurandy Almeida; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sacilotti_2025_WACV, author = {Sacilotti, Andr\'e and dos Santos, Samuel Felipe and Sebe, Nicu and Almeida, Jurandy}, title = {Transferable-Guided Attention is All You Need for Video Domain Adaptation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8680-8690} }
An Encoder-Agnostic Weakly Supervised Method for Describing Textures: Shangbo Mao,

Deepu Rajan; [pdf] [supp]
[bibtex]
@InProceedings{Mao_2025_WACV, author = {Mao, Shangbo and Rajan, Deepu}, title = {An Encoder-Agnostic Weakly Supervised Method for Describing Textures}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8101-8110} }
Deciphering the Complaint Aspects: Towards an Aspect-Based Complaint Identification Model with Video Complaint Dataset in Finance: Sarmistha Das,

Basha Mujavarsheik,

R E Zera Lyngkhoi,

Sriparna Saha,

Alka Maurya; [pdf]
[bibtex]
@InProceedings{Das_2025_WACV, author = {Das, Sarmistha and Mujavarsheik, Basha and E Zera Lyngkhoi, R and Saha, Sriparna and Maurya, Alka}, title = {Deciphering the Complaint Aspects: Towards an Aspect-Based Complaint Identification Model with Video Complaint Dataset in Finance}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {7195-7204} }
DiffuPT: Class Imbalance Mitigation for Glaucoma Detection via Diffusion Based Generation and Model Pretraining: Youssof Nawar,

Nouran Soliman,

Moustafa Wassel,

Mohamed ElHabebe,

Noha Adly,

Marwan Torki,

Ahmed Elmassry,

Islam Ahmed; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nawar_2025_WACV, author = {Nawar, Youssof and Soliman, Nouran and Wassel, Moustafa and ElHabebe, Mohamed and Adly, Noha and Torki, Marwan and Elmassry, Ahmed and Ahmed, Islam}, title = {DiffuPT: Class Imbalance Mitigation for Glaucoma Detection via Diffusion Based Generation and Model Pretraining}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4098-4107} }
DiHuR: Diffusion-Guided Generalizable Human Reconstruction: Jinnan Chen,

Chen Li,

Gim Hee Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2025_WACV, author = {Chen, Jinnan and Li, Chen and Lee, Gim Hee}, title = {DiHuR: Diffusion-Guided Generalizable Human Reconstruction}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {6032-6041} }
CUNSB-RFIE: Context-Aware Unpaired Neural Schrodinger Bridge in Retinal Fundus Image Enhancement: Xuanzhao Dong,

Vamsi Krishna Vasa,

Wenhui Zhu,

Peijie Qiu,

Xiwen Chen,

Yi Su,

Yujian Xiong,

Zhangsihao Yang,

Yanxi Chen,

Yalin Wang; [pdf] [supp]
[bibtex]
@InProceedings{Dong_2025_WACV, author = {Dong, Xuanzhao and Vasa, Vamsi Krishna and Zhu, Wenhui and Qiu, Peijie and Chen, Xiwen and Su, Yi and Xiong, Yujian and Yang, Zhangsihao and Chen, Yanxi and Wang, Yalin}, title = {CUNSB-RFIE: Context-Aware Unpaired Neural Schrodinger Bridge in Retinal Fundus Image Enhancement}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {4502-4511} }
Self-Supervised Incremental Learning of Object Representations from Arbitrary Image Sets: George Leotescu,

Alin-Ionut Popa,

Diana-Nicoleta N Grigore,

Daniel Voinea,

Pietro Perona; [pdf] [supp]
[bibtex]
@InProceedings{Leotescu_2025_WACV, author = {Leotescu, George and Popa, Alin-Ionut and Grigore, Diana-Nicoleta N and Voinea, Daniel and Perona, Pietro}, title = {Self-Supervised Incremental Learning of Object Representations from Arbitrary Image Sets}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8133-8143} }
ECF-YOLOv7-Tiny: Improving Feature Fusion and the Receptive Field for Lightweight Object Detectors: Dan-Sebastian Bacea,

Florin Oniga; [pdf] [supp]
[bibtex]
@InProceedings{Bacea_2025_WACV, author = {Bacea, Dan-Sebastian and Oniga, Florin}, title = {ECF-YOLOv7-Tiny: Improving Feature Fusion and the Receptive Field for Lightweight Object Detectors}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {1577-1586} }
Breaking the Frame: Visual Place Recognition by Overlap Prediction: Tong Wei,

Philipp Lindenberger,

Jirí Matas,

Daniel Barath; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wei_2025_WACV, author = {Wei, Tong and Lindenberger, Philipp and Matas, Jir{\'\i} and Barath, Daniel}, title = {Breaking the Frame: Visual Place Recognition by Overlap Prediction}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2322-2331} }
Paladin: Understanding Video Intentions in Political Advertisement Videos: Hong Liu,

Yuta Nakashima,

Noboru Babaguchi; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2025_WACV, author = {Liu, Hong and Nakashima, Yuta and Babaguchi, Noboru}, title = {Paladin: Understanding Video Intentions in Political Advertisement Videos}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8228-8237} }
DarSwin-Unet: Distortion Aware Architecture: Akshaya Athwale,

Ichrak Shili,

Émile Bergeron,

Ola Ahmad,

Jean-Francois Lalonde; [pdf] [supp]
[bibtex]
@InProceedings{Athwale_2025_WACV, author = {Athwale, Akshaya and Shili, Ichrak and Bergeron, \'Emile and Ahmad, Ola and Lalonde, Jean-Francois}, title = {DarSwin-Unet: Distortion Aware Architecture}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8659-8669} }
Transientangelo: Few-Viewpoint Surface Reconstruction using Single-Photon Lidar: Weihan Luo,

Anagh Malik,

David B Lindell; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Luo_2025_WACV, author = {Luo, Weihan and Malik, Anagh and Lindell, David B}, title = {Transientangelo: Few-Viewpoint Surface Reconstruction using Single-Photon Lidar}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8712-8722} }
Shape-Biased Texture Agnostic Representations for Improved Textureless and Metallic Object Detection and 6D Pose Estimation: Peter Hönig,

Stefan Thalhammer,

Jean-Baptiste Weibel,

Matthias Hirschmanner,

Markus Vincze; [pdf]
[bibtex]
@InProceedings{Honig_2025_WACV, author = {H\"onig, Peter and Thalhammer, Stefan and Weibel, Jean-Baptiste and Hirschmanner, Matthias and Vincze, Markus}, title = {Shape-Biased Texture Agnostic Representations for Improved Textureless and Metallic Object Detection and 6D Pose Estimation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8795-8804} }
Multi-Modal Large Language Models are Effective Vision Learners: Li Sun,

Chaitanya Ahuja,

Peng Chen,

Matt D'Zmura,

Kayhan Batmanghelich,

Philip Bontrager; [pdf] [supp]
[bibtex]
@InProceedings{Sun_2025_WACV, author = {Sun, Li and Ahuja, Chaitanya and Chen, Peng and D'Zmura, Matt and Batmanghelich, Kayhan and Bontrager, Philip}, title = {Multi-Modal Large Language Models are Effective Vision Learners}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {8606-8615} }
GeoGuide: Geometric Guidance of Diffusion Models: Mateusz Poleski,

Jacek Tabor,

Przemyslaw Spurek; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Poleski_2025_WACV, author = {Poleski, Mateusz and Tabor, Jacek and Spurek, Przemyslaw}, title = {GeoGuide: Geometric Guidance of Diffusion Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {297-305} }