WACV 2026 Open Access Repository

Papers

Back
ATM: Enhanced Alignment for Text-to-Motion Generation: Ke Han,

Yueming Lyu,

Weichen Yu,

Nicu Sebe; [pdf] [supp]
[bibtex]
@InProceedings{Han_2026_WACV, author = {Han, Ke and Lyu, Yueming and Yu, Weichen and Sebe, Nicu}, title = {ATM: Enhanced Alignment for Text-to-Motion Generation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6862-6872} }
Contrastive Integrated Gradients: A Feature Attribution-Based Method for Explaining Whole Slide Image Classification: Anh Mai Vu,

Tuan L. Vo,

Ngoc Lam Quang Bui,

Nam N. B. Le,

Akash Awasthi,

Huy Q. Vo,

Thanh-Huy Nguyen,

Zhu Han,

Chandra Mohan,

Hien Van Nguyen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Vu_2026_WACV, author = {Vu, Anh Mai and Vo, Tuan L. and Bui, Ngoc Lam Quang and Le, Nam N. B. and Awasthi, Akash and Vo, Huy Q. and Nguyen, Thanh-Huy and Han, Zhu and Mohan, Chandra and Van Nguyen, Hien}, title = {Contrastive Integrated Gradients: A Feature Attribution-Based Method for Explaining Whole Slide Image Classification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1201-1210} }
Forget Less by Learning Together through Concept Consolidation: Arjun Ramesh Kaushik,

Naresh Kumar Devulapally,

Vishnu Suresh Lokhande,

Nalini Ratha,

Venu Govindaraju; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kaushik_2026_WACV, author = {Kaushik, Arjun Ramesh and Devulapally, Naresh Kumar and Lokhande, Vishnu Suresh and Ratha, Nalini and Govindaraju, Venu}, title = {Forget Less by Learning Together through Concept Consolidation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {265-275} }
GFT: Graph Feature Tuning for Efficient Point Cloud Analysis: Manish Dhakal,

Venkat R Dasari,

Rajshekhar Sunderraman,

Yi Ding; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dhakal_2026_WACV, author = {Dhakal, Manish and Dasari, Venkat R and Sunderraman, Rajshekhar and Ding, Yi}, title = {GFT: Graph Feature Tuning for Efficient Point Cloud Analysis}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7955-7964} }
Scalpel: Fine-Grained Alignment of Attention Activation Manifolds via Mixture Gaussian Bridges to Mitigate Multimodal Hallucination: Ziqiang Shi,

Rujie Liu,

Shanshan Yu,

Satoshi Munakata,

Koichi Shirahata; [pdf] [arXiv]
[bibtex]
@InProceedings{Shi_2026_WACV, author = {Shi, Ziqiang and Liu, Rujie and Yu, Shanshan and Munakata, Satoshi and Shirahata, Koichi}, title = {Scalpel: Fine-Grained Alignment of Attention Activation Manifolds via Mixture Gaussian Bridges to Mitigate Multimodal Hallucination}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2964-2973} }
MMCM: Multimodality-aware Metric using Clustering-based Modes for Probabilistic Human Motion Prediction: Kyotaro Tokoro,

Hiromu Taketsugu,

Norimichi Ukita; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tokoro_2026_WACV, author = {Tokoro, Kyotaro and Taketsugu, Hiromu and Ukita, Norimichi}, title = {MMCM: Multimodality-aware Metric using Clustering-based Modes for Probabilistic Human Motion Prediction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2637-2647} }
ScoliGaitX: A Deep Multi-Modal Fusion Network for Scoliosis Assessment via Gait Video Analysis: Kaushik Vishwakarma,

Aditya Nigam; [pdf]
[bibtex]
@InProceedings{Vishwakarma_2026_WACV, author = {Vishwakarma, Kaushik and Nigam, Aditya}, title = {ScoliGaitX: A Deep Multi-Modal Fusion Network for Scoliosis Assessment via Gait Video Analysis}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2404-2413} }
OpenCowID: Zero-Shot Visual Identification of Dairy Cows: Omkar Prabhune,

Younghyun Kim; [pdf]
[bibtex]
@InProceedings{Prabhune_2026_WACV, author = {Prabhune, Omkar and Kim, Younghyun}, title = {OpenCowID: Zero-Shot Visual Identification of Dairy Cows}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1491-1500} }
FG-TRACER: Tracing Information Flow in Multimodal Large Language Models in Free-Form Generation: Alessia Saporita,

Vittorio Pipoli,

Federico Bolelli,

Lorenzo Baraldi,

Andrea Acquaviva,

Elisa Ficarra; [pdf] [supp]
[bibtex]
@InProceedings{Saporita_2026_WACV, author = {Saporita, Alessia and Pipoli, Vittorio and Bolelli, Federico and Baraldi, Lorenzo and Acquaviva, Andrea and Ficarra, Elisa}, title = {FG-TRACER: Tracing Information Flow in Multimodal Large Language Models in Free-Form Generation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7903-7912} }
SpikeRain: Towards Energy-Efficient Single Image Deraining with Spiking Neural Networks: Md Tanvir Islam,

Inzamamul Alam,

Sambit Bakshi,

Khan Muhammad,

Javier Del Ser,

Sangtae Ahn; [pdf] [supp]
[bibtex]
@InProceedings{Islam_2026_WACV, author = {Islam, Md Tanvir and Alam, Inzamamul and Bakshi, Sambit and Muhammad, Khan and Del Ser, Javier and Ahn, Sangtae}, title = {SpikeRain: Towards Energy-Efficient Single Image Deraining with Spiking Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1094-1105} }
CAST: Evaluating Multi-Object Trackers with Context-Aware Switch and Transfer Scores: Jin Bai,

Gregory D. Hager; [pdf]
[bibtex]
@InProceedings{Bai_2026_WACV, author = {Bai, Jin and Hager, Gregory D.}, title = {CAST: Evaluating Multi-Object Trackers with Context-Aware Switch and Transfer Scores}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7260-7268} }
NavMapFusion: Diffusion-based Fusion of Navigation Maps for Online Vectorized HD Map Construction: Thomas Monninger,

Zihan Zhang,

Steffen Staab,

Sihao Ding; [pdf] [arXiv]
[bibtex]
@InProceedings{Monninger_2026_WACV, author = {Monninger, Thomas and Zhang, Zihan and Staab, Steffen and Ding, Sihao}, title = {NavMapFusion: Diffusion-based Fusion of Navigation Maps for Online Vectorized HD Map Construction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7945-7954} }
DREAM: Dynamic Prompts and GuidedMix for Efficient Continual Adaptation of Visual-Language Models: Evelyn Chee,

Mong Li Lee,

Wynne Hsu; [pdf]
[bibtex]
@InProceedings{Chee_2026_WACV, author = {Chee, Evelyn and Lee, Mong Li and Hsu, Wynne}, title = {DREAM: Dynamic Prompts and GuidedMix for Efficient Continual Adaptation of Visual-Language Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5853-5863} }
SynPlay: Large-Scale Synthetic Human Data with Real-World Diversity for Aerial-View Perception: Jinsub Yim,

Hyungtae Lee,

Sungmin Eum,

Yi-Ting Shen,

Yan Zhang,

Heesung Kwon,

Shuvra S. Bhattacharyya; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yim_2026_WACV, author = {Yim, Jinsub and Lee, Hyungtae and Eum, Sungmin and Shen, Yi-Ting and Zhang, Yan and Kwon, Heesung and Bhattacharyya, Shuvra S.}, title = {SynPlay: Large-Scale Synthetic Human Data with Real-World Diversity for Aerial-View Perception}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {938-947} }
Overcoming Small Data Limitations in Video-Based Infant Respiration Estimation: Liyang Song,

Hardik Bishnoi,

Sai Kumar Reddy Manne,

Sarah Ostadabbas,

Briana J. Taylor,

Michael Wan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Song_2026_WACV, author = {Song, Liyang and Bishnoi, Hardik and Manne, Sai Kumar Reddy and Ostadabbas, Sarah and Taylor, Briana J. and Wan, Michael}, title = {Overcoming Small Data Limitations in Video-Based Infant Respiration Estimation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6340-6349} }
SIAM: Synchronous Interaction Attention for Human Mesh Recovery: Niaz Ahmad,

Saif Ullah,

Youngmoon Lee,

Guanghui Wang; [pdf] [supp]
[bibtex]
@InProceedings{Ahmad_2026_WACV, author = {Ahmad, Niaz and Ullah, Saif and Lee, Youngmoon and Wang, Guanghui}, title = {SIAM: Synchronous Interaction Attention for Human Mesh Recovery}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4535-4545} }
OW-Rep: Open World Object Detection with Instance Representation Learning: Sunoh Lee,

Minsik Jeon,

Jihong Min,

Junwon Seo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2026_WACV, author = {Lee, Sunoh and Jeon, Minsik and Min, Jihong and Seo, Junwon}, title = {OW-Rep: Open World Object Detection with Instance Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {339-349} }
Training-free Multi-view 4D Human Motion Reconstruction Virtual Reality System: Yijie Li,

Ce Zheng,

Yijie He,

Joel Julin,

Ryosuke Ichikari,

Satoki Ogiso,

Satoshi Nakae,

Akihiro Sato,

Takeshi Kurata,

Laszlo A. Jeni; [pdf] [supp]
[bibtex]
@InProceedings{Li_2026_WACV, author = {Li, Yijie and Zheng, Ce and He, Yijie and Julin, Joel and Ichikari, Ryosuke and Ogiso, Satoki and Nakae, Satoshi and Sato, Akihiro and Kurata, Takeshi and Jeni, Laszlo A.}, title = {Training-free Multi-view 4D Human Motion Reconstruction Virtual Reality System}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {318-327} }
Beyond the Encoder: Joint Encoder-Decoder Contrastive Pre-Training Improves Dense Prediction: Sébastien Quetin,

Tapotosh Ghosh,

Farhad Maleki; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Quetin_2026_WACV, author = {Quetin, S\'ebastien and Ghosh, Tapotosh and Maleki, Farhad}, title = {Beyond the Encoder: Joint Encoder-Decoder Contrastive Pre-Training Improves Dense Prediction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1000-1010} }
Discrete Facial Encoding: A Framework for Data-driven Facial Display Discovery: Minh Tran,

Maksim Siniukov,

Zhangyu Jin,

Mohammad Soleymani; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tran_2026_WACV, author = {Tran, Minh and Siniukov, Maksim and Jin, Zhangyu and Soleymani, Mohammad}, title = {Discrete Facial Encoding: A Framework for Data-driven Facial Display Discovery}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2348-2358} }
Zero-shot Hierarchical Plant Segmentation via Foundation Segmentation Models and Text-to-image Attention: Junhao Xing,

Ryohei Miyakawa,

Yang Yang,

Xinpeng Liu,

Risa Shinoda,

Hiroaki Santo,

Yosuke Toda,

Fumio Okura; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xing_2026_WACV, author = {Xing, Junhao and Miyakawa, Ryohei and Yang, Yang and Liu, Xinpeng and Shinoda, Risa and Santo, Hiroaki and Toda, Yosuke and Okura, Fumio}, title = {Zero-shot Hierarchical Plant Segmentation via Foundation Segmentation Models and Text-to-image Attention}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2510-2519} }
Semi-supervised Domain Adaptation via Mutual Alignment through Joint Error: Dexuan Zhang,

Thomas Westfechtel,

Tatsuya Harada; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2026_WACV, author = {Zhang, Dexuan and Westfechtel, Thomas and Harada, Tatsuya}, title = {Semi-supervised Domain Adaptation via Mutual Alignment through Joint Error}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5426-5436} }
Distribution Highlighted Reference-based Label Distribution Learning for Facial Age Estimation: Satoshi Suzuki,

Shin'ya Yamaguchi,

Shoichiro Takeda,

Takuhiro Kaneko,

Shota Orihashi,

Ryo Masumura; [pdf] [supp]
[bibtex]
@InProceedings{Suzuki_2026_WACV, author = {Suzuki, Satoshi and Yamaguchi, Shin'ya and Takeda, Shoichiro and Kaneko, Takuhiro and Orihashi, Shota and Masumura, Ryo}, title = {Distribution Highlighted Reference-based Label Distribution Learning for Facial Age Estimation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6464-6473} }
VISTA: A Vision and Intent-Aware Social Attention Framework for Multi-Agent Trajectory Prediction: Stephane Da Silva Martins,

Emanuel Aldea,

Sylvie Le Hégarat-Mascle; [pdf] [supp]
[bibtex]
@InProceedings{Da_Silva_Martins_2026_WACV, author = {Da Silva Martins, Stephane and Aldea, Emanuel and Le H\'egarat-Mascle, Sylvie}, title = {VISTA: A Vision and Intent-Aware Social Attention Framework for Multi-Agent Trajectory Prediction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {287-296} }
IMKD: Intensity-Aware Multi-Level Knowledge Distillation for Camera-Radar Fusion: Shashank Mishra,

Karan Patil,

Didier Stricker,

Jason Rambach; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mishra_2026_WACV, author = {Mishra, Shashank and Patil, Karan and Stricker, Didier and Rambach, Jason}, title = {IMKD: Intensity-Aware Multi-Level Knowledge Distillation for Camera-Radar Fusion}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6027-6038} }
WWE-UIE: A Wavelet & White Balance Efficient Network for Underwater Image Enhancement: Ching-Heng Cheng,

Jen-Wei Lee,

Chia-Ming Lee,

Chih-Chung Hsu; [pdf] [arXiv]
[bibtex]
@InProceedings{Cheng_2026_WACV, author = {Cheng, Ching-Heng and Lee, Jen-Wei and Lee, Chia-Ming and Hsu, Chih-Chung}, title = {WWE-UIE: A Wavelet \& White Balance Efficient Network for Underwater Image Enhancement}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2135-2145} }
Leveraging Semantic Attribute Binding for Free-Lunch Color Control in Diffusion Models: Héctor Laria,

Alexandra Gomez-Villa,

Jiang Qin,

Muhammad Atif Butt,

Bogdan Raducanu,

Javier Vazquez-Corral,

Joost van de Weijer,

Kai Wang; [pdf] [supp]
[bibtex]
@InProceedings{Laria_2026_WACV, author = {Laria, H\'ector and Gomez-Villa, Alexandra and Qin, Jiang and Butt, Muhammad Atif and Raducanu, Bogdan and Vazquez-Corral, Javier and van de Weijer, Joost and Wang, Kai}, title = {Leveraging Semantic Attribute Binding for Free-Lunch Color Control in Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7689-7698} }
ForestSplats: Deformable Transient Field for Gaussian Splatting in the Wild: Wongi Park,

Myeongseok Nam,

Siwon Kim,

Sangwoo Jo,

Soomok Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Park_2026_WACV, author = {Park, Wongi and Nam, Myeongseok and Kim, Siwon and Jo, Sangwoo and Lee, Soomok}, title = {ForestSplats: Deformable Transient Field for Gaussian Splatting in the Wild}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6978-6987} }
3D Cell Oversegmentation Correction via Geo-Wasserstein Divergence: Peter Chen,

Bryan Chang,

Olivia A Creasey,

Julie Beth Sneddon,

Zev J Gartner,

Yining Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2026_WACV, author = {Chen, Peter and Chang, Bryan and A Creasey, Olivia and Sneddon, Julie Beth and Gartner, Zev J and Liu, Yining}, title = {3D Cell Oversegmentation Correction via Geo-Wasserstein Divergence}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7534-7543} }
STRinGS: Selective Text Refinement in Gaussian Splatting: Abhinav Raundhal,

Gaurav Behera,

P. J. Narayanan,

Ravi Kiran Sarvadevabhatla,

Makarand Tapaswi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Raundhal_2026_WACV, author = {Raundhal, Abhinav and Behera, Gaurav and Narayanan, P. J. and Sarvadevabhatla, Ravi Kiran and Tapaswi, Makarand}, title = {STRinGS: Selective Text Refinement in Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8574-8583} }
DARB-Splatting: Generalizing Splatting with Decaying Anisotropic Radial Basis Functions: Hashiru Pramuditha,

Vinasirajan Viruthshaan,

Vishagar Arunan,

Saeedha Nazar,

Sameera Ramasinghe,

Simon Lucey,

Ranga Rodrigo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pramuditha_2026_WACV, author = {Pramuditha, Hashiru and Viruthshaan, Vinasirajan and Arunan, Vishagar and Nazar, Saeedha and Ramasinghe, Sameera and Lucey, Simon and Rodrigo, Ranga}, title = {DARB-Splatting: Generalizing Splatting with Decaying Anisotropic Radial Basis Functions}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4504-4514} }
DenseBEV: Transforming BEV Grid Cells into 3D Objects: Marius Dähling,

Sebastian Krebs,

J. Marius Zöllner; [pdf] [supp]
[bibtex]
@InProceedings{Dahling_2026_WACV, author = {D\"ahling, Marius and Krebs, Sebastian and Z\"ollner, J. Marius}, title = {DenseBEV: Transforming BEV Grid Cells into 3D Objects}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2370-2379} }
Sun-E: Dataset and Benchmark for Event-Based Sun Sensing: Sydney Dolan,

Alessandro Golkar; [pdf]
[bibtex]
@InProceedings{Dolan_2026_WACV, author = {Dolan, Sydney and Golkar, Alessandro}, title = {Sun-E: Dataset and Benchmark for Event-Based Sun Sensing}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4818-4826} }
SceneEdited: A City-Scale Benchmark for 3D HD Map Updating via Image-Guided Change Detection: Chun-Jung Lin,

Tat-Jun Chin,

Sourav Garg,

Feras Dayoub; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lin_2026_WACV, author = {Lin, Chun-Jung and Chin, Tat-Jun and Garg, Sourav and Dayoub, Feras}, title = {SceneEdited: A City-Scale Benchmark for 3D HD Map Updating via Image-Guided Change Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6330-6339} }
Learning from Unknown for Open-Set Test-Time Adaptation: Taki Hasan Rafi,

Amit Agarwal,

Hitesh L. Patel,

Dong-Kyu Chae; [pdf] [supp]
[bibtex]
@InProceedings{Rafi_2026_WACV, author = {Rafi, Taki Hasan and Agarwal, Amit and Patel, Hitesh L. and Chae, Dong-Kyu}, title = {Learning from Unknown for Open-Set Test-Time Adaptation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2993-3004} }
Enhanced Back-Projection of Vision Features for 3D Symmetry Detection: Isaac Aguirre,

Ivan Sipiran; [pdf] [supp]
[bibtex]
@InProceedings{Aguirre_2026_WACV, author = {Aguirre, Isaac and Sipiran, Ivan}, title = {Enhanced Back-Projection of Vision Features for 3D Symmetry Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {66-76} }
START: Spatial and Textual Learning for Chart Understanding: Zhuoming Liu,

Xiaofeng Gao,

Feiyang Niu,

Qiaozi Gao,

Liu Liu,

Robinson Piramuthu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2026_WACV, author = {Liu, Zhuoming and Gao, Xiaofeng and Niu, Feiyang and Gao, Qiaozi and Liu, Liu and Piramuthu, Robinson}, title = {START: Spatial and Textual Learning for Chart Understanding}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8146-8156} }
Tables Guide Vision: Learning to See the Heart through Tabular Data: Marta Hasny,

Maxime Di Folco,

Keno Bressem,

Julia Schnabel; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hasny_2026_WACV, author = {Hasny, Marta and Di Folco, Maxime and Bressem, Keno and Schnabel, Julia}, title = {Tables Guide Vision: Learning to See the Heart through Tabular Data}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1716-1725} }
Adversarial Pseudo-replay for Exemplar-free Class-incremental Learning: Hiroto Honda; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Honda_2026_WACV, author = {Honda, Hiroto}, title = {Adversarial Pseudo-replay for Exemplar-free Class-incremental Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7493-7502} }
AugMapNet: Improving Spatial Latent Structure via BEV Grid Augmentation for Enhanced Vectorized Online HD Map Construction: Thomas Monninger,

Md Zafar Anwar,

Stanislaw Antol,

Steffen Staab,

Sihao Ding; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Monninger_2026_WACV, author = {Monninger, Thomas and Anwar, Md Zafar and Antol, Stanislaw and Staab, Steffen and Ding, Sihao}, title = {AugMapNet: Improving Spatial Latent Structure via BEV Grid Augmentation for Enhanced Vectorized Online HD Map Construction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8541-8550} }
Sketch-guided Cage-based 3D Gaussian Splatting Deformation: Tianhao Xie,

Noam Aigerman,

Eugene Belilovsky,

Tiberiu Popa; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xie_2026_WACV, author = {Xie, Tianhao and Aigerman, Noam and Belilovsky, Eugene and Popa, Tiberiu}, title = {Sketch-guided Cage-based 3D Gaussian Splatting Deformation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3658-3667} }
Mem-MLP: Real-Time 3D Human Motion Generation from Sparse Inputs: Sinan Mutlu,

Georgios F. Angelis,

Savas Ozkan,

Paul Wisbey,

Anastasios Drosou,

Mete Ozay; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mutlu_2026_WACV, author = {Mutlu, Sinan and Angelis, Georgios F. and Ozkan, Savas and Wisbey, Paul and Drosou, Anastasios and Ozay, Mete}, title = {Mem-MLP: Real-Time 3D Human Motion Generation from Sparse Inputs}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8343-8352} }
RapidMV: Leveraging Spatio-Angular Latent Space for Efficient and Consistent Text-to-Multi-View Synthesis: Seungwook Kim,

Yichun Shi,

Kejie Li,

Minsu Cho,

Peng Wang; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2026_WACV, author = {Kim, Seungwook and Shi, Yichun and Li, Kejie and Cho, Minsu and Wang, Peng}, title = {RapidMV: Leveraging Spatio-Angular Latent Space for Efficient and Consistent Text-to-Multi-View Synthesis}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1674-1684} }
BrandFusion: Aligning Image Generation with Brand Styles: Parul Gupta,

Varun Khurana,

Yaman Kumar Singla,

Balaji Krishnamurthy,

Abhinav Dhall; [pdf] [supp]
[bibtex]
@InProceedings{Gupta_2026_WACV, author = {Gupta, Parul and Khurana, Varun and Singla, Yaman Kumar and Krishnamurthy, Balaji and Dhall, Abhinav}, title = {BrandFusion: Aligning Image Generation with Brand Styles}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2316-2326} }
SurgXBench: Explainable Vision-Language Model Benchmark for Surgery: Jiajun Cheng,

Xianwu Zhao,

Sainan Liu,

Xiaofan Yu,

Ravi Prakash,

Patrick J. Codd,

Jonathan Elliott Katz,

Shan Lin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cheng_2026_WACV, author = {Cheng, Jiajun and Zhao, Xianwu and Liu, Sainan and Yu, Xiaofan and Prakash, Ravi and Codd, Patrick J. and Katz, Jonathan Elliott and Lin, Shan}, title = {SurgXBench: Explainable Vision-Language Model Benchmark for Surgery}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8188-8198} }
SCALEX: Scalable Concept and Latent Exploration for Diffusion Models: E. Zhixuan Zeng,

Yuhao Chen,

Alexander Wong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zeng_2026_WACV, author = {Zeng, E. Zhixuan and Chen, Yuhao and Wong, Alexander}, title = {SCALEX: Scalable Concept and Latent Exploration for Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3617-3627} }
CanKD: Cross-Attention-based Non-local Operation for Feature-based Knowledge Distillation: Shizhe Sun,

Wataru Ohyama; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sun_2026_WACV, author = {Sun, Shizhe and Ohyama, Wataru}, title = {CanKD: Cross-Attention-based Non-local Operation for Feature-based Knowledge Distillation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8606-8616} }
Reverse Personalization: Han-Wei Kung,

Tuomas Varanka,

Nicu Sebe; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kung_2026_WACV, author = {Kung, Han-Wei and Varanka, Tuomas and Sebe, Nicu}, title = {Reverse Personalization}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {988-999} }
HumanBench: Two Heads, No Legs, But Mostly Human, the State of Generative Capabilities in T2I Models: Anubhooti Jain,

Mayank Vatsa,

Richa Singh; [pdf] [supp]
[bibtex]
@InProceedings{Jain_2026_WACV, author = {Jain, Anubhooti and Vatsa, Mayank and Singh, Richa}, title = {HumanBench: Two Heads, No Legs, But Mostly Human, the State of Generative Capabilities in T2I Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4087-4096} }
SmokeBench: Evaluating Multimodal Large Language Models for Wildfire Smoke Detection: Tianye Qi,

Weihao Li,

Nick Barnes; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Qi_2026_WACV, author = {Qi, Tianye and Li, Weihao and Barnes, Nick}, title = {SmokeBench: Evaluating Multimodal Large Language Models for Wildfire Smoke Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1043-1053} }
ObjectCore - Efficient Few-shot Logical Anomaly Detection using Object Representations: Matic Fučka,

Vitjan Zavrtanik,

Danijel Skočaj; [pdf] [supp]
[bibtex]
@InProceedings{Fucka_2026_WACV, author = {Fu\v{c}ka, Matic and Zavrtanik, Vitjan and Sko\v{c}aj, Danijel}, title = {ObjectCore - Efficient Few-shot Logical Anomaly Detection using Object Representations}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3857-3867} }
CLIP-IT: CLIP-based Pairing of Histology Images with Privileged Textual Information: Banafsheh Karimian,

Giulia Avanzato,

Soufiane Belharbi,

Alexis Guichemerre,

Luke McCaffrey,

Mohammadhadi Shateri,

Eric Granger; [pdf] [supp]
[bibtex]
@InProceedings{Karimian_2026_WACV, author = {Karimian, Banafsheh and Avanzato, Giulia and Belharbi, Soufiane and Guichemerre, Alexis and McCaffrey, Luke and Shateri, Mohammadhadi and Granger, Eric}, title = {CLIP-IT: CLIP-based Pairing of Histology Images with Privileged Textual Information}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3700-3709} }
UniTabBank: A Large Scale Multi-Lingual, Multi-Layout, Multi-Type, Multi-Format Dataset for Table Detection: Ajoy Mondal,

Saumya Mundra,

Avijit Dasgupta,

C.V. Jawahar; [pdf] [supp]
[bibtex]
@InProceedings{Mondal_2026_WACV, author = {Mondal, Ajoy and Mundra, Saumya and Dasgupta, Avijit and Jawahar, C.V.}, title = {UniTabBank: A Large Scale Multi-Lingual, Multi-Layout, Multi-Type, Multi-Format Dataset for Table Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6486-6495} }
Temporal Object Captioning for Street Scene Videos from LiDAR Tracks: Vignesh Gopinathan,

Urs Zimmermann,

Michael Arnold,

Matthias Rottmann; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gopinathan_2026_WACV, author = {Gopinathan, Vignesh and Zimmermann, Urs and Arnold, Michael and Rottmann, Matthias}, title = {Temporal Object Captioning for Street Scene Videos from LiDAR Tracks}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2848-2857} }
MDUNet: Multimodal Decoding UNet for Passive Occluder-Aided Non-line-of-sight 3D Imaging: Fadlullah Raji,

John Murray-Bruce; [pdf] [supp]
[bibtex]
@InProceedings{Raji_2026_WACV, author = {Raji, Fadlullah and Murray-Bruce, John}, title = {MDUNet: Multimodal Decoding UNet for Passive Occluder-Aided Non-line-of-sight 3D Imaging}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {461-471} }
Being Positive about Negative Queries: Exclusion Aware Multimodal Retrieval using Disentangled Representations: Prachi Jha,

Sumit Bhatia,

Srikanta Bedathur; [pdf]
[bibtex]
@InProceedings{Jha_2026_WACV, author = {Jha, Prachi and Bhatia, Sumit and Bedathur, Srikanta}, title = {Being Positive about Negative Queries: Exclusion Aware Multimodal Retrieval using Disentangled Representations}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7832-7841} }
Gaussian Swaying: Surface-Based Framework for Aerodynamic Simulation with 3D Gaussians: Hongru Yan,

Xiang Zhang,

Zeyuan Chen,

Fangyin Wei,

Zhuowen Tu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yan_2026_WACV, author = {Yan, Hongru and Zhang, Xiang and Chen, Zeyuan and Wei, Fangyin and Tu, Zhuowen}, title = {Gaussian Swaying: Surface-Based Framework for Aerodynamic Simulation with 3D Gaussians}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4932-4942} }
Enhancing Vision Language Corruption Robustness using Cross-Distribution & Prompted Denoisers: Sameer Shafayet Latif,

Sadab Shiper,

K. M. Rahiduzzaman Kiran,

Md Farhan Ishmam,

Md Azam Hossain,

Abu Raihan Mostofa Kamal,

Md Hamjajul Ashmafee; [pdf] [supp]
[bibtex]
@InProceedings{Latif_2026_WACV, author = {Latif, Sameer Shafayet and Shiper, Sadab and Kiran, K. M. Rahiduzzaman and Ishmam, Md Farhan and Hossain, Md Azam and Kamal, Abu Raihan Mostofa and Ashmafee, Md Hamjajul}, title = {Enhancing Vision Language Corruption Robustness using Cross-Distribution \& Prompted Denoisers}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5754-5765} }
FALCONEye: Finding Answers and Localizing Content in ONE-hour-long videos with multi-modal LLMs: Carlos Plou,

Cesar Borja,

Ruben Martinez-Cantin,

Ana C. Murillo; [pdf] [supp]
[bibtex]
@InProceedings{Plou_2026_WACV, author = {Plou, Carlos and Borja, Cesar and Martinez-Cantin, Ruben and Murillo, Ana C.}, title = {FALCONEye: Finding Answers and Localizing Content in ONE-hour-long videos with multi-modal LLMs}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1334-1344} }
WALDO: Where Unseen Model-based 6D Pose Estimation Meets Occlusion: Sajjad Pakdamansavoji,

Yintao Ma,

Amir Rasouli,

Tongtong Cao; [pdf] [arXiv]
[bibtex]
@InProceedings{Pakdamansavoji_2026_WACV, author = {Pakdamansavoji, Sajjad and Ma, Yintao and Rasouli, Amir and Cao, Tongtong}, title = {WALDO: Where Unseen Model-based 6D Pose Estimation Meets Occlusion}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4067-4076} }
Enabling High-Quality In-the-Wild Imaging from Severely Aberrated Metalens Bursts: Debabrata Mandal,

Zhihan Peng,

Yujie Wang,

Praneeth Chakravarthula; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mandal_2026_WACV, author = {Mandal, Debabrata and Peng, Zhihan and Wang, Yujie and Chakravarthula, Praneeth}, title = {Enabling High-Quality In-the-Wild Imaging from Severely Aberrated Metalens Bursts}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {849-859} }
CORA: Consistency-Guided Semi-Supervised Framework for Reasoning Segmentation: Prantik Howlader,

Hoang Nguyen-Canh,

Srijan Das,

Jingyi Xu,

Hieu Le,

Dimitris Samaras; [pdf] [supp]
[bibtex]
@InProceedings{Howlader_2026_WACV, author = {Howlader, Prantik and Nguyen-Canh, Hoang and Das, Srijan and Xu, Jingyi and Le, Hieu and Samaras, Dimitris}, title = {CORA: Consistency-Guided Semi-Supervised Framework for Reasoning Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5934-5944} }
Gradient-Free Classifier Guidance for Diffusion Model Sampling: Rahul Shenoy,

Zhihong Pan,

Kaushik Balakrishnan,

Qiseng Cheng,

Yongmoon Jeon,

Heejune Yang,

Jaewon Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shenoy_2026_WACV, author = {Shenoy, Rahul and Pan, Zhihong and Balakrishnan, Kaushik and Cheng, Qiseng and Jeon, Yongmoon and Yang, Heejune and Kim, Jaewon}, title = {Gradient-Free Classifier Guidance for Diffusion Model Sampling}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3162-3171} }
Point2Pose: A Generative Framework for 3D Human Pose Estimation with Multi-View Point Cloud Dataset: Hyunsoo Lee,

Daeum Jeon,

Hyeokjae Oh; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2026_WACV, author = {Lee, Hyunsoo and Jeon, Daeum and Oh, Hyeokjae}, title = {Point2Pose: A Generative Framework for 3D Human Pose Estimation with Multi-View Point Cloud Dataset}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6744-6753} }
GDoFS: Gaussian DoF Separation for Plausible 3D Geometry in Sparse-View 3DGS: Yongsung Kim,

Jooyoung Choi,

Sungroh Yoon; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2026_WACV, author = {Kim, Yongsung and Choi, Jooyoung and Yoon, Sungroh}, title = {GDoFS: Gaussian DoF Separation for Plausible 3D Geometry in Sparse-View 3DGS}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6643-6652} }
Gen-AFFECT: Generation of Avatar Fine-grained Facial Expressions with Consistent identiTy: Hao Yu,

Rupayan Mallick,

Margrit Betke,

Sarah Adel Bargal; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2026_WACV, author = {Yu, Hao and Mallick, Rupayan and Betke, Margrit and Bargal, Sarah Adel}, title = {Gen-AFFECT: Generation of Avatar Fine-grained Facial Expressions with Consistent identiTy}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3889-3899} }
Distilling Offline Action Detection Models into Real-Time Streaming Models: Deep Patel,

Yasunori Babazaki,

Yasuto Nagase,

Iain Melvin,

Martin Renqiang Min; [pdf]
[bibtex]
@InProceedings{Patel_2026_WACV, author = {Patel, Deep and Babazaki, Yasunori and Nagase, Yasuto and Melvin, Iain and Min, Martin Renqiang}, title = {Distilling Offline Action Detection Models into Real-Time Streaming Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6205-6214} }
From Bands to Depth: Understanding Bathymetry Decisions on Sentinel-2: Satyaki Roy Chowdhury,

Aswathnarayan Radhakrishnan,

Hari Subramoni; [pdf] [arXiv]
[bibtex]
@InProceedings{Chowdhury_2026_WACV, author = {Chowdhury, Satyaki Roy and Radhakrishnan, Aswathnarayan and Subramoni, Hari}, title = {From Bands to Depth: Understanding Bathymetry Decisions on Sentinel-2}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2063-2072} }
Remote Sensing Forestry Similarity Convolution: Shikuan Wang,

Yuangong Chen,

Jianzhou Gong,

Lingyi Meng,

Mengquan Wu,

Longxing Liu,

Haiwei Yuan,

Mingbin Guo; [pdf]
[bibtex]
@InProceedings{Wang_2026_WACV, author = {Wang, Shikuan and Chen, Yuangong and Gong, Jianzhou and Meng, Lingyi and Wu, Mengquan and Liu, Longxing and Yuan, Haiwei and Guo, Mingbin}, title = {Remote Sensing Forestry Similarity Convolution}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7565-7575} }
Conjuring Positive Pairs for Efficient Unification of Representation Learning and Image Synthesis: Imanol G. Estepa,

Jesús M. Rodríguez-de-Vera,

Ignacio Sarasúa,

Bhalaji Nagarajan,

Petia Radeva; [pdf] [supp]
[bibtex]
@InProceedings{Estepa_2026_WACV, author = {Estepa, Imanol G. and Rodr{\'\i}guez-de-Vera, Jes\'us M. and Saras\'ua, Ignacio and Nagarajan, Bhalaji and Radeva, Petia}, title = {Conjuring Positive Pairs for Efficient Unification of Representation Learning and Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {751-761} }
Root Completion from Intraoral Scans of Tooth Crowns using Diffusion with Patch Perturbation: Yohan Jang,

In-Seok Song,

Seung Jun Baek; [pdf]
[bibtex]
@InProceedings{Jang_2026_WACV, author = {Jang, Yohan and Song, In-Seok and Baek, Seung Jun}, title = {Root Completion from Intraoral Scans of Tooth Crowns using Diffusion with Patch Perturbation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {483-492} }
Multimodal Graph Representation Learning over Arbitrary Sets of Modalities: Santosh Patapati,

Trisanth Srinivasan; [pdf] [supp]
[bibtex]
@InProceedings{Patapati_2026_WACV, author = {Patapati, Santosh and Srinivasan, Trisanth}, title = {Multimodal Graph Representation Learning over Arbitrary Sets of Modalities}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7104-7115} }
FlowMorph: Revealing an Optimizable Flow Latent Space for Controlled Image Morphing: Yan Zheng,

Yi Yang,

Lanqing Guo,

Zhangyang Wang; [pdf] [supp]
[bibtex]
@InProceedings{Zheng_2026_WACV, author = {Zheng, Yan and Yang, Yi and Guo, Lanqing and Wang, Zhangyang}, title = {FlowMorph: Revealing an Optimizable Flow Latent Space for Controlled Image Morphing}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2455-2464} }
Crafting Descriptive Information for a Zero-shot Method to Improve Knowledge-Based Visual Question Answering Performance: Mohammad Mahdi Moradi,

Sudhir Mudur; [pdf] [supp]
[bibtex]
@InProceedings{Moradi_2026_WACV, author = {Moradi, Mohammad Mahdi and Mudur, Sudhir}, title = {Crafting Descriptive Information for a Zero-shot Method to Improve Knowledge-Based Visual Question Answering Performance}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3120-3128} }
Boosting Medical Vision-Language Pretraining via Momentum Self-Distillation under Limited Computing Resources: Phuc Pham,

Nhu Pham,

Ngoc Quoc Ly; [pdf] [arXiv]
[bibtex]
@InProceedings{Pham_2026_WACV, author = {Pham, Phuc and Pham, Nhu and Ly, Ngoc Quoc}, title = {Boosting Medical Vision-Language Pretraining via Momentum Self-Distillation under Limited Computing Resources}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {860-868} }
Uncertainty-Aware Vision-Language Segmentation for Medical Imaging: Aryan Das,

Tanishq Rachamalla,

Koushik Biswas,

Swalpa Kumar Roy,

Vinay Kumar Verma; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Das_2026_WACV, author = {Das, Aryan and Rachamalla, Tanishq and Biswas, Koushik and Roy, Swalpa Kumar and Verma, Vinay Kumar}, title = {Uncertainty-Aware Vision-Language Segmentation for Medical Imaging}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8490-8499} }
MR-Pruner: Training-free Multi-resolution Visual Token Pruning for Multi-modal Large Language Models: Seunghoon Han,

Hyewon Lee,

Soyoung Park,

Jong-Ryul Lee,

Sungsu Lim; [pdf]
[bibtex]
@InProceedings{Han_2026_WACV, author = {Han, Seunghoon and Lee, Hyewon and Park, Soyoung and Lee, Jong-Ryul and Lim, Sungsu}, title = {MR-Pruner: Training-free Multi-resolution Visual Token Pruning for Multi-modal Large Language Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1084-1093} }
SeqFeedNet: Sequential Feature Feedback Network for Background Subtraction: Yu-Shun Huang,

Jing-Ming Guo,

Yi-Xiang Yang; [pdf] [supp]
[bibtex]
@InProceedings{Huang_2026_WACV, author = {Huang, Yu-Shun and Guo, Jing-Ming and Yang, Yi-Xiang}, title = {SeqFeedNet: Sequential Feature Feedback Network for Background Subtraction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8199-8208} }
Crash2DocAI: Automated Integration of Post-Crash Car Part Images into Technical Reports: Vaclav Divis,

Jessica Giovagnola,

Khalil Ben Chikha,

Marek Hrúz; [pdf]
[bibtex]
@InProceedings{Divis_2026_WACV, author = {Divis, Vaclav and Giovagnola, Jessica and Ben Chikha, Khalil and Hr\'uz, Marek}, title = {Crash2DocAI: Automated Integration of Post-Crash Car Part Images into Technical Reports}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8272-8281} }
CoL2A: Convolution-free Local Linear Attention for SpatioTemporal Event Processing: Yusuke Sekikawa,

Jun Nagata,

Itsumi Araki,

Andreu Girbau; [pdf] [supp]
[bibtex]
@InProceedings{Sekikawa_2026_WACV, author = {Sekikawa, Yusuke and Nagata, Jun and Araki, Itsumi and Girbau, Andreu}, title = {CoL2A: Convolution-free Local Linear Attention for SpatioTemporal Event Processing}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4869-4880} }
From Prompt to Production: Automating Brand-Safe Marketing Imagery with Text-to-Image Models: Parmida Atighehchian,

Henry Wang,

Andrei Kapustin,

Boris Lerner,

Tiancheng Jiang,

Taylor Jensen,

Negin Sokhandan; [pdf] [supp]
[bibtex]
@InProceedings{Atighehchian_2026_WACV, author = {Atighehchian, Parmida and Wang, Henry and Kapustin, Andrei and Lerner, Boris and Jiang, Tiancheng and Jensen, Taylor and Sokhandan, Negin}, title = {From Prompt to Production: Automating Brand-Safe Marketing Imagery with Text-to-Image Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6818-6826} }
2S-CEDiff: A Two-Stage Diffusion Framework for Generating High-Fidelity Contrast-Enhanced CT Images from Non-Contrast Scans: Yibang Wu,

Tzung-Dau Wang,

Shang-Hong Lai; [pdf] [supp]
[bibtex]
@InProceedings{Wu_2026_WACV, author = {Wu, Yibang and Wang, Tzung-Dau and Lai, Shang-Hong}, title = {2S-CEDiff: A Two-Stage Diffusion Framework for Generating High-Fidelity Contrast-Enhanced CT Images from Non-Contrast Scans}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3918-3927} }
Descrip3D: Enhancing Large Language Model-based 3D Scene Understanding with Object-Level Text Descriptions: Jintang Xue,

Ganning Zhao,

Jie-En Yao,

Hong-En Chen,

Yue Hu,

Meida Chen,

Suya You,

C.-C. Jay Kuo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xue_2026_WACV, author = {Xue, Jintang and Zhao, Ganning and Yao, Jie-En and Chen, Hong-En and Hu, Yue and Chen, Meida and You, Suya and Kuo, C.-C. Jay}, title = {Descrip3D: Enhancing Large Language Model-based 3D Scene Understanding with Object-Level Text Descriptions}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1746-1756} }
Unconditional Priors Matter! Improving Conditional Generation of Fine-Tuned Diffusion Models: Prin Phunyaphibarn,

Phillip Y. Lee,

Jaihoon Kim,

Minhyuk Sung; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Phunyaphibarn_2026_WACV, author = {Phunyaphibarn, Prin and Lee, Phillip Y. and Kim, Jaihoon and Sung, Minhyuk}, title = {Unconditional Priors Matter! Improving Conditional Generation of Fine-Tuned Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3982-3992} }
MuseDance: A Diffusion-based Music-Driven Image Animation System: Zhikang Dong,

Weituo Hao,

Ju-Chiang Wang,

Peng Zhang,

Pawel Polak; [pdf]
[bibtex]
@InProceedings{Dong_2026_WACV, author = {Dong, Zhikang and Hao, Weituo and Wang, Ju-Chiang and Zhang, Peng and Polak, Pawel}, title = {MuseDance: A Diffusion-based Music-Driven Image Animation System}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3813-3824} }
1LoRA: Summation Compression for Very Low-Rank Adaptation: Alessio Quercia,

Zhuo Cao,

Arya Bangun,

Richard D. Paul,

Abigail Morrison,

Ira Assent,

Hanno Scharr; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Quercia_2026_WACV, author = {Quercia, Alessio and Cao, Zhuo and Bangun, Arya and Paul, Richard D. and Morrison, Abigail and Assent, Ira and Scharr, Hanno}, title = {1LoRA: Summation Compression for Very Low-Rank Adaptation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2253-2262} }
MaxInfo: A Training-Free Key-Frame Selection Method Using Maximum Volume for Enhanced Video Understanding: Pengyi Li,

Irina Abdullaeva,

Alexander Gambashidze,

Andrey Kuznetsov,

Ivan Oseledets; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2026_WACV, author = {Li, Pengyi and Abdullaeva, Irina and Gambashidze, Alexander and Kuznetsov, Andrey and Oseledets, Ivan}, title = {MaxInfo: A Training-Free Key-Frame Selection Method Using Maximum Volume for Enhanced Video Understanding}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7198-7207} }
Conditional Text-to-Image Generation with Reference Guidance: Taewook Kim,

Ze Wang,

Zhengyuan Yang,

Jiang Wang,

Lijuan Wang,

Zicheng Liu,

Qiang Qiu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2026_WACV, author = {Kim, Taewook and Wang, Ze and Yang, Zhengyuan and Wang, Jiang and Wang, Lijuan and Liu, Zicheng and Qiu, Qiang}, title = {Conditional Text-to-Image Generation with Reference Guidance}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2879-2889} }
SDT-6D: Fully Sparse Depth-Transformer for Staged End-to-End 6D Pose Estimation in Industrial Multi-View Bin Picking: Nico Leuze,

Maximilian Hoh,

Samed Doğan,

Nicolas R.-Peña,

Alfred Schoettl; [pdf]
[bibtex]
@InProceedings{Leuze_2026_WACV, author = {Leuze, Nico and Hoh, Maximilian and Do\u{g}an, Samed and R.-Pe\~na, Nicolas and Schoettl, Alfred}, title = {SDT-6D: Fully Sparse Depth-Transformer for Staged End-to-End 6D Pose Estimation in Industrial Multi-View Bin Picking}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8406-8415} }
VideoSketcher: A Training-Free Approach for Coherent Video Sketch Transfer: Huining Li,

Bangzhen Liu,

Rui Yang,

Yang Zhou,

Chenshu Xu,

Xufang Pang,

Shengfeng He; [pdf] [supp]
[bibtex]
@InProceedings{Li_2026_WACV, author = {Li, Huining and Liu, Bangzhen and Yang, Rui and Zhou, Yang and Xu, Chenshu and Pang, Xufang and He, Shengfeng}, title = {VideoSketcher: A Training-Free Approach for Coherent Video Sketch Transfer}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7333-7343} }
From Darkness to Detail: Frequency-Aware SSMs for Low-Light Vision: Eashan Adhikarla,

Kai Zhang,

Gong Chen,

John Nicholson,

Brian D. Davison; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Adhikarla_2026_WACV, author = {Adhikarla, Eashan and Zhang, Kai and Chen, Gong and Nicholson, John and Davison, Brian D.}, title = {From Darkness to Detail: Frequency-Aware SSMs for Low-Light Vision}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6956-6967} }
Deepfake Detection that Generalizes Across Benchmarks: Andrii Yermakov,

Jan Cech,

Jiri Matas,

Mario Fritz; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yermakov_2026_WACV, author = {Yermakov, Andrii and Cech, Jan and Matas, Jiri and Fritz, Mario}, title = {Deepfake Detection that Generalizes Across Benchmarks}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {773-783} }
Mean-Shift Distillation for Diffusion Mode Seeking: Vikas Thamizharasan,

Nikitas Chatzis,

Iliyan Georgiev,

Matthew Fisher,

Evangelos Kalogerakis,

Difan Liu,

Nanxuan Zhao,

Michal Lukáč; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Thamizharasan_2026_WACV, author = {Thamizharasan, Vikas and Chatzis, Nikitas and Georgiev, Iliyan and Fisher, Matthew and Kalogerakis, Evangelos and Liu, Difan and Zhao, Nanxuan and Luk\'a\v{c}, Michal}, title = {Mean-Shift Distillation for Diffusion Mode Seeking}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6537-6546} }
ISALux: Illumination and Semantics-Aware Transformer Employing Mixture of Experts for Low Light Image Enhancement: Raul Balmez,

Alexandru Brateanu,

Ciprian Orhei,

Codruta O. Ancuti,

Cosmin Ancuti; [pdf] [supp]
[bibtex]
@InProceedings{Balmez_2026_WACV, author = {Balmez, Raul and Brateanu, Alexandru and Orhei, Ciprian and Ancuti, Codruta O. and Ancuti, Cosmin}, title = {ISALux: Illumination and Semantics-Aware Transformer Employing Mixture of Experts for Low Light Image Enhancement}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7862-7872} }
CycleSL: Server-Client Cyclical Update Driven Scalable Split Learning: Mengdi Wang,

Efe Bozkir,

Enkelejda Kasneci; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2026_WACV, author = {Wang, Mengdi and Bozkir, Efe and Kasneci, Enkelejda}, title = {CycleSL: Server-Client Cyclical Update Driven Scalable Split Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1841-1851} }
MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenes: Ruiyuan Gao,

Kai Chen,

Zhihao Li,

Lanqing Hong,

Zhenguo Li,

Qiang Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gao_2026_WACV, author = {Gao, Ruiyuan and Chen, Kai and Li, Zhihao and Hong, Lanqing and Li, Zhenguo and Xu, Qiang}, title = {MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenes}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5724-5733} }
SVS-GAN for Semantic Synthesis of Traffic Videos for Autonomous Driving: Khaled M. Seyam,

Julian Wiederer,

Markus Braun,

Bin Yang; [pdf] [supp]
[bibtex]
@InProceedings{Seyam_2026_WACV, author = {Seyam, Khaled M. and Wiederer, Julian and Braun, Markus and Yang, Bin}, title = {SVS-GAN for Semantic Synthesis of Traffic Videos for Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8650-8659} }
From SAM to DINOv2: Towards Distilling Foundation Models to Lightweight Baselines for Generalized Polyp Segmentation: Shivanshu Agnihotri,

Snehashis Majhi,

Deepak Ranjan Nayak,

Debesh Jha; [pdf] [arXiv]
[bibtex]
@InProceedings{Agnihotri_2026_WACV, author = {Agnihotri, Shivanshu and Majhi, Snehashis and Nayak, Deepak Ranjan and Jha, Debesh}, title = {From SAM to DINOv2: Towards Distilling Foundation Models to Lightweight Baselines for Generalized Polyp Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1757-1766} }
One-shot Portrait Stylizaiton via Geometric Alignment: Xinrui Wang,

Zilin Guo,

Zhuoru Li,

Jinze Yu,

Heng Zhang,

Yusuke Iwasawa,

Yutaka Matsuo,

Jiaxian Guo; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2026_WACV, author = {Wang, Xinrui and Guo, Zilin and Li, Zhuoru and Yu, Jinze and Zhang, Heng and Iwasawa, Yusuke and Matsuo, Yutaka and Guo, Jiaxian}, title = {One-shot Portrait Stylizaiton via Geometric Alignment}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4964-4973} }
Decoupling Shape and Texture in SAM-2 via Controlled Texture Replacement: Inbal Cohen,

Boaz Meivar,

Peihan Tu,

Shai Avidan,

Gal Oren; [pdf] [supp]
[bibtex]
@InProceedings{Cohen_2026_WACV, author = {Cohen, Inbal and Meivar, Boaz and Tu, Peihan and Avidan, Shai and Oren, Gal}, title = {Decoupling Shape and Texture in SAM-2 via Controlled Texture Replacement}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4077-4086} }
Graph-Based Spectral Attention with Multi-Spectral Images for Illuminant Estimation: Dong-Hoon Kang,

Seung-Yeop Baek,

Jong-Ok Kim; [pdf] [supp]
[bibtex]
@InProceedings{Kang_2026_WACV, author = {Kang, Dong-Hoon and Baek, Seung-Yeop and Kim, Jong-Ok}, title = {Graph-Based Spectral Attention with Multi-Spectral Images for Illuminant Estimation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2912-2922} }
Memoire: Learning User Personas from Gallery Tags for Personalized Photo Curation: Praful Mathur,

Mohsin Iftekhar,

Aman Sharma,

Sarvesh Tiwari,

Meghali Deka,

Sathish Cherukuri,

K Roopa Sheshadri,

Rakesh Valusa; [pdf] [supp]
[bibtex]
@InProceedings{Mathur_2026_WACV, author = {Mathur, Praful and Iftekhar, Mohsin and Sharma, Aman and Tiwari, Sarvesh and Deka, Meghali and Cherukuri, Sathish and Sheshadri, K Roopa and Valusa, Rakesh}, title = {Memoire: Learning User Personas from Gallery Tags for Personalized Photo Curation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6873-6882} }
Boosting Unsupervised Video Instance Segmentation with Automatic Quality-Guided Self-Training: Kaixuan Lu,

Mehmet Onurcan Kaya,

Dim P. Papadopoulos; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lu_2026_WACV, author = {Lu, Kaixuan and Kaya, Mehmet Onurcan and Papadopoulos, Dim P.}, title = {Boosting Unsupervised Video Instance Segmentation with Automatic Quality-Guided Self-Training}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7387-7397} }
Test Time Adaptation Using Adaptive Quantile Recalibration: Paria Mehrbod,

Pedro Vianna,

Geraldin Nanfack,

Guy Wolf,

Eugene Belilovsky; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mehrbod_2026_WACV, author = {Mehrbod, Paria and Vianna, Pedro and Nanfack, Geraldin and Wolf, Guy and Belilovsky, Eugene}, title = {Test Time Adaptation Using Adaptive Quantile Recalibration}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5986-5995} }
Knowledge to Sight: Reasoning over Visual Attributes via Knowledge Decomposition for Abnormality Grounding: Jun Li,

Che Liu,

Wenjia Bai,

Mingxuan Liu,

Rossella Arcucci,

Cosmin I. Bercea,

Julia Schnabel; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2026_WACV, author = {Li, Jun and Liu, Che and Bai, Wenjia and Liu, Mingxuan and Arcucci, Rossella and Bercea, Cosmin I. and Schnabel, Julia}, title = {Knowledge to Sight: Reasoning over Visual Attributes via Knowledge Decomposition for Abnormality Grounding}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2359-2369} }
SceneEval: Evaluating Semantic Coherence in Text-Conditioned 3D Indoor Scene Synthesis: Hou In Ivan Tam,

Hou In Derek Pun,

Austin T. Wang,

Angel X. Chang,

Manolis Savva; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tam_2026_WACV, author = {Tam, Hou In Ivan and Pun, Hou In Derek and Wang, Austin T. and Chang, Angel X. and Savva, Manolis}, title = {SceneEval: Evaluating Semantic Coherence in Text-Conditioned 3D Indoor Scene Synthesis}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7355-7365} }
MAFM3: Modular Adaptation of Foundation Models for Multi-Modal Medical AI: Mohammad Areeb Qazi,

Munachiso S Nwadike,

Ibrahim Almakky,

Mohammad Yaqub,

Numan Saeed; [pdf]
[bibtex]
@InProceedings{Qazi_2026_WACV, author = {Qazi, Mohammad Areeb and Nwadike, Munachiso S and Almakky, Ibrahim and Yaqub, Mohammad and Saeed, Numan}, title = {MAFM3: Modular Adaptation of Foundation Models for Multi-Modal Medical AI}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3494-3503} }
4D-Animal: Freely Reconstructing Animatable 3D Animals from Videos: Shanshan Zhong,

Jiawei Peng,

Zehan Zheng,

Zhongzhan Huang,

Wufei Ma,

Guofeng Zhang,

Qihao Liu,

Alan Yuille,

Jieneng Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhong_2026_WACV, author = {Zhong, Shanshan and Peng, Jiawei and Zheng, Zehan and Huang, Zhongzhan and Ma, Wufei and Zhang, Guofeng and Liu, Qihao and Yuille, Alan and Chen, Jieneng}, title = {4D-Animal: Freely Reconstructing Animatable 3D Animals from Videos}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {602-612} }
PVeRA: Probabilistic Vector-Based Random Matrix Adaptation: Leo Fillioux,

Enzo Ferrante,

Paul-Henry Cournède,

Maria Vakalopoulou,

Stergios Christodoulidis; [pdf] [supp]
[bibtex]
@InProceedings{Fillioux_2026_WACV, author = {Fillioux, Leo and Ferrante, Enzo and Courn\`ede, Paul-Henry and Vakalopoulou, Maria and Christodoulidis, Stergios}, title = {PVeRA: Probabilistic Vector-Based Random Matrix Adaptation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2465-2474} }
Rethinking Latent Variable in Learned Image Compression: Fangzhou Yi,

Zhicheng Gong,

Hui Zeng; [pdf] [supp]
[bibtex]
@InProceedings{Yi_2026_WACV, author = {Yi, Fangzhou and Gong, Zhicheng and Zeng, Hui}, title = {Rethinking Latent Variable in Learned Image Compression}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8531-8540} }
Stroke Modeling Enables Vectorized Character Generation with Large Vectorized Glyph Model: Xinyue Zhang,

Haolong Li,

Jiawei Ma,

Chen Ye; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2026_WACV, author = {Zhang, Xinyue and Li, Haolong and Ma, Jiawei and Ye, Chen}, title = {Stroke Modeling Enables Vectorized Character Generation with Large Vectorized Glyph Model}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3401-3410} }
DCText: Scheduled Attention Masking for Visual Text Generation via Divide-and-Conquer Strategy: Jaewoo Song,

Jooyoung Choi,

Kanghyun Baek,

Sangyub Lee,

Daemin Park,

Sungroh Yoon; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Song_2026_WACV, author = {Song, Jaewoo and Choi, Jooyoung and Baek, Kanghyun and Lee, Sangyub and Park, Daemin and Yoon, Sungroh}, title = {DCText: Scheduled Attention Masking for Visual Text Generation via Divide-and-Conquer Strategy}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4305-4314} }
Improved Wildfire Spread Prediction with Time-Series Data and the WSTS+ Benchmark: Saad Lahrichi,

Jake Bova,

Jesse Johnson,

Jordan Malof; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lahrichi_2026_WACV, author = {Lahrichi, Saad and Bova, Jake and Johnson, Jesse and Malof, Jordan}, title = {Improved Wildfire Spread Prediction with Time-Series Data and the WSTS+ Benchmark}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2890-2900} }
CADE: Continual Weakly-supervised Video Anomaly Detection with Ensembles: Satoshi Hashimoto,

Tatsuya Konishi,

Tomoya Kaichi,

Kazunori Matsumoto,

Mori Kurokawa; [pdf] [arXiv]
[bibtex]
@InProceedings{Hashimoto_2026_WACV, author = {Hashimoto, Satoshi and Konishi, Tatsuya and Kaichi, Tomoya and Matsumoto, Kazunori and Kurokawa, Mori}, title = {CADE: Continual Weakly-supervised Video Anomaly Detection with Ensembles}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {708-717} }
DOODLE: Diffusion-based Out-of-Distribution Learning for Open-set LiDAR Semantic Segmentation: Changgyoon Oh,

Hyeonseong Kim,

Daehyun We,

Jongoh Jeong,

Yujeong Chae,

Kuk-Jin Yoon; [pdf] [supp]
[bibtex]
@InProceedings{Oh_2026_WACV, author = {Oh, Changgyoon and Kim, Hyeonseong and We, Daehyun and Jeong, Jongoh and Chae, Yujeong and Yoon, Kuk-Jin}, title = {DOODLE: Diffusion-based Out-of-Distribution Learning for Open-set LiDAR Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2273-2283} }
MUSE: Model-based Uncertainty-aware Similarity Estimation for zero-shot 2D Object Detection and Segmentation: Sungmin Cho,

Sungbum Park,

Insoo Oh; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cho_2026_WACV, author = {Cho, Sungmin and Park, Sungbum and Oh, Insoo}, title = {MUSE: Model-based Uncertainty-aware Similarity Estimation for zero-shot 2D Object Detection and Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6090-6100} }
HistoMILKD: A Multiple Instance Learning based Multi-Teacher Knowledge Distillation Framework for Whole Slide Image Classification: Mayur Mallya,

Ali Khajegili Mirabadi,

Hossein Farahani,

Ali Bashashati; [pdf] [supp]
[bibtex]
@InProceedings{Mallya_2026_WACV, author = {Mallya, Mayur and Mirabadi, Ali Khajegili and Farahani, Hossein and Bashashati, Ali}, title = {HistoMILKD: A Multiple Instance Learning based Multi-Teacher Knowledge Distillation Framework for Whole Slide Image Classification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3390-3400} }
RobustFormer: Noise-Robust Pre-training for Images and Videos: Ashish Bastola,

Nishant Luitel,

Hao Wang,

Danda Pani Paudel,

Roshni Poudel,

Abolfazl Razi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bastola_2026_WACV, author = {Bastola, Ashish and Luitel, Nishant and Wang, Hao and Paudel, Danda Pani and Poudel, Roshni and Razi, Abolfazl}, title = {RobustFormer: Noise-Robust Pre-training for Images and Videos}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2284-2294} }
Modeling and Learning Multiple Hypotheses for Monocular 3D Object Detection: Hyeonjeong Park,

Peixi Xiong,

Pei Yu,

Wei Tang; [pdf] [supp]
[bibtex]
@InProceedings{Park_2026_WACV, author = {Park, Hyeonjeong and Xiong, Peixi and Yu, Pei and Tang, Wei}, title = {Modeling and Learning Multiple Hypotheses for Monocular 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7040-7050} }
Context-Preserving Dermoscopic Editing: Mask-Guided Lesion-Aware Diffusion for Attribute Modification: Tao Sun,

Yun Jiang,

Yarong Jin,

Huanting Guo,

Zequn Zhang; [pdf]
[bibtex]
@InProceedings{Sun_2026_WACV, author = {Sun, Tao and Jiang, Yun and Jin, Yarong and Guo, Huanting and Zhang, Zequn}, title = {Context-Preserving Dermoscopic Editing: Mask-Guided Lesion-Aware Diffusion for Attribute Modification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5364-5373} }
Guided Texture Segmentation via Coordinate-Aware Class-Ratio Mapping: Bishal Ranjan Swain,

Kyung Joo Cheoi,

Jaepil Ko; [pdf]
[bibtex]
@InProceedings{Swain_2026_WACV, author = {Swain, Bishal Ranjan and Cheoi, Kyung Joo and Ko, Jaepil}, title = {Guided Texture Segmentation via Coordinate-Aware Class-Ratio Mapping}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4253-4261} }
SD-CSFL: A Synthetic Data-Driven Conformity Scoring Framework for Robust Federated Learning: Ebtisaam Alharbi,

Abdulrahman Kerim,

Leandro Soriano Marcolino,

Qiang Ni; [pdf] [supp]
[bibtex]
@InProceedings{Alharbi_2026_WACV, author = {Alharbi, Ebtisaam and Kerim, Abdulrahman and Marcolino, Leandro Soriano and Ni, Qiang}, title = {SD-CSFL: A Synthetic Data-Driven Conformity Scoring Framework for Robust Federated Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6903-6912} }
Patch-wise Retrieval: A Bag of Practical Techniques for Instance-level Matching: Wonseok Choi,

Sohwi Lim,

Nam Hyeon-Woo,

Moon Ye-Bin,

Dong-Ju Jeong,

Jinyoung Hwang,

Tae-Hyun Oh; [pdf] [supp]
[bibtex]
@InProceedings{Choi_2026_WACV, author = {Choi, Wonseok and Lim, Sohwi and Hyeon-Woo, Nam and Ye-Bin, Moon and Jeong, Dong-Ju and Hwang, Jinyoung and Oh, Tae-Hyun}, title = {Patch-wise Retrieval: A Bag of Practical Techniques for Instance-level Matching}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4922-4931} }
Reviving Unsupervised Optical Flow: Concept Reevaluation, Multi-Scale Advances and Full Open-Source Release: Azin Jahedi,

Marc Rivinius,

Noah Berenguel Senn,

Andres Bruhn; [pdf] [supp]
[bibtex]
@InProceedings{Jahedi_2026_WACV, author = {Jahedi, Azin and Rivinius, Marc and Senn, Noah Berenguel and Bruhn, Andres}, title = {Reviving Unsupervised Optical Flow: Concept Reevaluation, Multi-Scale Advances and Full Open-Source Release}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1533-1542} }
STARS: Self-supervised Tuning for 3D Action Recognition in Skeleton Sequences: Soroush Mehraban,

Mohammad Javad Rajabi,

Andrea Iaboni,

Babak Taati; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mehraban_2026_WACV, author = {Mehraban, Soroush and Rajabi, Mohammad Javad and Iaboni, Andrea and Taati, Babak}, title = {STARS: Self-supervised Tuning for 3D Action Recognition in Skeleton Sequences}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2858-2868} }
MedROV: Towards Real-Time Open-Vocabulary Detection Across Diverse Medical Imaging Modalities: Tooba Tehreem Sheikh,

Jean Lahoud,

Rao Muhammad Anwer,

Fahad Shahbaz Khan,

Salman Khan,

Hisham Cholakkal; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sheikh_2026_WACV, author = {Sheikh, Tooba Tehreem and Lahoud, Jean and Anwer, Rao Muhammad and Khan, Fahad Shahbaz and Khan, Salman and Cholakkal, Hisham}, title = {MedROV: Towards Real-Time Open-Vocabulary Detection Across Diverse Medical Imaging Modalities}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8628-8638} }
ConsensusXAI: A Framework to Examine Class-wise Agreement in Medical Imaging: Abbas Haider,

David Wright,

Ruth Hogg,

Hui Wang,

Tunde Peto,

Richard Gault; [pdf] [supp]
[bibtex]
@InProceedings{Haider_2026_WACV, author = {Haider, Abbas and Wright, David and Hogg, Ruth and Wang, Hui and Peto, Tunde and Gault, Richard}, title = {ConsensusXAI: A Framework to Examine Class-wise Agreement in Medical Imaging}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2661-2669} }
Towards Unconstrained Cross-View Pose Estimation: Alexander Wollam,

Kyle Ashley,

Maxim Shugaev,

Oliver Arend,

Ilya Semenov,

Hadis Dashtestani,

Sumved Ravi,

Nathan Jacobs; [pdf] [supp]
[bibtex]
@InProceedings{Wollam_2026_WACV, author = {Wollam, Alexander and Ashley, Kyle and Shugaev, Maxim and Arend, Oliver and Semenov, Ilya and Dashtestani, Hadis and Ravi, Sumved and Jacobs, Nathan}, title = {Towards Unconstrained Cross-View Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8448-8457} }
Towards Egocentric 3D Hand Pose Estimation in Unseen Domains: Wiktor Mucha,

Michael Wray,

Martin Kampel; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mucha_2026_WACV, author = {Mucha, Wiktor and Wray, Michael and Kampel, Martin}, title = {Towards Egocentric 3D Hand Pose Estimation in Unseen Domains}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5776-5786} }
Anatomy-VLM: A Fine-grained Vision-Language Model for Medical Interpretation: Difei Gu,

Yunhe Gao,

Mu Zhou,

Dimitris Metaxas; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gu_2026_WACV, author = {Gu, Difei and Gao, Yunhe and Zhou, Mu and Metaxas, Dimitris}, title = {Anatomy-VLM: A Fine-grained Vision-Language Model for Medical Interpretation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2838-2847} }
FocalComm: Hard Instance-Aware Multi-Agent Perception: Dereje Shenkut,

Vijayakumar Bhagavatula; [pdf] [arXiv]
[bibtex]
@InProceedings{Shenkut_2026_WACV, author = {Shenkut, Dereje and Bhagavatula, Vijayakumar}, title = {FocalComm: Hard Instance-Aware Multi-Agent Perception}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6277-6286} }
SeaClips: A Video Dataset for Maritime Object Detection.: Franziska Denk,

Christian Rankl,

Shaban Almouahed,

David Moser,

Robert Sablatnig; [pdf] [supp]
[bibtex]
@InProceedings{Denk_2026_WACV, author = {Denk, Franziska and Rankl, Christian and Almouahed, Shaban and Moser, David and Sablatnig, Robert}, title = {SeaClips: A Video Dataset for Maritime Object Detection.}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4599-4610} }
Video and Language Alignment in 2D Systems for 3D Multi-object Scenes with Multi-Information Derivative-Free Control: Jason Armitage,

Rico Sennrich; [pdf] [supp]
[bibtex]
@InProceedings{Armitage_2026_WACV, author = {Armitage, Jason and Sennrich, Rico}, title = {Video and Language Alignment in 2D Systems for 3D Multi-object Scenes with Multi-Information Derivative-Free Control}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6266-6276} }
AGENet: Adaptive Edge-aware Geodesic Distance Learning for Few-Shot Medical Image Segmentation: Ziyuan Gao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gao_2026_WACV, author = {Gao, Ziyuan}, title = {AGENet: Adaptive Edge-aware Geodesic Distance Learning for Few-Shot Medical Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4285-4294} }
GaussianHeadTalk: Wobble-Free 3D Talking Heads with Audio Driven Gaussian Splatting: Madhav Agarwal,

Mingtian Zhang,

Laura Sevilla-Lara,

Steven McDonagh; [pdf] [supp]
[bibtex]
@InProceedings{Agarwal_2026_WACV, author = {Agarwal, Madhav and Zhang, Mingtian and Sevilla-Lara, Laura and McDonagh, Steven}, title = {GaussianHeadTalk: Wobble-Free 3D Talking Heads with Audio Driven Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8017-8027} }
SVD-Det: A Lightweight Framework for Video Forgery Detection Using Semantic and Visual Defect Cues: Tsung-Shan Yang,

Tianyu Zhang,

Feng Qian,

Bing Yan,

C.-C. Jay Kuo; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2026_WACV, author = {Yang, Tsung-Shan and Zhang, Tianyu and Qian, Feng and Yan, Bing and Kuo, C.-C. Jay}, title = {SVD-Det: A Lightweight Framework for Video Forgery Detection Using Semantic and Visual Defect Cues}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7616-7625} }
milliMamba: Specular-Aware Human Pose Estimation via Dual mmWave Radar with Multi-Frame Mamba Fusion: Niraj Prakash Kini,

Shiau-Rung Tsai,

Guan-Hsun Lin,

Wen-Hsiao Peng,

Ching-Wen Ma,

Jenq-Neng Hwang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kini_2026_WACV, author = {Kini, Niraj Prakash and Tsai, Shiau-Rung and Lin, Guan-Hsun and Peng, Wen-Hsiao and Ma, Ching-Wen and Hwang, Jenq-Neng}, title = {milliMamba: Specular-Aware Human Pose Estimation via Dual mmWave Radar with Multi-Frame Mamba Fusion}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1481-1490} }
One-Cycle Structured Pruning via Stability-Driven Subnetwork Search: Deepak Ghimire,

Dayoung Kil,

Seonghwan Jeong,

Jaesik Park,

Seong-heum Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ghimire_2026_WACV, author = {Ghimire, Deepak and Kil, Dayoung and Jeong, Seonghwan and Park, Jaesik and Kim, Seong-heum}, title = {One-Cycle Structured Pruning via Stability-Driven Subnetwork Search}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5467-5476} }
Hestia: Voxel-Face-Aware Hierarchical Next-Best-View Acquisition for Efficient 3D Reconstruction: Cheng-You Lu,

Zhuoli Zhuang,

Nguyen Thanh Trung Le,

Da Xiao,

Yu-Cheng Chang,

Thomas Do,

Srinath Sridhar,

Chin-Teng Lin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lu_2026_WACV, author = {Lu, Cheng-You and Zhuang, Zhuoli and Le, Nguyen Thanh Trung and Xiao, Da and Chang, Yu-Cheng and Do, Thomas and Sridhar, Srinath and Lin, Chin-Teng}, title = {Hestia: Voxel-Face-Aware Hierarchical Next-Best-View Acquisition for Efficient 3D Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5302-5312} }
MIX-based Foreground and Background Patch Augmentation Guided by Physics and Material Properties for X-ray Detection: Xintong Liu,

Dongliang Chang,

Yujun Tong,

Zhanyu Ma; [pdf]
[bibtex]
@InProceedings{Liu_2026_WACV, author = {Liu, Xintong and Chang, Dongliang and Tong, Yujun and Ma, Zhanyu}, title = {MIX-based Foreground and Background Patch Augmentation Guided by Physics and Material Properties for X-ray Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {977-987} }
SGPMIL: Sparse Gaussian Process Multiple Instance Learning: Andreas Lolos,

Stergios Christodoulidis,

Aris L. Moustakas,

Jose Dolz,

Maria Vakalopoulou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lolos_2026_WACV, author = {Lolos, Andreas and Christodoulidis, Stergios and Moustakas, Aris L. and Dolz, Jose and Vakalopoulou, Maria}, title = {SGPMIL: Sparse Gaussian Process Multiple Instance Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {503-513} }
Beyond Real Weights: Hypercomplex Representations for Stable Quantization: Jawad Ibn Ahad,

Maisha Rahman,

Amrijit Biswas,

Muhammad Rafsan Kabir,

Robin Krambroeckers,

Sifat Momen,

Nabeel Mohammed,

Shafin Rahman; [pdf] [arXiv]
[bibtex]
@InProceedings{Ibn_Ahad_2026_WACV, author = {Ibn Ahad, Jawad and Rahman, Maisha and Biswas, Amrijit and Kabir, Muhammad Rafsan and Krambroeckers, Robin and Momen, Sifat and Mohammed, Nabeel and Rahman, Shafin}, title = {Beyond Real Weights: Hypercomplex Representations for Stable Quantization}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1180-1190} }
Uncertainty-Aware Subset Selection for Robust Visual Explainability under Distribution Shifts: Madhav Gupta,

Vishak Prasad,

Ganesh Ramakrishnan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gupta_2026_WACV, author = {Gupta, Madhav and Prasad, Vishak and Ramakrishnan, Ganesh}, title = {Uncertainty-Aware Subset Selection for Robust Visual Explainability under Distribution Shifts}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1643-1652} }
FastHMR: Accelerating Human Mesh Recovery via Token and Layer Merging with Diffusion Decoding: Soroush Mehraban,

Andrea Iaboni,

Babak Taati; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mehraban_2026_WACV, author = {Mehraban, Soroush and Iaboni, Andrea and Taati, Babak}, title = {FastHMR: Accelerating Human Mesh Recovery via Token and Layer Merging with Diffusion Decoding}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6733-6743} }
See, Think, Learn: A Self-Taught Multimodal Reasoner: Sourabh Sharma,

Sonam Gupta,

Sadbhawna Sadbhawna; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sharma_2026_WACV, author = {Sharma, Sourabh and Gupta, Sonam and Sadbhawna, Sadbhawna}, title = {See, Think, Learn: A Self-Taught Multimodal Reasoner}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8313-8322} }
CSF-Net: Context-Semantic Fusion Network for Large Mask Inpainting: Chae-Yeon Heo,

Yeong-Jun Cho; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Heo_2026_WACV, author = {Heo, Chae-Yeon and Cho, Yeong-Jun}, title = {CSF-Net: Context-Semantic Fusion Network for Large Mask Inpainting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8292-8301} }
Virtually Unrolling the Herculaneum Papyri by Diffeomorphic Spiral Fitting: Paul Henderson; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Henderson_2026_WACV, author = {Henderson, Paul}, title = {Virtually Unrolling the Herculaneum Papyri by Diffeomorphic Spiral Fitting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6401-6411} }
Joint Modeling of Corruption-Driven and Information-Limited Uncertainty for Robust 3D Gaussian Splatting: Zeji Hui,

Amirali Khodadadian Gostar,

WeiQin Chuah,

Alireza Bab-Hadiashar,

Ruwan Tennakoon; [pdf]
[bibtex]
@InProceedings{Hui_2026_WACV, author = {Hui, Zeji and Gostar, Amirali Khodadadian and Chuah, WeiQin and Bab-Hadiashar, Alireza and Tennakoon, Ruwan}, title = {Joint Modeling of Corruption-Driven and Information-Limited Uncertainty for Robust 3D Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {688-697} }
TalkingHeadBench: A Multi-Modal Benchmark & Analysis of Talking-Head DeepFake Detection: Xinqi Xiong,

Prakrut Patel,

Qingyuan Fan,

Amisha Wadhwa,

Sarathy Selvam,

Xiao Guo,

Luchao Qi,

Xiaoming Liu,

Roni Sengupta; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xiong_2026_WACV, author = {Xiong, Xinqi and Patel, Prakrut and Fan, Qingyuan and Wadhwa, Amisha and Selvam, Sarathy and Guo, Xiao and Qi, Luchao and Liu, Xiaoming and Sengupta, Roni}, title = {TalkingHeadBench: A Multi-Modal Benchmark \& Analysis of Talking-Head DeepFake Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4139-4149} }
SOAF: Scene Occlusion-aware Neural Acoustic Field: Huiyu Gao,

Jiahao Ma,

David Ahmedt-Aristizabal,

Chuong Nguyen,

Miaomiao Liu; [pdf] [supp]
[bibtex]
@InProceedings{Gao_2026_WACV, author = {Gao, Huiyu and Ma, Jiahao and Ahmedt-Aristizabal, David and Nguyen, Chuong and Liu, Miaomiao}, title = {SOAF: Scene Occlusion-aware Neural Acoustic Field}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4097-4107} }
Exploring the Boundaries of Diffusion Models for Offline Writer Identification with Sparse and Intra-Variable Data: Aritra Dey,

Chandranath Adak,

Kumari Priya,

Soumi Chattopadhyay,

Sukalpa Chanda; [pdf] [supp]
[bibtex]
@InProceedings{Dey_2026_WACV, author = {Dey, Aritra and Adak, Chandranath and Priya, Kumari and Chattopadhyay, Soumi and Chanda, Sukalpa}, title = {Exploring the Boundaries of Diffusion Models for Offline Writer Identification with Sparse and Intra-Variable Data}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7178-7187} }
QC-SF: Improving Computer Vision for Airborne LiDAR Point Clouds of Boreal Forests with Quebec Simulated Forest Dataset: Olivier Stocker,

Reza Mahmoudi Kouhi,

Omid Reisi Gahrouei,

Thierry Badard,

Eric Guilbert; [pdf] [supp]
[bibtex]
@InProceedings{Stocker_2026_WACV, author = {Stocker, Olivier and Kouhi, Reza Mahmoudi and Gahrouei, Omid Reisi and Badard, Thierry and Guilbert, Eric}, title = {QC-SF: Improving Computer Vision for Airborne LiDAR Point Clouds of Boreal Forests with Quebec Simulated Forest Dataset}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5026-5036} }
Grounding Descriptions in Images informs Zero-Shot Visual Recognition: Shaunak Halbe,

Junjiao Tian,

K J Joseph,

James Seale Smith,

Katherine Stevo,

Vineeth N. Balasubramanian,

Zsolt Kira; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Halbe_2026_WACV, author = {Halbe, Shaunak and Tian, Junjiao and Joseph, K J and Smith, James Seale and Stevo, Katherine and Balasubramanian, Vineeth N. and Kira, Zsolt}, title = {Grounding Descriptions in Images informs Zero-Shot Visual Recognition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5672-5681} }
iMotion-LLM: Instruction-Conditioned Trajectory Generation: Abdulwahab Felemban,

Nussair Hroub,

Jian Ding,

Eslam Abdelrahman,

Xiaoqian Shen,

Abduallah Mohamed,

Mohamed Elhoseiny; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Felemban_2026_WACV, author = {Felemban, Abdulwahab and Hroub, Nussair and Ding, Jian and Abdelrahman, Eslam and Shen, Xiaoqian and Mohamed, Abduallah and Elhoseiny, Mohamed}, title = {iMotion-LLM: Instruction-Conditioned Trajectory Generation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2710-2720} }
Hierarchical Instance Tracking to Balance Privacy Preservation with Accessible Information: Neelima Prasad,

Jarek Reynolds,

Neel Karsanbhai,

Tanusree Sharma,

Lotus Zhang,

Abigale Stangl,

Yang Wang,

Leah Findlater,

Danna Gurari; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Prasad_2026_WACV, author = {Prasad, Neelima and Reynolds, Jarek and Karsanbhai, Neel and Sharma, Tanusree and Zhang, Lotus and Stangl, Abigale and Wang, Yang and Findlater, Leah and Gurari, Danna}, title = {Hierarchical Instance Tracking to Balance Privacy Preservation with Accessible Information}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5945-5955} }
Inpaint360GS: Efficient Object-Aware 3D Inpainting via Gaussian Splatting for 360deg Scenes: Shaoxiang Wang,

Shihong Zhang,

Christen Millerdurai,

Rüdiger Westermann,

Didier Stricker,

Alain Pagani; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2026_WACV, author = {Wang, Shaoxiang and Zhang, Shihong and Millerdurai, Christen and Westermann, R\"udiger and Stricker, Didier and Pagani, Alain}, title = {Inpaint360GS: Efficient Object-Aware 3D Inpainting via Gaussian Splatting for 360deg Scenes}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {117-127} }
Model-free Domain Adaptation for Concealed Multimodal Large-Language Models: Yu Mitsuzumi,

Akisato Kimura,

Hisashi Kashima; [pdf] [supp]
[bibtex]
@InProceedings{Mitsuzumi_2026_WACV, author = {Mitsuzumi, Yu and Kimura, Akisato and Kashima, Hisashi}, title = {Model-free Domain Adaptation for Concealed Multimodal Large-Language Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1231-1241} }
Photo Dating by Facial Age Aggregation: Jakub Paplhám,

Vojtěch Franc; [pdf] [supp]
[bibtex]
@InProceedings{Paplham_2026_WACV, author = {Paplh\'am, Jakub and Franc, Vojt\v{e}ch}, title = {Photo Dating by Facial Age Aggregation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8103-8112} }
Test-Time Consistency in Vision Language Models: Shih-Han Chou,

Shivam Chandhok,

James J. Little,

Leonid Sigal; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chou_2026_WACV, author = {Chou, Shih-Han and Chandhok, Shivam and Little, James J. and Sigal, Leonid}, title = {Test-Time Consistency in Vision Language Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7789-7798} }
CSGaussian: Progressive Rate-Distortion Compression and Segmentation for 3D Gaussian Splatting: Yu-Jen Tseng,

Chia-Hao Kao,

Jing-Zhong Chen,

Alessandro Gnutti,

Shao-Yuan Lo,

Yen-Yu Lin,

Wen-Hsiao Peng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tseng_2026_WACV, author = {Tseng, Yu-Jen and Kao, Chia-Hao and Chen, Jing-Zhong and Gnutti, Alessandro and Lo, Shao-Yuan and Lin, Yen-Yu and Peng, Wen-Hsiao}, title = {CSGaussian: Progressive Rate-Distortion Compression and Segmentation for 3D Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6883-6892} }
Conversational Image Generation: Towards Multi-Round Personalized Generation with Multi-Modal Language Models: Haochen Zhang,

Animesh Sinha,

Felix Juefei-Xu,

Haoyu Ma,

Kunpeng Li,

Zhipeng Fan,

Xiaoliang Dai,

Tingbo Hou,

Peizhao Zhang,

Zecheng He; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2026_WACV, author = {Zhang, Haochen and Sinha, Animesh and Juefei-Xu, Felix and Ma, Haoyu and Li, Kunpeng and Fan, Zhipeng and Dai, Xiaoliang and Hou, Tingbo and Zhang, Peizhao and He, Zecheng}, title = {Conversational Image Generation: Towards Multi-Round Personalized Generation with Multi-Modal Language Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8282-8291} }
PhyEduVideo: A Benchmark for Evaluating Text-to-Video Models for Physics Education: Megha Mariam K.M,

Aditya Arun,

Zakaria Laskar,

C.V. Jawahar; [pdf] [supp]
[bibtex]
@InProceedings{K.M_2026_WACV, author = {K.M, Megha Mariam and Arun, Aditya and Laskar, Zakaria and Jawahar, C.V.}, title = {PhyEduVideo: A Benchmark for Evaluating Text-to-Video Models for Physics Education}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8690-8699} }
PEaRL: Pathway-Enhanced Representation Learning for Gene and Pathway Expression Prediction from Histology: Sejuti Majumder,

Saarthak Kapse,

Moinak Bhattacharya,

Xuan Xu,

Alisa Yurovsky,

Prateek Prasanna; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Majumder_2026_WACV, author = {Majumder, Sejuti and Kapse, Saarthak and Bhattacharya, Moinak and Xu, Xuan and Yurovsky, Alisa and Prasanna, Prateek}, title = {PEaRL: Pathway-Enhanced Representation Learning for Gene and Pathway Expression Prediction from Histology}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8052-8062} }
Automated Pore Detection from In-Situ FDM 3D Printing Video: A Comparative Evaluation of Modern Segmentation Models: Abdullah Al Ahad Khan,

Md Shariful Islam,

Lin Li,

Lai Jiang,

Noushin Ghaffari; [pdf]
[bibtex]
@InProceedings{Al_Ahad_Khan_2026_WACV, author = {Al Ahad Khan, Abdullah and Islam, Md Shariful and Li, Lin and Jiang, Lai and Ghaffari, Noushin}, title = {Automated Pore Detection from In-Situ FDM 3D Printing Video: A Comparative Evaluation of Modern Segmentation Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4673-4681} }
AD2: Analysis and Detection of Adversarial Threats in Visual Perception for End-to-End Autonomous Driving Systems: Ishan Sahu,

Somnath Hazra,

Somak Aditya,

Soumyajit Dey; [pdf] [supp]
[bibtex]
@InProceedings{Sahu_2026_WACV, author = {Sahu, Ishan and Hazra, Somnath and Aditya, Somak and Dey, Soumyajit}, title = {AD2: Analysis and Detection of Adversarial Threats in Visual Perception for End-to-End Autonomous Driving Systems}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1695-1704} }
FastPose-ViT: A Vision Transformer for Real-Time Spacecraft Pose Estimation: Pierre Ancey,

Andrew Price,

Saqib Javed,

Mathieu Salzmann; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ancey_2026_WACV, author = {Ancey, Pierre and Price, Andrew and Javed, Saqib and Salzmann, Mathieu}, title = {FastPose-ViT: A Vision Transformer for Real-Time Spacecraft Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7873-7882} }
BiPO: Bidirectional Partial Occlusion Network for Text-to-Motion Synthesis: Seong-Eun Hong,

SooBin Lim,

JuYeong Hwang,

Minwook Chang,

HyeongYeop Kang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hong_2026_WACV, author = {Hong, Seong-Eun and Lim, SooBin and Hwang, JuYeong and Chang, Minwook and Kang, HyeongYeop}, title = {BiPO: Bidirectional Partial Occlusion Network for Text-to-Motion Synthesis}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {32-42} }
Improvise, Adapt, Overcome -- Telescopic Adapters for Efficient Fine-tuning of Vision Language Models in Medical Imaging: Ujjwal Mishra,

Vinita Shukla,

Praful Hambarde,

Amit Shukla; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mishra_2026_WACV, author = {Mishra, Ujjwal and Shukla, Vinita and Hambarde, Praful and Shukla, Amit}, title = {Improvise, Adapt, Overcome -- Telescopic Adapters for Efficient Fine-tuning of Vision Language Models in Medical Imaging}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7605-7615} }
How I Met Your Bias: Investigating Bias Amplification in Diffusion Models: Nathan Roos,

Ekaterina Iakovleva,

Ani Gjergji,

Vito Paolo Pastore,

Enzo Tartaglione; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Roos_2026_WACV, author = {Roos, Nathan and Iakovleva, Ekaterina and Gjergji, Ani and Pastore, Vito Paolo and Tartaglione, Enzo}, title = {How I Met Your Bias: Investigating Bias Amplification in Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5374-5383} }
Color Bind: Exploring Color Perception in Text-to-Image Models: Shay Shomer-Chai,

Wenxuan Peng,

Bharath Hariharan,

Hadar Averbuch-Elor; [pdf] [supp]
[bibtex]
@InProceedings{Shomer-Chai_2026_WACV, author = {Shomer-Chai, Shay and Peng, Wenxuan and Hariharan, Bharath and Averbuch-Elor, Hadar}, title = {Color Bind: Exploring Color Perception in Text-to-Image Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1916-1925} }
Learning Subglacial Bed Topography from Sparse Radar with Physics-Guided Residuals: Bayu Adhi Tama,

Jianwu Wang,

Vandana Janeja,

Mostafa Cham; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tama_2026_WACV, author = {Tama, Bayu Adhi and Wang, Jianwu and Janeja, Vandana and Cham, Mostafa}, title = {Learning Subglacial Bed Topography from Sparse Radar with Physics-Guided Residuals}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5447-5456} }
From Lightweight CNNs to SpikeNets: Benchmarking Accuracy-Energy Tradeoffs with Pruned Spiking SqueezeNet: Radib Bin Kabir,

Tawsif Tashwar Dipto,

Mehedi Ahamed,

Sabbir Ahmed,

Md Hasanul Kabir; [pdf] [arXiv]
[bibtex]
@InProceedings{Bin_Kabir_2026_WACV, author = {Bin Kabir, Radib and Dipto, Tawsif Tashwar and Ahamed, Mehedi and Ahmed, Sabbir and Kabir, Md Hasanul}, title = {From Lightweight CNNs to SpikeNets: Benchmarking Accuracy-Energy Tradeoffs with Pruned Spiking SqueezeNet}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1137-1146} }
Zero-LEAD: Source-Free Universal Domain Adaptation for Abdominal Multi-Organ Segmentation: Ahmed El-Sayed,

Marwan Torki; [pdf]
[bibtex]
@InProceedings{El-Sayed_2026_WACV, author = {El-Sayed, Ahmed and Torki, Marwan}, title = {Zero-LEAD: Source-Free Universal Domain Adaptation for Abdominal Multi-Organ Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6715-6723} }
Cross-Modal Event Encoder: Bridging Image-Text Knowledge to Event Streams: Sungheon Jeong,

Hanning Chen,

Sanggeon Yun,

Suhyeon Cho,

Wenjun Huang,

Xiangjian Liu,

Mohsen Imani; [pdf] [supp]
[bibtex]
@InProceedings{Jeong_2026_WACV, author = {Jeong, Sungheon and Chen, Hanning and Yun, Sanggeon and Cho, Suhyeon and Huang, Wenjun and Liu, Xiangjian and Imani, Mohsen}, title = {Cross-Modal Event Encoder: Bridging Image-Text Knowledge to Event Streams}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3213-3222} }
Dual-Domain Multimodal Hyperbolic Fusion for Cardiopulmonary Disease Diagnosis in Emergency Care: Ke Nan,

Maggie Samaan,

Benjamin Burns,

Xia Ning,

Yuchi Han,

Yuan Xue; [pdf]
[bibtex]
@InProceedings{Nan_2026_WACV, author = {Nan, Ke and Samaan, Maggie and Burns, Benjamin and Ning, Xia and Han, Yuchi and Xue, Yuan}, title = {Dual-Domain Multimodal Hyperbolic Fusion for Cardiopulmonary Disease Diagnosis in Emergency Care}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8700-8710} }
Procedure Learning via Regularized Gromov-Wasserstein Optimal Transport: Syed Ahmed Mahmood,

Ali Shah Ali,

Umer Ahmed,

Fawad Javed Fateh,

M. Zeeshan Zia,

Quoc-Huy Tran; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mahmood_2026_WACV, author = {Mahmood, Syed Ahmed and Ali, Ali Shah and Ahmed, Umer and Fateh, Fawad Javed and Zia, M. Zeeshan and Tran, Quoc-Huy}, title = {Procedure Learning via Regularized Gromov-Wasserstein Optimal Transport}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6925-6935} }
PDV: Prompt Directional Vectors for Zero-shot Composed Image Retrieval: Osman Tursun,

Sinan Kalkan,

Simon Denman,

Clinton Fookes; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tursun_2026_WACV, author = {Tursun, Osman and Kalkan, Sinan and Denman, Simon and Fookes, Clinton}, title = {PDV: Prompt Directional Vectors for Zero-shot Composed Image Retrieval}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7740-7749} }
Any Detector Can Detect Anything: Thomas E. Huang,

Siyuan Li,

Martin Danelljan,

Henghui Ding,

Luc Van Gool,

Fisher Yu; [pdf] [supp]
[bibtex]
@InProceedings{Huang_2026_WACV, author = {Huang, Thomas E. and Li, Siyuan and Danelljan, Martin and Ding, Henghui and Van Gool, Luc and Yu, Fisher}, title = {Any Detector Can Detect Anything}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8437-8447} }
Automated Suturing Skill Assessment in Robot-assisted Surgery from Endoscopic Videos using Clinically-guided Evaluation Criteria: Atharva Sunil Deo,

Ujjwal Pasupulety,

Nicholas Matsumoto,

Jay Moran,

Cherine Yang,

Jeanine Kim,

Rafal Dariusz Kocielnik,

Aurash Naser-Tavakolian,

Andrew Hung; [pdf]
[bibtex]
@InProceedings{Deo_2026_WACV, author = {Deo, Atharva Sunil and Pasupulety, Ujjwal and Matsumoto, Nicholas and Moran, Jay and Yang, Cherine and Kim, Jeanine and Kocielnik, Rafal Dariusz and Naser-Tavakolian, Aurash and Hung, Andrew}, title = {Automated Suturing Skill Assessment in Robot-assisted Surgery from Endoscopic Videos using Clinically-guided Evaluation Criteria}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7218-7228} }
Efficient Text-Guided Convolutional Adapter for the Diffusion Model: Aryan Das,

Koushik Biswas,

Swalpa Kumar Roy,

Badri Narayana Patro,

Vinay Kumar Verma; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Das_2026_WACV, author = {Das, Aryan and Biswas, Koushik and Roy, Swalpa Kumar and Patro, Badri Narayana and Verma, Vinay Kumar}, title = {Efficient Text-Guided Convolutional Adapter for the Diffusion Model}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4015-4024} }
Enhancing Object Detection Training via Joint Image-Annotation Generation: Roy Uziel,

Oded Bialer; [pdf] [supp]
[bibtex]
@InProceedings{Uziel_2026_WACV, author = {Uziel, Roy and Bialer, Oded}, title = {Enhancing Object Detection Training via Joint Image-Annotation Generation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1736-1745} }
Direct Visual Grounding by Directing Attention of Visual Tokens: Parsa Esmaeilkhani,

Longin Jan Latecki; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Esmaeilkhani_2026_WACV, author = {Esmaeilkhani, Parsa and Latecki, Longin Jan}, title = {Direct Visual Grounding by Directing Attention of Visual Tokens}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5787-5797} }
Anatomically-guided Masked Autoencoder Pre-training for Aneurysm Detection: Alberto M. Ceballos Arroyo,

Jisoo Kim,

Chu-Hsuan Lin,

Lei Qin,

Geoffrey S. Young,

Huaizu Jiang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Arroyo_2026_WACV, author = {Arroyo, Alberto M. Ceballos and Kim, Jisoo and Lin, Chu-Hsuan and Qin, Lei and Young, Geoffrey S. and Jiang, Huaizu}, title = {Anatomically-guided Masked Autoencoder Pre-training for Aneurysm Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5693-5702} }
DreamAnywhere: Object-Centric Panoramic 3D Scene Generation: Edoardo A. Dominici,

Jozef Hladký,

Floor Verhoeven,

Lukas Radl,

Thomas Deixelberger,

Stefan Ainetter,

Philipp Drescher,

Stefan Hauswiesner,

Arno Coomans,

Giacomo Nazzaro,

Konstantinos Vardis,

Markus Steinberger; [pdf] [supp]
[bibtex]
@InProceedings{Dominici_2026_WACV, author = {Dominici, Edoardo A. and Hladk\'y, Jozef and Verhoeven, Floor and Radl, Lukas and Deixelberger, Thomas and Ainetter, Stefan and Drescher, Philipp and Hauswiesner, Stefan and Coomans, Arno and Nazzaro, Giacomo and Vardis, Konstantinos and Steinberger, Markus}, title = {DreamAnywhere: Object-Centric Panoramic 3D Scene Generation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1-11} }
Polymorph: Energy-Efficient Multi-Label Classification for Video Streams on Embedded Devices: Saeid Ghafouri,

Mohsen Fayyaz,

Xiangchen Li,

Deepu John,

Bo Ji,

Dimitrios S. Nikolopoulos,

Hans Vandierendonck; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ghafouri_2026_WACV, author = {Ghafouri, Saeid and Fayyaz, Mohsen and Li, Xiangchen and John, Deepu and Ji, Bo and Nikolopoulos, Dimitrios S. and Vandierendonck, Hans}, title = {Polymorph: Energy-Efficient Multi-Label Classification for Video Streams on Embedded Devices}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6432-6441} }
KD360-VoxelBEV: LiDAR and 360-degree Camera Cross Modality Knowledge Distillation for Bird's-Eye-View Segmentation: Wenke E,

Yixin Sun,

Jiaxu Liu,

Hubert P. H. Shum,

Amir Atapour-Abarghouei,

Toby P. Breckon; [pdf] [supp]
[bibtex]
@InProceedings{E_2026_WACV, author = {E, Wenke and Sun, Yixin and Liu, Jiaxu and Shum, Hubert P. H. and Atapour-Abarghouei, Amir and Breckon, Toby P.}, title = {KD360-VoxelBEV: LiDAR and 360-degree Camera Cross Modality Knowledge Distillation for Bird's-Eye-View Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3483-3493} }
WSSSP-Net: Weakly Supervised Semantic Segmentation Plugin Network for Face Anti-Spoofing: Krzysztof Galus,

Piotr Syga,

Piotr Kawa; [pdf] [supp]
[bibtex]
@InProceedings{Galus_2026_WACV, author = {Galus, Krzysztof and Syga, Piotr and Kawa, Piotr}, title = {WSSSP-Net: Weakly Supervised Semantic Segmentation Plugin Network for Face Anti-Spoofing}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5247-5257} }
DiT-VTON: Diffusion Transformer Framework for Unified Multi-Category Virtual Try-On and Virtual Try-All with Integrated Image Editing: Qi Li,

Shuwen Qiu,

Kee Kiat Koo,

Julien Han,

Karim Bouyarmane; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2026_WACV, author = {Li, Qi and Qiu, Shuwen and Koo, Kee Kiat and Han, Julien and Bouyarmane, Karim}, title = {DiT-VTON: Diffusion Transformer Framework for Unified Multi-Category Virtual Try-On and Virtual Try-All with Integrated Image Editing}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {202-211} }
VectorSynth: Fine-Grained Satellite Image Synthesis with Structured Semantics: Daniel Cher,

Brian Wei,

Srikumar Sastry,

Nathan Jacobs; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cher_2026_WACV, author = {Cher, Daniel and Wei, Brian and Sastry, Srikumar and Jacobs, Nathan}, title = {VectorSynth: Fine-Grained Satellite Image Synthesis with Structured Semantics}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7019-7029} }
FlowEO: Generative Unsupervised Domain Adaptation for Earth Observation: Georges Le Bellier,

Nicolas Audebert; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Le_Bellier_2026_WACV, author = {Le Bellier, Georges and Audebert, Nicolas}, title = {FlowEO: Generative Unsupervised Domain Adaptation for Earth Observation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3900-3907} }
Pose-Diverse Multi-View Virtual Try-on from a Single Frontal Image via Diffusion Transformer: Seonghee Han,

Minchang Chung,

Gyeongsu Cho,

Kyungdon Joo,

Taehwan Kim; [pdf] [supp]
[bibtex]
@InProceedings{Han_2026_WACV, author = {Han, Seonghee and Chung, Minchang and Cho, Gyeongsu and Joo, Kyungdon and Kim, Taehwan}, title = {Pose-Diverse Multi-View Virtual Try-on from a Single Frontal Image via Diffusion Transformer}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3310-3319} }
ObjectMeshDeform : Towards Recovering Precise 3D Geometry of Real Objects via Image-guided Mesh Deformation of 3D Generative Priors: Siddharth Katageri,

Sanjana Sinha,

Sourav Ghosh,

Soumyadip Maity,

Brojeshwar Bhowmick; [pdf] [supp]
[bibtex]
@InProceedings{Katageri_2026_WACV, author = {Katageri, Siddharth and Sinha, Sanjana and Ghosh, Sourav and Maity, Soumyadip and Bhowmick, Brojeshwar}, title = {ObjectMeshDeform : Towards Recovering Precise 3D Geometry of Real Objects via Image-guided Mesh Deformation of 3D Generative Priors}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2585-2595} }
Cluster-based Pseudo-labeling for Semi-Supervised LiDAR Semantic Segmentation: Qingju Guo,

Shuang Li,

Jing Geng,

Binhui Xie,

Jiawei Shan,

Wei Li; [pdf] [supp]
[bibtex]
@InProceedings{Guo_2026_WACV, author = {Guo, Qingju and Li, Shuang and Geng, Jing and Xie, Binhui and Shan, Jiawei and Li, Wei}, title = {Cluster-based Pseudo-labeling for Semi-Supervised LiDAR Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {623-634} }
Memory-Augmented Representation for Efficient Event-based Visuomotor Policy Learning with Adaptive Perception and Control: Uday Kamal,

Saibal Mukhopadhyay; [pdf]
[bibtex]
@InProceedings{Kamal_2026_WACV, author = {Kamal, Uday and Mukhopadhyay, Saibal}, title = {Memory-Augmented Representation for Efficient Event-based Visuomotor Policy Learning with Adaptive Perception and Control}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2596-2605} }
DiffRegCD: Integrated Registration and Change Detection with Diffusion Features: Seyedehanita Madani,

Rama Chellappa,

Vishal M. Patel; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Madani_2026_WACV, author = {Madani, Seyedehanita and Chellappa, Rama and Patel, Vishal M.}, title = {DiffRegCD: Integrated Registration and Change Detection with Diffusion Features}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7503-7512} }
LangPose: Language-Aligned Motion for Robust 3D Human Pose Estimation: Longyun Liao,

Rong Zheng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liao_2026_WACV, author = {Liao, Longyun and Zheng, Rong}, title = {LangPose: Language-Aligned Motion for Robust 3D Human Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8073-8083} }
Accelerated Dose Generation in Gamma Knife Radiosurgery Using a Wavelet Diffusion Model for Sparse Representation: Sangyoon Lee,

Shubuendu Mishra,

Yoichi Watanabe; [pdf] [supp]
[bibtex]
@InProceedings{Lee_2026_WACV, author = {Lee, Sangyoon and Mishra, Shubuendu and Watanabe, Yoichi}, title = {Accelerated Dose Generation in Gamma Knife Radiosurgery Using a Wavelet Diffusion Model for Sparse Representation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {917-926} }
Lorentz Entailment Cone for Semantic Segmentation: Zahid Hasan,

Masud Ahmed,

Nirmalya Roy; [pdf] [supp]
[bibtex]
@InProceedings{Hasan_2026_WACV, author = {Hasan, Zahid and Ahmed, Masud and Roy, Nirmalya}, title = {Lorentz Entailment Cone for Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5216-5225} }
Can We Challenge Open-Vocabulary Object Detectors with Generated Content in Street Scenes?: Annika Mütze,

Sadia Ilyas,

Christian Dörpelkus,

Matthias Rottmann; [pdf] [supp]
[bibtex]
@InProceedings{Mutze_2026_WACV, author = {M\"utze, Annika and Ilyas, Sadia and D\"orpelkus, Christian and Rottmann, Matthias}, title = {Can We Challenge Open-Vocabulary Object Detectors with Generated Content in Street Scenes?}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {740-750} }
Lose Your Self (LoYS): An Adversarial Entropy-based Unsupervised Approach for Model Debiasing: Vito Paolo Pastore,

Massimiliano Ciranni,

Vittorio Murino; [pdf] [supp]
[bibtex]
@InProceedings{Pastore_2026_WACV, author = {Pastore, Vito Paolo and Ciranni, Massimiliano and Murino, Vittorio}, title = {Lose Your Self (LoYS): An Adversarial Entropy-based Unsupervised Approach for Model Debiasing}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5714-5723} }
Autocorrelation-based Fiducial Markers for Traceability: Ismail Bencheikh,

Max Dunitz,

Marie d'Autume,

Enric Meinhardt-Llopis,

Marc Pic,

Gabriele Facciolo,

Pablo Musé; [pdf] [supp]
[bibtex]
@InProceedings{Bencheikh_2026_WACV, author = {Bencheikh, Ismail and Dunitz, Max and d'Autume, Marie and Meinhardt-Llopis, Enric and Pic, Marc and Facciolo, Gabriele and Mus\'e, Pablo}, title = {Autocorrelation-based Fiducial Markers for Traceability}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1345-1354} }
AutoSew: A Geometric Approach to Stitching Prediction with Graph Neural Networks: Pablo Ríos-Navarro,

Elena Garces,

Jorge Lopez-Moreno; [pdf] [supp]
[bibtex]
@InProceedings{Rios-Navarro_2026_WACV, author = {R{\'\i}os-Navarro, Pablo and Garces, Elena and Lopez-Moreno, Jorge}, title = {AutoSew: A Geometric Approach to Stitching Prediction with Graph Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1374-1383} }
Color Preserving CMOS-SPAD Fusion for Multi-Frame HDR: Aleksi Suonsivu,

Lauri Salmela,

Lassi Helin,

Leevi Uosukainen,

Giacomo Boracchi; [pdf]
[bibtex]
@InProceedings{Suonsivu_2026_WACV, author = {Suonsivu, Aleksi and Salmela, Lauri and Helin, Lassi and Uosukainen, Leevi and Boracchi, Giacomo}, title = {Color Preserving CMOS-SPAD Fusion for Multi-Frame HDR}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5100-5109} }
CLIP-UP: CLIP-Based Unanswerable Problem Detection for Visual Question Answering: Ben Vardi,

Oron Nir,

Ariel Shamir; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Vardi_2026_WACV, author = {Vardi, Ben and Nir, Oron and Shamir, Ariel}, title = {CLIP-UP: CLIP-Based Unanswerable Problem Detection for Visual Question Answering}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5898-5908} }
BoxSplitGen: A Generative Model for 3D Part Bounding Boxes in Varying Granularity: Juil Koo,

Wei-Tung Lin,

Chanho Park,

Chanhyeok Park,

Minhyuk Sung; [pdf] [supp]
[bibtex]
@InProceedings{Koo_2026_WACV, author = {Koo, Juil and Lin, Wei-Tung and Park, Chanho and Park, Chanhyeok and Sung, Minhyuk}, title = {BoxSplitGen: A Generative Model for 3D Part Bounding Boxes in Varying Granularity}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1777-1787} }
Beyond Paired Data: Self-Supervised UAV Geo-Localization from Reference Imagery Alone: Tristan Amadei,

Enric Meinhardt-Llopis,

Benedicte Bascle,

Corentin Abgrall,

Gabriele Facciolo; [pdf] [supp]
[bibtex]
@InProceedings{Amadei_2026_WACV, author = {Amadei, Tristan and Meinhardt-Llopis, Enric and Bascle, Benedicte and Abgrall, Corentin and Facciolo, Gabriele}, title = {Beyond Paired Data: Self-Supervised UAV Geo-Localization from Reference Imagery Alone}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7409-7419} }
Improving Animal Pose Estimation through Species Similarity Measures and Rigorous Label Definition: Medhashree Parhy,

Shaan Chanchani,

Claire Kim,

Josh Mansky,

Zian Pan,

Parth Thakre,

Haoyu Chen,

Amy R. Reibman; [pdf] [supp]
[bibtex]
@InProceedings{Parhy_2026_WACV, author = {Parhy, Medhashree and Chanchani, Shaan and Kim, Claire and Mansky, Josh and Pan, Zian and Thakre, Parth and Chen, Haoyu and Reibman, Amy R.}, title = {Improving Animal Pose Estimation through Species Similarity Measures and Rigorous Label Definition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5662-5671} }
Training-Free Few-Shot Segmentation via Vision-Language Guided Prompting: Euihyun Yoon,

Taejin Park,

Jaekoo Lee; [pdf]
[bibtex]
@InProceedings{Yoon_2026_WACV, author = {Yoon, Euihyun and Park, Taejin and Lee, Jaekoo}, title = {Training-Free Few-Shot Segmentation via Vision-Language Guided Prompting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6517-6526} }
SynchroRaMa : Lip-Synchronized and Emotion-Aware Talking Face Generation via Multi-Modal Emotion Embedding: Phyo Thet Yee,

Dimitrios Kollias,

Sudeepta Mishra,

Abhinav Dhall; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yee_2026_WACV, author = {Yee, Phyo Thet and Kollias, Dimitrios and Mishra, Sudeepta and Dhall, Abhinav}, title = {SynchroRaMa : Lip-Synchronized and Emotion-Aware Talking Face Generation via Multi-Modal Emotion Embedding}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4546-4555} }
HDR Reconstruction Boosting with Training-Free and Exposure-Consistent Diffusion: Yo-Tin Lin,

Su-Kai Chen,

Hou-Ning Hu,

Yen-Yu Lin,

Yu-Lun Liu; [pdf] [supp]
[bibtex]
@InProceedings{Lin_2026_WACV, author = {Lin, Yo-Tin and Chen, Su-Kai and Hu, Hou-Ning and Lin, Yen-Yu and Liu, Yu-Lun}, title = {HDR Reconstruction Boosting with Training-Free and Exposure-Consistent Diffusion}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7513-7523} }
Exploring Automated Recognition of Instructional Activity and Discourse from Multimodal Classroom Data: Ivo Bueno,

Ruikun Hou,

Babette Bühler,

Tim Fütterer,

James Drimalla,

Jonathan K. Foster,

Peter Youngs,

Peter Gerjets,

Ulrich Trautwein,

Enkelejda Kasneci; [pdf] [supp]
[bibtex]
@InProceedings{Bueno_2026_WACV, author = {Bueno, Ivo and Hou, Ruikun and B\"uhler, Babette and F\"utterer, Tim and Drimalla, James and Foster, Jonathan K. and Youngs, Peter and Gerjets, Peter and Trautwein, Ulrich and Kasneci, Enkelejda}, title = {Exploring Automated Recognition of Instructional Activity and Discourse from Multimodal Classroom Data}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6806-6817} }
GeoHSAF: Geometric Hippocampus Shape Analysis Framework for Longitudinal Alzheimer's Disease Classification: Mubarak Olaoluwa,

Heni Loukil,

Arafet Sbei,

Hassen Drira; [pdf] [supp]
[bibtex]
@InProceedings{Olaoluwa_2026_WACV, author = {Olaoluwa, Mubarak and Loukil, Heni and Sbei, Arafet and Drira, Hassen}, title = {GeoHSAF: Geometric Hippocampus Shape Analysis Framework for Longitudinal Alzheimer's Disease Classification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2156-2167} }
Power of Boundary and Reflection: Semantic Transparent Object Segmentation using Pyramid Vision Transformer with Transparent Cues: Tuan-Anh Vu,

Hai Nguyen-Truong,

Ziqiang Zheng,

Binh-Son Hua,

Qing Guo,

Ivor W. Tsang,

Sai-Kit Yeung; [pdf] [supp]
[bibtex]
@InProceedings{Vu_2026_WACV, author = {Vu, Tuan-Anh and Nguyen-Truong, Hai and Zheng, Ziqiang and Hua, Binh-Son and Guo, Qing and Tsang, Ivor W. and Yeung, Sai-Kit}, title = {Power of Boundary and Reflection: Semantic Transparent Object Segmentation using Pyramid Vision Transformer with Transparent Cues}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3360-3369} }
SCAdapter: Content-Style Disentanglement for Diffusion Style Transfer: Luan Thanh Trinh; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Trinh_2026_WACV, author = {Trinh, Luan Thanh}, title = {SCAdapter: Content-Style Disentanglement for Diffusion Style Transfer}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7312-7321} }
Equivariant Sampling for Improving Diffusion Model-based Image Restoration: Chenxu Wu,

Qingpeng Kong,

Peiang Zhao,

Wendi Yang,

Wenxin Ma,

Fenghe Tang,

Zihang Jiang,

S.Kevin Zhou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2026_WACV, author = {Wu, Chenxu and Kong, Qingpeng and Zhao, Peiang and Yang, Wendi and Ma, Wenxin and Tang, Fenghe and Jiang, Zihang and Zhou, S.Kevin}, title = {Equivariant Sampling for Improving Diffusion Model-based Image Restoration}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6827-6839} }
Generalization of Real World Video Deblurring By Image-to-Image Translation: Kassymzhomart Aitbek,

Seungjoon Yang; [pdf] [supp]
[bibtex]
@InProceedings{Aitbek_2026_WACV, author = {Aitbek, Kassymzhomart and Yang, Seungjoon}, title = {Generalization of Real World Video Deblurring By Image-to-Image Translation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4705-4714} }
CRISP: Cylindrical Rendering for In-Stream Point Clouds: Hyungwoo Kang,

Seonyoung Jang,

Yeojun Yoon,

Byung Tae Oh; [pdf] [supp]
[bibtex]
@InProceedings{Kang_2026_WACV, author = {Kang, Hyungwoo and Jang, Seonyoung and Yoon, Yeojun and Oh, Byung Tae}, title = {CRISP: Cylindrical Rendering for In-Stream Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5550-5559} }
ProSkill: Segment-Level Skill Assessment in Procedural Videos: Michele Mazzamuto,

Daniele Di Mauro,

Gianpiero Francesca,

Giovanni Maria Farinella,

Antonino Furnari; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mazzamuto_2026_WACV, author = {Mazzamuto, Michele and Di Mauro, Daniele and Francesca, Gianpiero and Farinella, Giovanni Maria and Furnari, Antonino}, title = {ProSkill: Segment-Level Skill Assessment in Procedural Videos}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4849-4858} }
SilverLining: Data-First Mitigation of Spatial and Spectral Shortcuts Without Introducing New Confounders: Balagopal Unnikrishnan,

Michael Brudno,

Chris McIntosh; [pdf] [supp]
[bibtex]
@InProceedings{Unnikrishnan_2026_WACV, author = {Unnikrishnan, Balagopal and Brudno, Michael and McIntosh, Chris}, title = {SilverLining: Data-First Mitigation of Spatial and Spectral Shortcuts Without Introducing New Confounders}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1294-1303} }
Real-Time Tracking of Flexible Markers in Low-Contrast Fluoroscopy Using a Deep Neural Network Trained Solely on Synthetic Data: Tomoki Uchiyama,

Yukinobu Sakata,

Ryusuke Hirai,

Hitoshi Ishikawa,

Shinichiro Mori; [pdf] [supp]
[bibtex]
@InProceedings{Uchiyama_2026_WACV, author = {Uchiyama, Tomoki and Sakata, Yukinobu and Hirai, Ryusuke and Ishikawa, Hitoshi and Mori, Shinichiro}, title = {Real-Time Tracking of Flexible Markers in Low-Contrast Fluoroscopy Using a Deep Neural Network Trained Solely on Synthetic Data}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2670-2679} }
Ordinal-Aware Multimodal Engagement Recognition for Collaborative Learning: Nha Tran,

Dat Ly,

Phi Ta,

Hung Nguyen,

Hien D. Nguyen; [pdf] [supp]
[bibtex]
@InProceedings{Tran_2026_WACV, author = {Tran, Nha and Ly, Dat and Ta, Phi and Nguyen, Hung and Nguyen, Hien D.}, title = {Ordinal-Aware Multimodal Engagement Recognition for Collaborative Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2424-2433} }
AuViRe: Audio-visual Speech Representation Reconstruction for Deepfake Temporal Localization: Christos Koutlis,

Symeon Papadopoulos; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Koutlis_2026_WACV, author = {Koutlis, Christos and Papadopoulos, Symeon}, title = {AuViRe: Audio-visual Speech Representation Reconstruction for Deepfake Temporal Localization}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7168-7177} }
DOTGraph: CLIP-Driven Feature Disentanglement and Optimal Transport based Graph Learning for Few-Shot Segmentation: Shreya Biswas,

Zhaozheng Yin; [pdf] [supp]
[bibtex]
@InProceedings{Biswas_2026_WACV, author = {Biswas, Shreya and Yin, Zhaozheng}, title = {DOTGraph: CLIP-Driven Feature Disentanglement and Optimal Transport based Graph Learning for Few-Shot Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3638-3647} }
TA-Prompting: Enhancing Video Large Language Models for Dense Video Captioning via Temporal Anchors: Wei-Yuan Cheng,

Kai-Po Chang,

Chi-Pin Huang,

Fu-En Yang,

Yu-Chiang Frank Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cheng_2026_WACV, author = {Cheng, Wei-Yuan and Chang, Kai-Po and Huang, Chi-Pin and Yang, Fu-En and Wang, Yu-Chiang Frank}, title = {TA-Prompting: Enhancing Video Large Language Models for Dense Video Captioning via Temporal Anchors}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {225-235} }
Predicting Task fMRI Contrasts from Resting-State fMRI Using Sparse 3D Convolutions: Ivan Sviridov,

Maria Boyko,

Maksim Sharaev; [pdf]
[bibtex]
@InProceedings{Sviridov_2026_WACV, author = {Sviridov, Ivan and Boyko, Maria and Sharaev, Maksim}, title = {Predicting Task fMRI Contrasts from Resting-State fMRI Using Sparse 3D Convolutions}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6320-6329} }
Causality-Driven Audits of Model Robustness: Nathan Drenkow,

William Paul,

Chris Ribaudo,

Mathias Unberath; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Drenkow_2026_WACV, author = {Drenkow, Nathan and Paul, William and Ribaudo, Chris and Unberath, Mathias}, title = {Causality-Driven Audits of Model Robustness}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5956-5966} }
Harnessing Object Grounding for Time-Sensitive Video Understanding: Tz-Ying Wu,

Sharath Nittur Sridhar,

Subarna Tripathi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2026_WACV, author = {Wu, Tz-Ying and Sridhar, Sharath Nittur and Tripathi, Subarna}, title = {Harnessing Object Grounding for Time-Sensitive Video Understanding}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2475-2484} }
Pointmap-Conditioned Diffusion for Consistent Novel View Synthesis: Thang-Anh-Quan Nguyen,

Laurent Caraffa,

Jean-Philippe Tarel,

Roland Brémond; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nguyen_2026_WACV, author = {Nguyen, Thang-Anh-Quan and Caraffa, Laurent and Tarel, Jean-Philippe and Br\'emond, Roland}, title = {Pointmap-Conditioned Diffusion for Consistent Novel View Synthesis}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6360-6370} }
Reciprocal Teaching: Dynamic Multi-Model Teacher-Student Learning for Multiple Noisy Annotations: Wenjie Ai,

Cuong C. Nguyen,

Adrian Hilton,

Gustavo Carneiro; [pdf] [supp]
[bibtex]
@InProceedings{Ai_2026_WACV, author = {Ai, Wenjie and Nguyen, Cuong C. and Hilton, Adrian and Carneiro, Gustavo}, title = {Reciprocal Teaching: Dynamic Multi-Model Teacher-Student Learning for Multiple Noisy Annotations}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8376-8385} }
OracleGS: Grounding Generative Priors for Sparse-View Gaussian Splatting: Atakan Topaloğlu,

Kunyi Li,

Michael Niemeyer,

Nassir Navab,

A. Murat Tekalp,

Federico Tombari; [pdf] [supp]
[bibtex]
@InProceedings{Topaloglu_2026_WACV, author = {Topalo\u{g}lu, Atakan and Li, Kunyi and Niemeyer, Michael and Navab, Nassir and Tekalp, A. Murat and Tombari, Federico}, title = {OracleGS: Grounding Generative Priors for Sparse-View Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {77-87} }
DICE: Discrete Inversion Enabling Controllable Editing for Masked Generative Models: Xiaoxiao He,

Quan Dao,

Ligong Han,

Song Wen,

Minhao Bai,

Di Liu,

Han Zhang,

Felix Juefei-Xu,

Chaowei Tan,

Bo Liu,

Martin Renqiang Min,

Kang Li,

Faez Ahmed,

Akash Srivastava,

Hongdong Li,

Junzhou Huang,

Dimitris N. Metaxas; [pdf] [supp]
[bibtex]
@InProceedings{He_2026_WACV, author = {He, Xiaoxiao and Dao, Quan and Han, Ligong and Wen, Song and Bai, Minhao and Liu, Di and Zhang, Han and Juefei-Xu, Felix and Tan, Chaowei and Liu, Bo and Min, Martin Renqiang and Li, Kang and Ahmed, Faez and Srivastava, Akash and Li, Hongdong and Huang, Junzhou and Metaxas, Dimitris N.}, title = {DICE: Discrete Inversion Enabling Controllable Editing for Masked Generative Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {762-772} }
Human Pose Aggregation for Multi-View Temporal Video Alignment: Fabien Delattre,

Tsung-Wei Huang,

Guan-Ming Su,

Erik Learned-Miller; [pdf]
[bibtex]
@InProceedings{Delattre_2026_WACV, author = {Delattre, Fabien and Huang, Tsung-Wei and Su, Guan-Ming and Learned-Miller, Erik}, title = {Human Pose Aggregation for Multi-View Temporal Video Alignment}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {635-646} }
RampWatch: An In-the-Wild Dataset and Text-Guided Detection Framework for Recreational Vessels: Malik Muhammad Asim,

Claire B. Smallwood,

Abdullah Tariq,

Johnny Lo,

Syed Zulqarnain Gilani; [pdf] [supp]
[bibtex]
@InProceedings{Asim_2026_WACV, author = {Asim, Malik Muhammad and Smallwood, Claire B. and Tariq, Abdullah and Lo, Johnny and Gilani, Syed Zulqarnain}, title = {RampWatch: An In-the-Wild Dataset and Text-Guided Detection Framework for Recreational Vessels}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7576-7585} }
How to Design and Train Your Implicit Neural Representation for Video Compression: Matthew Gwilliam,

Roy Zhang,

Namitha Padmanabhan,

Hongyang Du,

Abhinav Shrivastava; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gwilliam_2026_WACV, author = {Gwilliam, Matthew and Zhang, Roy and Padmanabhan, Namitha and Du, Hongyang and Shrivastava, Abhinav}, title = {How to Design and Train Your Implicit Neural Representation for Video Compression}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {729-739} }
Q-Former Autoencoder: A Modern Framework for Medical Anomaly Detection: Francesco Dalmonte,

Emirhan Bayar,

Emre Akbas,

Mariana-Iuliana Georgescu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dalmonte_2026_WACV, author = {Dalmonte, Francesco and Bayar, Emirhan and Akbas, Emre and Georgescu, Mariana-Iuliana}, title = {Q-Former Autoencoder: A Modern Framework for Medical Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7985-7995} }
Latent Uncertainty-Aware Multi-View SDF Scan Completion: Faezeh Zakeri,

Lukas Ruppert,

Raphael Braun,

Hendrik P.A. Lensch; [pdf] [supp]
[bibtex]
@InProceedings{Zakeri_2026_WACV, author = {Zakeri, Faezeh and Ruppert, Lukas and Braun, Raphael and Lensch, Hendrik P.A.}, title = {Latent Uncertainty-Aware Multi-View SDF Scan Completion}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3556-3566} }
MoSCo: Real-time and Efficient Text-to-Motion Synthesis via Delta Training: Zhiyuan Zhang,

Lingqiao Liu; [pdf]
[bibtex]
@InProceedings{Zhang_2026_WACV, author = {Zhang, Zhiyuan and Liu, Lingqiao}, title = {MoSCo: Real-time and Efficient Text-to-Motion Synthesis via Delta Training}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6298-6308} }
DPBridge: Latent Diffusion Bridge for Dense Prediction: Haorui Ji,

Taojun Lin,

Hongdong Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ji_2026_WACV, author = {Ji, Haorui and Lin, Taojun and Li, Hongdong}, title = {DPBridge: Latent Diffusion Bridge for Dense Prediction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5520-5530} }
CraftSVG: Multi-Object Text-to-SVG Synthesis via Layout Guided Diffusion: Ayan Banerjee,

Nityanand Mathur,

Josep Llados,

Umapada Pal,

Anjan Dutta; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Banerjee_2026_WACV, author = {Banerjee, Ayan and Mathur, Nityanand and Llados, Josep and Pal, Umapada and Dutta, Anjan}, title = {CraftSVG: Multi-Object Text-to-SVG Synthesis via Layout Guided Diffusion}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2564-2574} }
Streaming Real-Time Trajectory Prediction Using Endpoint-Aware Modeling: Alexander Prutsch,

David Schinagl,

Horst Possegger; [pdf] [supp]
[bibtex]
@InProceedings{Prutsch_2026_WACV, author = {Prutsch, Alexander and Schinagl, David and Possegger, Horst}, title = {Streaming Real-Time Trajectory Prediction Using Endpoint-Aware Modeling}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3005-3014} }
Splannequin: Freezing Monocular Mannequin-Challenge Footage with Dual-Detection Splatting: Hao-Jen Chien,

Yi-Chuan Huang,

Chung-Ho Wu,

Wei-Lun Chao,

Yu-Lun Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chien_2026_WACV, author = {Chien, Hao-Jen and Huang, Yi-Chuan and Wu, Chung-Ho and Chao, Wei-Lun and Liu, Yu-Lun}, title = {Splannequin: Freezing Monocular Mannequin-Challenge Footage with Dual-Detection Splatting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8028-8040} }
Trajectory Tactics: When Transformers Learn Exploration to Generate Online Signature: Anurag Pandey,

Aditya Nigam,

Arnav Bhavsar,

Ashutosh Sharma,

Basu Verma,

Divya Acharya,

Mohd Amir; [pdf]
[bibtex]
@InProceedings{Pandey_2026_WACV, author = {Pandey, Anurag and Nigam, Aditya and Bhavsar, Arnav and Sharma, Ashutosh and Verma, Basu and Acharya, Divya and Amir, Mohd}, title = {Trajectory Tactics: When Transformers Learn Exploration to Generate Online Signature}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2306-2315} }
Hybrid State Representation for Video Procedure Planning: Woo Suk Choi,

Youwon Jang,

Minsu Lee,

Byoung-Tak Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Choi_2026_WACV, author = {Choi, Woo Suk and Jang, Youwon and Lee, Minsu and Zhang, Byoung-Tak}, title = {Hybrid State Representation for Video Procedure Planning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6507-6516} }
MageBench: Bridging Large Multimodal Models to Agents: Miaosen Zhang,

Qi Dai,

Yifan Yang,

Jianmin Bao,

Dongdong Chen,

Kai Qiu,

Chong Luo,

Xin Geng,

Baining Guo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2026_WACV, author = {Zhang, Miaosen and Dai, Qi and Yang, Yifan and Bao, Jianmin and Chen, Dongdong and Qiu, Kai and Luo, Chong and Geng, Xin and Guo, Baining}, title = {MageBench: Bridging Large Multimodal Models to Agents}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1415-1427} }
Diagnose Like A REAL Pathologist: An Uncertainty-Focused Approach for Trustworthy Multi-Resolution Multiple Instance Learning: Sungrae Hong,

Sol Lee,

Jisu Shin,

Jiwon Jeong,

Mun Yong Yi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hong_2026_WACV, author = {Hong, Sungrae and Lee, Sol and Shin, Jisu and Jeong, Jiwon and Yi, Mun Yong}, title = {Diagnose Like A REAL Pathologist: An Uncertainty-Focused Approach for Trustworthy Multi-Resolution Multiple Instance Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6132-6141} }
Curve Skeletonization in Continuous domain for Meshes and Point Clouds: Jai Bardhan,

Ramya Hebbalaguppe,

Aravind Udupa; [pdf] [supp]
[bibtex]
@InProceedings{Bardhan_2026_WACV, author = {Bardhan, Jai and Hebbalaguppe, Ramya and Udupa, Aravind}, title = {Curve Skeletonization in Continuous domain for Meshes and Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5079-5089} }
NerVast: Compression-Efficient Scaling of Implicit Neural Video Representations via Scene-based Parameter-sharing: Yunheon Lee,

Juncheol Ye,

Jaehong Kim,

Dongsu Han; [pdf] [supp]
[bibtex]
@InProceedings{Lee_2026_WACV, author = {Lee, Yunheon and Ye, Juncheol and Kim, Jaehong and Han, Dongsu}, title = {NerVast: Compression-Efficient Scaling of Implicit Neural Video Representations via Scene-based Parameter-sharing}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2616-2625} }
Align Video Diffusion Model with Online Video-Centric Preference Optimization: Jiacheng Zhang,

Jie Wu,

Weifeng Chen,

Yatai Ji,

Xuefeng Xiao,

Weilin Huang,

Kai Han; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2026_WACV, author = {Zhang, Jiacheng and Wu, Jie and Chen, Weifeng and Ji, Yatai and Xiao, Xuefeng and Huang, Weilin and Han, Kai}, title = {Align Video Diffusion Model with Online Video-Centric Preference Optimization}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6142-6152} }
SSMRadNet : A Sample-wise State-Space Framework for Efficient and Ultra-Light Radar Segmentation and Object Detection: Anuvab Sen,

Mir Sayeed Mohammad,

Saibal Mukhopadhyay; [pdf] [arXiv]
[bibtex]
@InProceedings{Sen_2026_WACV, author = {Sen, Anuvab and Mohammad, Mir Sayeed and Mukhopadhyay, Saibal}, title = {SSMRadNet : A Sample-wise State-Space Framework for Efficient and Ultra-Light Radar Segmentation and Object Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4365-4374} }
CAMP-VQA: Caption-Embedded Multimodal Perception for No-Reference Quality Assessment of Compressed Video: Xinyi Wang,

Angeliki Katsenou,

Junxiao Shen,

David Bull; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2026_WACV, author = {Wang, Xinyi and Katsenou, Angeliki and Shen, Junxiao and Bull, David}, title = {CAMP-VQA: Caption-Embedded Multimodal Perception for No-Reference Quality Assessment of Compressed Video}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2042-2051} }
HyperPose: Hyper-pose Embeddings for 3D-Aware Generative Models with Self-Supervised Disentangling of Pose and Scene: Mijeong Kim,

Namgi Kim,

Bohyung Han; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2026_WACV, author = {Kim, Mijeong and Kim, Namgi and Han, Bohyung}, title = {HyperPose: Hyper-pose Embeddings for 3D-Aware Generative Models with Self-Supervised Disentangling of Pose and Scene}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1011-1021} }
AortaDiff: A Unified Multitask Diffusion Framework for Contrast-Free AAA Imaging: Yuxuan Ou,

Ning Bi,

Jiazhen Pan,

Jiancheng Yang,

Boliang Yu,

Usama Zidan,

Regent Lee,

Vicente Grau; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ou_2026_WACV, author = {Ou, Yuxuan and Bi, Ning and Pan, Jiazhen and Yang, Jiancheng and Yu, Boliang and Zidan, Usama and Lee, Regent and Grau, Vicente}, title = {AortaDiff: A Unified Multitask Diffusion Framework for Contrast-Free AAA Imaging}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8242-8251} }
Beyond Faces: A Multimodal Person Clustering for Unconstrained Environments: Sahngmin Yoo,

Sangwon Lee,

Seongin Jo; [pdf]
[bibtex]
@InProceedings{Yoo_2026_WACV, author = {Yoo, Sahngmin and Lee, Sangwon and Jo, Seongin}, title = {Beyond Faces: A Multimodal Person Clustering for Unconstrained Environments}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4631-4640} }
High-Rate Mixout: Revisiting Mixout for Robust Domain Generalization: Masih Aminbeidokhti,

Heitor Rapela Medeiros,

Srikanth Muralidharan,

Eric Granger,

Marco Pedersoli; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Aminbeidokhti_2026_WACV, author = {Aminbeidokhti, Masih and Medeiros, Heitor Rapela and Muralidharan, Srikanth and Granger, Eric and Pedersoli, Marco}, title = {High-Rate Mixout: Revisiting Mixout for Robust Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3803-3812} }
High-Level Semantics and Low-Level Features Fusion for Multi-Scale Object Detection in Dynamic Construction Environments: Mahdi Bonyani,

Maryam Soleymani,

Chao Wang; [pdf]
[bibtex]
@InProceedings{Bonyani_2026_WACV, author = {Bonyani, Mahdi and Soleymani, Maryam and Wang, Chao}, title = {High-Level Semantics and Low-Level Features Fusion for Multi-Scale Object Detection in Dynamic Construction Environments}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6527-6536} }
BiNAR: A Bi-Modal Framework for Non-Aligned RGB-IR 3D Reconstruction via Gaussian Splatting: Zhongwen Wang,

Han Ling,

Weihao Zhang,

Yinghui Sun,

Quansen Sun; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2026_WACV, author = {Wang, Zhongwen and Ling, Han and Zhang, Weihao and Sun, Yinghui and Sun, Quansen}, title = {BiNAR: A Bi-Modal Framework for Non-Aligned RGB-IR 3D Reconstruction via Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4407-4416} }
Timestamp Query Transformer for Temporal Action Segmentation: Tieqiao Wang,

Sinisa Todorovic; [pdf]
[bibtex]
@InProceedings{Wang_2026_WACV, author = {Wang, Tieqiao and Todorovic, Sinisa}, title = {Timestamp Query Transformer for Temporal Action Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5016-5025} }
Mitigating Backdoor Attacks via Trigger Reconstruction and Model Hardening: Guanhong Tao,

Siyuan Cheng,

Guangyu Shen,

Yingqi Liu,

Shengwei An,

Zhuo Zhang,

Zhenting Wang,

Hanxi Guo,

Xiangyu Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Tao_2026_WACV, author = {Tao, Guanhong and Cheng, Siyuan and Shen, Guangyu and Liu, Yingqi and An, Shengwei and Zhang, Zhuo and Wang, Zhenting and Guo, Hanxi and Zhang, Xiangyu}, title = {Mitigating Backdoor Attacks via Trigger Reconstruction and Model Hardening}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {580-590} }
Visibility guided Self-Supervised Occlusion-Resilient Human Pose Estimation: Arindam Dutta,

Sarosij Bose,

Rohit Kundu,

Calvin-Khang Ta,

Saketh Bachu,

Konstantinos Karydis,

Amit K. Roy-Chowdhury; [pdf] [supp]
[bibtex]
@InProceedings{Dutta_2026_WACV, author = {Dutta, Arindam and Bose, Sarosij and Kundu, Rohit and Ta, Calvin-Khang and Bachu, Saketh and Karydis, Konstantinos and Roy-Chowdhury, Amit K.}, title = {Visibility guided Self-Supervised Occlusion-Resilient Human Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1054-1063} }
Feature-Disentangling RGB-NIR Fusion Network for Remote Driver Physiological Measurement: Tayssir Bouraffa,

Ziyuan Wang,

Daniel Strüber; [pdf] [supp]
[bibtex]
@InProceedings{Bouraffa_2026_WACV, author = {Bouraffa, Tayssir and Wang, Ziyuan and Str\"uber, Daniel}, title = {Feature-Disentangling RGB-NIR Fusion Network for Remote Driver Physiological Measurement}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {657-666} }
VividAnimator: An End-to-End Audio and Pose-driven Half-Body Human Animation Framework: Donglin Huang,

Yongyuan Li,

Tianhang Liu,

Junming Huang,

Xiaoda Yang,

Chi Wang,

Weiwei Xu; [pdf] [arXiv]
[bibtex]
@InProceedings{Huang_2026_WACV, author = {Huang, Donglin and Li, Yongyuan and Liu, Tianhang and Huang, Junming and Yang, Xiaoda and Wang, Chi and Xu, Weiwei}, title = {VividAnimator: An End-to-End Audio and Pose-driven Half-Body Human Animation Framework}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4325-4334} }
Delta-LLaVA: Base-then-Specialize Alignment for Token-Efficient Vision-Language Models: Mohamad Zamini,

Diksha Shukla; [pdf] [arXiv]
[bibtex]
@InProceedings{Zamini_2026_WACV, author = {Zamini, Mohamad and Shukla, Diksha}, title = {Delta-LLaVA: Base-then-Specialize Alignment for Token-Efficient Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3648-3657} }
CommonForms: A Large, Diverse Dataset for Form Field Detection: Joe Barrow; [pdf] [arXiv]
[bibtex]
@InProceedings{Barrow_2026_WACV, author = {Barrow, Joe}, title = {CommonForms: A Large, Diverse Dataset for Form Field Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1170-1179} }
OpenLVLM-MIA: A Controlled Benchmark Revealing the Limits of Membership Inference Attacks on Large Vision-Language Models: Ryoto Miyamoto,

Xin Fan,

Fuyuko Kido,

Tsuneo Matsumoto,

Hayato Yamana; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Miyamoto_2026_WACV, author = {Miyamoto, Ryoto and Fan, Xin and Kido, Fuyuko and Matsumoto, Tsuneo and Yamana, Hayato}, title = {OpenLVLM-MIA: A Controlled Benchmark Revealing the Limits of Membership Inference Attacks on Large Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2680-2689} }
AusSmoke meets MultiNatSmoke: a fully-labelled diverse smoke segmentation dataset: Weihao Li,

Hongjin Zhao,

Gao Zhu,

Ge-Peng Ji,

Nicholas Wilson,

Marta Yebra,

Nick Barnes; [pdf]
[bibtex]
@InProceedings{Li_2026_WACV, author = {Li, Weihao and Zhao, Hongjin and Zhu, Gao and Ji, Ge-Peng and Wilson, Nicholas and Yebra, Marta and Barnes, Nick}, title = {AusSmoke meets MultiNatSmoke: a fully-labelled diverse smoke segmentation dataset}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7996-8006} }
MVAT: Multi-View Aware Teacher for Weakly Supervised 3D Object Detection: Saad Lahlali,

Alexandre Fournier-Mongieux,

Nicolas Granger,

Hervé Le Borgne,

Quoc-Cuong Pham; [pdf] [supp]
[bibtex]
@InProceedings{Lahlali_2026_WACV, author = {Lahlali, Saad and Fournier-Mongieux, Alexandre and Granger, Nicolas and Le Borgne, Herv\'e and Pham, Quoc-Cuong}, title = {MVAT: Multi-View Aware Teacher for Weakly Supervised 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6101-6110} }
DreamCatcher: Efficient Multi-Concept Customization via Representation Finetuning: Jungwon Lee,

Changhun Lee,

Eunhyeok Park; [pdf] [supp]
[bibtex]
@InProceedings{Lee_2026_WACV, author = {Lee, Jungwon and Lee, Changhun and Park, Eunhyeok}, title = {DreamCatcher: Efficient Multi-Concept Customization via Representation Finetuning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7062-7072} }
GorillaWatch: An Automated System for In-the-Wild Gorilla Re-Identification and Population Monitoring: Maximilian Schall,

Felix Leonard Knöfel,

Noah Elias König,

Jan Jonas Kubeler,

Maximilian von Klinski,

Joan Wilhelm Linnemann,

Xiaoshi Liu,

Iven Jelle Schlegelmilch,

Ole Woyciniuk,

Alexandra Schild,

Dante Wasmuht,

Magdalena Bermejo Espinet,

German Illera Basas,

Gerard de Melo; [pdf]
[bibtex]
@InProceedings{Schall_2026_WACV, author = {Schall, Maximilian and Kn\"ofel, Felix Leonard and K\"onig, Noah Elias and Kubeler, Jan Jonas and von Klinski, Maximilian and Linnemann, Joan Wilhelm and Liu, Xiaoshi and Schlegelmilch, Iven Jelle and Woyciniuk, Ole and Schild, Alexandra and Wasmuht, Dante and Espinet, Magdalena Bermejo and Basas, German Illera and de Melo, Gerard}, title = {GorillaWatch: An Automated System for In-the-Wild Gorilla Re-Identification and Population Monitoring}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8364-8375} }
QCFace: Image Quality Control for boosting Face Representation & Recognition: Duc-Phuong Doan-Ngo,

Thanh-Dang Diep,

Thanh Nguyen-Duc,

Thanh-Sach LE,

Nam Thoai; [pdf] [supp]
[bibtex]
@InProceedings{Doan-Ngo_2026_WACV, author = {Doan-Ngo, Duc-Phuong and Diep, Thanh-Dang and Nguyen-Duc, Thanh and LE, Thanh-Sach and Thoai, Nam}, title = {QCFace: Image Quality Control for boosting Face Representation \& Recognition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1501-1511} }
CLoCKDistill: Consistent Location and Context aware Knowledge Distillation for DETRs: Qizhen Lan,

Qing Tian; [pdf] [arXiv]
[bibtex]
@InProceedings{Lan_2026_WACV, author = {Lan, Qizhen and Tian, Qing}, title = {CLoCKDistill: Consistent Location and Context aware Knowledge Distillation for DETRs}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7188-7197} }
False Alarm Rectification for Early Smoke Segmentation: Hongjin Zhao,

Weihao Li,

Ge-Peng Ji,

Nick Barnes; [pdf]
[bibtex]
@InProceedings{Zhao_2026_WACV, author = {Zhao, Hongjin and Li, Weihao and Ji, Ge-Peng and Barnes, Nick}, title = {False Alarm Rectification for Early Smoke Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1969-1978} }
NAPP: Noise-Adaptive Prototype Perturbation for Few-Shot Learning: Ilhwan Kim,

Sangwoo Yun,

Dongheon Lee,

Seongsu Kim,

Joonki Paik; [pdf]
[bibtex]
@InProceedings{Kim_2026_WACV, author = {Kim, Ilhwan and Yun, Sangwoo and Lee, Dongheon and Kim, Seongsu and Paik, Joonki}, title = {NAPP: Noise-Adaptive Prototype Perturbation for Few-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8007-8016} }
MemeTAG: Keyword-Driven Meme Classification through Tag Embedding Reconstruction: Akshit Sharma,

Prashant W Patil; [pdf] [supp]
[bibtex]
@InProceedings{Sharma_2026_WACV, author = {Sharma, Akshit and Patil, Prashant W}, title = {MemeTAG: Keyword-Driven Meme Classification through Tag Embedding Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7679-7688} }
DMAT: An End-to-End Framework for Joint Atmospheric Turbulence Mitigation and Object Detection: Paul Hill,

Zhiming Liu,

Alin Achim,

David Bull,

Nantheera Anantrasirichai; [pdf] [arXiv]
[bibtex]
@InProceedings{Hill_2026_WACV, author = {Hill, Paul and Liu, Zhiming and Achim, Alin and Bull, David and Anantrasirichai, Nantheera}, title = {DMAT: An End-to-End Framework for Joint Atmospheric Turbulence Mitigation and Object Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2690-2699} }
ViGG: Robust RGB-D Point Cloud Registration using Visual-Geometric Mutual Guidance: Congjia Chen,

Shen Yan,

Yufu Qu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2026_WACV, author = {Chen, Congjia and Yan, Shen and Qu, Yufu}, title = {ViGG: Robust RGB-D Point Cloud Registration using Visual-Geometric Mutual Guidance}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {816-826} }
Learning Unified Spatio-temporal Representations for Efficient Compressed Video Understanding: Shristi Das Biswas,

Efstathia Soufleri,

Arani Roy,

Kaushik Roy; [pdf] [supp]
[bibtex]
@InProceedings{Das_Biswas_2026_WACV, author = {Das Biswas, Shristi and Soufleri, Efstathia and Roy, Arani and Roy, Kaushik}, title = {Learning Unified Spatio-temporal Representations for Efficient Compressed Video Understanding}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4755-4765} }
Hymavi : A Hybrid Mamba-Attention Network in Multi-View Framework for Volumetric Medical Image Segmentation: Sy Dat Tran,

Jin Kyu Gahm; [pdf]
[bibtex]
@InProceedings{Tran_2026_WACV, author = {Tran, Sy Dat and Gahm, Jin Kyu}, title = {Hymavi : A Hybrid Mamba-Attention Network in Multi-View Framework for Volumetric Medical Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6006-6015} }
Revisiting Layer Normalization for Point Cloud Test Time Adaptation: Moslem Yazdanpanah,

Ali Bahri,

Mehrdad Noori,

Sahar Dastani,

Samuel Barbeau,

David Osowiechi,

Gustavo Adolfo Vargas Hakim,

Ismail Ben Ayed,

Christian Desrosiers; [pdf] [supp]
[bibtex]
@InProceedings{Yazdanpanah_2026_WACV, author = {Yazdanpanah, Moslem and Bahri, Ali and Noori, Mehrdad and Dastani, Sahar and Barbeau, Samuel and Osowiechi, David and Hakim, Gustavo Adolfo Vargas and Ben Ayed, Ismail and Desrosiers, Christian}, title = {Revisiting Layer Normalization for Point Cloud Test Time Adaptation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {537-546} }
LooC: Effective Low-Dimensional Codebook for Compositional Vector Quantization: Jie Li,

Kwan-Yee K. Wong,

Kai Han; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2026_WACV, author = {Li, Jie and Wong, Kwan-Yee K. and Han, Kai}, title = {LooC: Effective Low-Dimensional Codebook for Compositional Vector Quantization}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {160-170} }
DocWaveDiff: A Predict-and-Refine approach for Document Image Enhancement with Wavelet U-Nets and Diffusion models: Matteo Marulli,

Marco Bertini; [pdf] [supp]
[bibtex]
@InProceedings{Marulli_2026_WACV, author = {Marulli, Matteo and Bertini, Marco}, title = {DocWaveDiff: A Predict-and-Refine approach for Document Image Enhancement with Wavelet U-Nets and Diffusion models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8511-8520} }
A-V Representation Learning via Audio Shift Prediction for Multimodal Deepfake Detection and Temporal Localization: Ashutosh Anshul,

Eng Siong Chng,

Deepu Rajan; [pdf] [supp]
[bibtex]
@InProceedings{Anshul_2026_WACV, author = {Anshul, Ashutosh and Chng, Eng Siong and Rajan, Deepu}, title = {A-V Representation Learning via Audio Shift Prediction for Multimodal Deepfake Detection and Temporal Localization}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2553-2563} }
3D Gaussian Point Encoders: Jim James,

Benjamin Wilson,

Simon Lucey,

James Hays; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{James_2026_WACV, author = {James, Jim and Wilson, Benjamin and Lucey, Simon and Hays, James}, title = {3D Gaussian Point Encoders}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1788-1797} }
ODEt(ODEl): Shortcutting the Time and the Length in Diffusion and Flow Models for Faster Sampling: Denis Gudovskiy,

Wenzhao Zheng,

Tomoyuki Okuno,

Yohei Nakata,

Kurt Keutzer; [pdf] [supp]
[bibtex]
@InProceedings{Gudovskiy_2026_WACV, author = {Gudovskiy, Denis and Zheng, Wenzhao and Okuno, Tomoyuki and Nakata, Yohei and Keutzer, Kurt}, title = {ODEt(ODEl): Shortcutting the Time and the Length in Diffusion and Flow Models for Faster Sampling}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6111-6120} }
Can Image Splicing and Copy-Move Forgery Be Detected by the Same Model? Forensim: An Attention-Based State-Space Approach: Soumyaroop Nandi,

Prem Natarajan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nandi_2026_WACV, author = {Nandi, Soumyaroop and Natarajan, Prem}, title = {Can Image Splicing and Copy-Move Forgery Be Detected by the Same Model? Forensim: An Attention-Based State-Space Approach}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6194-6204} }
Controllable Long-term Motion Generation with Extended Joint Targets: Eunjong Lee,

Eunhee Kim,

Sanghoon Hong,

Eunho Jung,

Jihoon Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2026_WACV, author = {Lee, Eunjong and Kim, Eunhee and Hong, Sanghoon and Jung, Eunho and Kim, Jihoon}, title = {Controllable Long-term Motion Generation with Extended Joint Targets}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5164-5173} }
CVP: Central-Peripheral Vision-Inspired Multimodal Model for Spatial Reasoning: Zeyuan Chen,

Xiang Zhang,

Haiyang Xu,

Jianwen Xie,

Zhuowen Tu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2026_WACV, author = {Chen, Zeyuan and Zhang, Xiang and Xu, Haiyang and Xie, Jianwen and Tu, Zhuowen}, title = {CVP: Central-Peripheral Vision-Inspired Multimodal Model for Spatial Reasoning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2295-2305} }
TopoRec: Point Cloud Recognition Using Topological Data Analysis: Anirban Ghosh,

Iliya Kulbaka,

Ian Dahlin,

Ayan Dutta; [pdf] [arXiv]
[bibtex]
@InProceedings{Ghosh_2026_WACV, author = {Ghosh, Anirban and Kulbaka, Iliya and Dahlin, Ian and Dutta, Ayan}, title = {TopoRec: Point Cloud Recognition Using Topological Data Analysis}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7544-7553} }
SFMNet: Sparse Focal Modulation for 3D Object Detection: Oren Shrout,

Ayellet Tal; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shrout_2026_WACV, author = {Shrout, Oren and Tal, Ayellet}, title = {SFMNet: Sparse Focal Modulation for 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6287-6297} }
Not Like Transformers: Drop the Beat Representation for Dance Generation with Mamba-Based Diffusion Model: Sangjune Park,

Inhyeok Choi,

Donghyeon Soon,

Youngwoo Jeon,

Kyungdon Joo; [pdf] [supp]
[bibtex]
@InProceedings{Park_2026_WACV, author = {Park, Sangjune and Choi, Inhyeok and Soon, Donghyeon and Jeon, Youngwoo and Joo, Kyungdon}, title = {Not Like Transformers: Drop the Beat Representation for Dance Generation with Mamba-Based Diffusion Model}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1767-1776} }
Multi-Grained Text-Guided Image Fusion for Multi-Exposure and Multi-Focus Scenarios: Mingwei Tang,

Jiahao Nie,

Guang Yang,

Ziqing Cui,

Jie Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tang_2026_WACV, author = {Tang, Mingwei and Nie, Jiahao and Yang, Guang and Cui, Ziqing and Li, Jie}, title = {Multi-Grained Text-Guided Image Fusion for Multi-Exposure and Multi-Focus Scenarios}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7668-7678} }
Odo: Depth-Guided Diffusion for Identity-Preserving Body Reshaping: Siddharth Khandelwal,

Sridhar Kamath,

Arjun Jain; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Khandelwal_2026_WACV, author = {Khandelwal, Siddharth and Kamath, Sridhar and Jain, Arjun}, title = {Odo: Depth-Guided Diffusion for Identity-Preserving Body Reshaping}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {22-31} }
Enhancing Visual Planning with Auxiliary Tasks and Multi-token Prediction: Ce Zhang,

Yale Song,

Ruta Desai,

Michael Louis Iuzzolino,

Joseph Tighe,

Gedas Bertasius,

Satwik Kottur; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2026_WACV, author = {Zhang, Ce and Song, Yale and Desai, Ruta and Iuzzolino, Michael Louis and Tighe, Joseph and Bertasius, Gedas and Kottur, Satwik}, title = {Enhancing Visual Planning with Auxiliary Tasks and Multi-token Prediction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4190-4200} }
F-INR: Functional Tensor Decomposition for Implicit Neural Representations: Sai Karthikeya Vemuri,

Tim Büchner,

Joachim Denzler; [pdf] [supp]
[bibtex]
@InProceedings{Vemuri_2026_WACV, author = {Vemuri, Sai Karthikeya and B\"uchner, Tim and Denzler, Joachim}, title = {F-INR: Functional Tensor Decomposition for Implicit Neural Representations}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6557-6568} }
Dronaquatics: Real-time Swimming Analytics Using Drone Captured Imagery: Thu Tran,

Harold Abraham Joseph,

Kichang Lee,

Kenny Tsu Wei Choo,

Dong Ma,

Shaohui Foong,

Thivya Kandappu,

Jeonggil Ko,

Rajesh Balan; [pdf] [supp]
[bibtex]
@InProceedings{Tran_2026_WACV, author = {Tran, Thu and Joseph, Harold Abraham and Lee, Kichang and Choo, Kenny Tsu Wei and Ma, Dong and Foong, Shaohui and Kandappu, Thivya and Ko, Jeonggil and Balan, Rajesh}, title = {Dronaquatics: Real-time Swimming Analytics Using Drone Captured Imagery}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4881-4889} }
GASP: Unifying Geometric and Semantic Self-Supervised Pre-training for Autonomous Driving: William Ljungbergh,

Adam Lilja,

Adam Tonderski,

Arvid Laveno Ling,

Carl Lindström,

Willem Verbeke,

Junsheng Fu,

Christoffer Petersson,

Lars Hammarstrand,

Michael Felsberg; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ljungbergh_2026_WACV, author = {Ljungbergh, William and Lilja, Adam and Tonderski, Adam and Ling, Arvid Laveno and Lindstr\"om, Carl and Verbeke, Willem and Fu, Junsheng and Petersson, Christoffer and Hammarstrand, Lars and Felsberg, Michael}, title = {GASP: Unifying Geometric and Semantic Self-Supervised Pre-training for Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3077-3087} }
Understanding the Visual Projection Space of Multimodal LLMs: Sungheon Jeong,

Yoojeong Song,

Hyungjoon Kim; [pdf]
[bibtex]
@InProceedings{Jeong_2026_WACV, author = {Jeong, Sungheon and Song, Yoojeong and Kim, Hyungjoon}, title = {Understanding the Visual Projection Space of Multimodal LLMs}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6049-6058} }
WarpRF: Multi-View Consistency for Training-Free Uncertainty Quantification and Applications in Radiance Fields: Sadra Safadoust,

Fabio Tosi,

Fatma Güney,

Matteo Poggi; [pdf] [supp]
[bibtex]
@InProceedings{Safadoust_2026_WACV, author = {Safadoust, Sadra and Tosi, Fabio and G\"uney, Fatma and Poggi, Matteo}, title = {WarpRF: Multi-View Consistency for Training-Free Uncertainty Quantification and Applications in Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5226-5235} }
FAST-EQA: Efficient Embodied Question Answering with Global and Local Region Relevancy: Haochen Zhang,

Nirav Savaliya,

Faizan Siddiqui,

Enna Sachdeva; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2026_WACV, author = {Zhang, Haochen and Savaliya, Nirav and Siddiqui, Faizan and Sachdeva, Enna}, title = {FAST-EQA: Efficient Embodied Question Answering with Global and Local Region Relevancy}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1664-1673} }
Flood-LDM: Generalizable Latent Diffusion Models for rapid and accurate zero-shot High-Resolution Flood Mapping: Sun Han Neo,

Sachith Seneviratne,

Herath Mudiyanselage Viraj Vidura Herath Herath,

Abhishek Saha,

Sanka Rasnayaka,

Lucy Amanda Marshall; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Neo_2026_WACV, author = {Neo, Sun Han and Seneviratne, Sachith and Herath, Herath Mudiyanselage Viraj Vidura Herath and Saha, Abhishek and Rasnayaka, Sanka and Marshall, Lucy Amanda}, title = {Flood-LDM: Generalizable Latent Diffusion Models for rapid and accurate zero-shot High-Resolution Flood Mapping}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8063-8072} }
Fused Similarity Measure Based Alignment with Dual-Scale Adaptive Selection for Weakly Supervised Video Anomaly Detection: Yue-Gao Lu,

Hong-Jie Xing,

Chun-Guo Li; [pdf]
[bibtex]
@InProceedings{Lu_2026_WACV, author = {Lu, Yue-Gao and Xing, Hong-Jie and Li, Chun-Guo}, title = {Fused Similarity Measure Based Alignment with Dual-Scale Adaptive Selection for Weakly Supervised Video Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3193-3202} }
FARF-Net: Frequency-guided Adaptive Receptive Field Network for Edge-enhanced Polyp Segmentation: Xue Li,

Aiwen Jiang,

Hongqian Yu,

Yang Xiao; [pdf]
[bibtex]
@InProceedings{Li_2026_WACV, author = {Li, Xue and Jiang, Aiwen and Yu, Hongqian and Xiao, Yang}, title = {FARF-Net: Frequency-guided Adaptive Receptive Field Network for Edge-enhanced Polyp Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2338-2347} }
PerVL-Bench: Benchmarking Multimodal Personalization for Large Vision-Language Models: Minsung Kim; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2026_WACV, author = {Kim, Minsung}, title = {PerVL-Bench: Benchmarking Multimodal Personalization for Large Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6696-6704} }
OSEG: Improving Diffusion sampling through Orthogonal Smoothed Energy Guidance: Masud An Nur Islam Fahim,

Nazmus Saqib,

Joon-Min Gil; [pdf] [supp]
[bibtex]
@InProceedings{Fahim_2026_WACV, author = {Fahim, Masud An Nur Islam and Saqib, Nazmus and Gil, Joon-Min}, title = {OSEG: Improving Diffusion sampling through Orthogonal Smoothed Energy Guidance}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5996-6005} }
Detecting Social Engagement of Elderly From Lifelog Image-streams to Identify Effective Cues for Autobiographic Recall: Vengateswaran Subramaniam,

Vigneshwaran Subbaraju,

Debaditya Roy,

Pramath Krishna,

Thivya Kandappu,

Qianli Xu; [pdf] [supp]
[bibtex]
@InProceedings{Subramaniam_2026_WACV, author = {Subramaniam, Vengateswaran and Subbaraju, Vigneshwaran and Roy, Debaditya and Krishna, Pramath and Kandappu, Thivya and Xu, Qianli}, title = {Detecting Social Engagement of Elderly From Lifelog Image-streams to Identify Effective Cues for Autobiographic Recall}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3380-3389} }
Text Slider: Efficient and Plug-and-Play Continuous Concept Control for Image/Video Synthesis via LoRA Adapters: Pin-Yen Chiu,

I-Sheng Fang,

Jun-Cheng Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chiu_2026_WACV, author = {Chiu, Pin-Yen and Fang, I-Sheng and Chen, Jun-Cheng}, title = {Text Slider: Efficient and Plug-and-Play Continuous Concept Control for Image/Video Synthesis via LoRA Adapters}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {613-622} }
Motion-Aware Graph Fusion Network for 3D Human Pose Estimation: Yen Pham,

Xiaohui Yuan,

Chengyuan Zhuang; [pdf] [supp]
[bibtex]
@InProceedings{Pham_2026_WACV, author = {Pham, Yen and Yuan, Xiaohui and Zhuang, Chengyuan}, title = {Motion-Aware Graph Fusion Network for 3D Human Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5798-5808} }
Learning Spatio-temporal Feature Representations for Video-based Gaze Estimation: Alexandre Personnic,

Mihai Bace; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Personnic_2026_WACV, author = {Personnic, Alexandre and Bace, Mihai}, title = {Learning Spatio-temporal Feature Representations for Video-based Gaze Estimation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5121-5130} }
ProtoGMVAE: A Variational Auto-Encoder with True Gaussian Mixture Prior for Prototypical-based Self-Explainability: Martin Blanchard,

Christophe Ducottet,

Damien Muselet,

Olivier Delézay; [pdf] [supp]
[bibtex]
@InProceedings{Blanchard_2026_WACV, author = {Blanchard, Martin and Ducottet, Christophe and Muselet, Damien and Del\'ezay, Olivier}, title = {ProtoGMVAE: A Variational Auto-Encoder with True Gaussian Mixture Prior for Prototypical-based Self-Explainability}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5396-5405} }
Graph Query Networks for Object Detection with Automotive Radar: Loveneet Saini,

Hasan Tercan,

Tobias Meisen; [pdf] [arXiv]
[bibtex]
@InProceedings{Saini_2026_WACV, author = {Saini, Loveneet and Tercan, Hasan and Meisen, Tobias}, title = {Graph Query Networks for Object Detection with Automotive Radar}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6988-6997} }
GroupPortrait: Multi-ID Portrait Generation with High Identity Preservation and Fine-Grained Control: Meijia Huang,

Ruida Li,

Bing Ma,

Liangwei Jiang,

Shuo Fang,

Chenguang Ma; [pdf] [supp]
[bibtex]
@InProceedings{Huang_2026_WACV, author = {Huang, Meijia and Li, Ruida and Ma, Bing and Jiang, Liangwei and Fang, Shuo and Ma, Chenguang}, title = {GroupPortrait: Multi-ID Portrait Generation with High Identity Preservation and Fine-Grained Control}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6226-6235} }
4D Multimodal Co-attention Fusion Network with Latent Contrastive Alignment for Alzheimer's Diagnosis: Yuxiang Wei,

Yanteng Zhang,

Xi Xiao,

Tianyang Wang,

Xiao Wang,

Vince D. Calhoun; [pdf]
[bibtex]
@InProceedings{Wei_2026_WACV, author = {Wei, Yuxiang and Zhang, Yanteng and Xiao, Xi and Wang, Tianyang and Wang, Xiao and Calhoun, Vince D.}, title = {4D Multimodal Co-attention Fusion Network with Latent Contrastive Alignment for Alzheimer's Diagnosis}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5457-5466} }
Beyond Realism: Learning the Art of Expressive Composition with StickerNet: Haoming Lu,

David Kocharian,

Humphrey Shi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lu_2026_WACV, author = {Lu, Haoming and Kocharian, David and Shi, Humphrey}, title = {Beyond Realism: Learning the Art of Expressive Composition with StickerNet}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {869-878} }
ClusterMine: Robust Label-Free Visual Out-Of-Distribution Detection via Concept Mining from Text Corpora: Nikolas Adaloglou,

Diana Petrusheva,

Mohamed Asker,

Felix Michels,

Markus Kollmann; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Adaloglou_2026_WACV, author = {Adaloglou, Nikolas and Petrusheva, Diana and Asker, Mohamed and Michels, Felix and Kollmann, Markus}, title = {ClusterMine: Robust Label-Free Visual Out-Of-Distribution Detection via Concept Mining from Text Corpora}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1999-2010} }
FAIR-SIGHT: Fairness Assurance in Image Recognition via Simultaneous Conformal Thresholding and Dynamic Output Repair: Arya Fayyazi,

Mehdi Kamal,

Massoud Pedram; [pdf] [arXiv]
[bibtex]
@InProceedings{Fayyazi_2026_WACV, author = {Fayyazi, Arya and Kamal, Mehdi and Pedram, Massoud}, title = {FAIR-SIGHT: Fairness Assurance in Image Recognition via Simultaneous Conformal Thresholding and Dynamic Output Repair}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6633-6642} }
T2LF: LLM-Guided Multimodal Diffusion for Text-to-Light Field Synthesis: Soyoung Yoon,

Namhyuk Ahn,

In Kyu Park; [pdf] [supp]
[bibtex]
@InProceedings{Yoon_2026_WACV, author = {Yoon, Soyoung and Ahn, Namhyuk and Park, In Kyu}, title = {T2LF: LLM-Guided Multimodal Diffusion for Text-to-Light Field Synthesis}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7322-7332} }
LENVIZ: A High-Resolution Low-Exposure Night Vision Benchmark Dataset: Manjushree Aithal,

Rosaura G VidalMata,

Manikandtan Kartha,

Gong Chen,

Eashan Adhikarla,

Lucas Nedel Kirsten,

Zhicheng Fu,

Nikhil Ambha Madhusudhana,

Joseph V. Nasti; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Aithal_2026_WACV, author = {Aithal, Manjushree and VidalMata, Rosaura G and Kartha, Manikandtan and Chen, Gong and Adhikarla, Eashan and Kirsten, Lucas Nedel and Fu, Zhicheng and Madhusudhana, Nikhil Ambha and Nasti, Joseph V.}, title = {LENVIZ: A High-Resolution Low-Exposure Night Vision Benchmark Dataset}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2531-2540} }
Fine-grained Defocus Blur Control for Generative Image Models: Ayush Shrivastava,

Connelly Barnes,

Xuaner Zhang,

Lingzhi Zhang,

Andrew Owens,

Sohrab Amirghodsi,

Eli Shechtman; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shrivastava_2026_WACV, author = {Shrivastava, Ayush and Barnes, Connelly and Zhang, Xuaner and Zhang, Lingzhi and Owens, Andrew and Amirghodsi, Sohrab and Shechtman, Eli}, title = {Fine-grained Defocus Blur Control for Generative Image Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4335-4344} }
MARS: a Multimodal Alignment and Ranking System for Few-Shot Segmentation: Nico Catalano,

Stefano Samele,

Paolo Pertino,

Matteo Matteucci; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Catalano_2026_WACV, author = {Catalano, Nico and Samele, Stefano and Pertino, Paolo and Matteucci, Matteo}, title = {MARS: a Multimodal Alignment and Ranking System for Few-Shot Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1284-1293} }
Training-free Conditional Image Embedding Framework Leveraging Large Vision Language Models: Masayuki Kawarada,

Kosuke Yamada,

Antonio Tejero-de-Pablos,

Naoto Inoue; [pdf] [supp]
[bibtex]
@InProceedings{Kawarada_2026_WACV, author = {Kawarada, Masayuki and Yamada, Kosuke and Tejero-de-Pablos, Antonio and Inoue, Naoto}, title = {Training-free Conditional Image Embedding Framework Leveraging Large Vision Language Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7636-7646} }
DreamMakeup: Face Makeup Customization using Latent Diffusion Models: Geon Yeong Park,

Inhwa Han,

Serin Yang,

Yeobin Hong,

Seongmin Jeong,

Heechan Jeon,

Myeongjin Goh,

Sung Won Yi,

Jin Nam,

Jong Chul Ye; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Park_2026_WACV, author = {Park, Geon Yeong and Han, Inhwa and Yang, Serin and Hong, Yeobin and Jeong, Seongmin and Jeon, Heechan and Goh, Myeongjin and Yi, Sung Won and Nam, Jin and Ye, Jong Chul}, title = {DreamMakeup: Face Makeup Customization using Latent Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {422-430} }
AirLock+: Scaling UAV-to-Satellite Image Registration for Target Geolocalization and Geospatial Augmented Reality: Zhiyun Deng,

Austin Case,

Luis Sentis; [pdf]
[bibtex]
@InProceedings{Deng_2026_WACV, author = {Deng, Zhiyun and Case, Austin and Sentis, Luis}, title = {AirLock+: Scaling UAV-to-Satellite Image Registration for Target Geolocalization and Geospatial Augmented Reality}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3340-3349} }
Morphing Through Time: Diffusion-Based Bridging of Temporal Gaps for Robust Alignment in Change Detection: Seyedehanita Madani,

Vishal M. Patel; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Madani_2026_WACV, author = {Madani, Seyedehanita and Patel, Vishal M.}, title = {Morphing Through Time: Diffusion-Based Bridging of Temporal Gaps for Robust Alignment in Change Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {431-439} }
General and Domain-Specific Zero-shot Detection of Generated Images via Conditional Likelihood: Roy Betser,

Omer Hofman,

Roman Vainshtein,

Guy Gilboa; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Betser_2026_WACV, author = {Betser, Roy and Hofman, Omer and Vainshtein, Roman and Gilboa, Guy}, title = {General and Domain-Specific Zero-shot Detection of Generated Images via Conditional Likelihood}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7809-7820} }
Multi-Modal Soccer Scene Analysis with Masked Pre-Training: Marc Peral,

Guillem Capellera,

Luis Ferraz,

Antonio Rubio,

Antonio Agudo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Peral_2026_WACV, author = {Peral, Marc and Capellera, Guillem and Ferraz, Luis and Rubio, Antonio and Agudo, Antonio}, title = {Multi-Modal Soccer Scene Analysis with Masked Pre-Training}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3536-3545} }
Learning Group Actions In Disentangled Latent Image Representations: Farhana Hossain Swarnali,

Miaomiao Zhang,

Tonmoy Hossain; [pdf] [arXiv]
[bibtex]
@InProceedings{Swarnali_2026_WACV, author = {Swarnali, Farhana Hossain and Zhang, Miaomiao and Hossain, Tonmoy}, title = {Learning Group Actions In Disentangled Latent Image Representations}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3140-3149} }
Evaluating the Capability of Video Question Generation for Expert Knowledge Elicitation: Huaying Zhang,

Atsushi Hashimoto,

Tosho Hirasawa; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2026_WACV, author = {Zhang, Huaying and Hashimoto, Atsushi and Hirasawa, Tosho}, title = {Evaluating the Capability of Video Question Generation for Expert Knowledge Elicitation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3047-3056} }
DiRe: Diversity-promoting Regularization for Dataset Condensation: Saumyaranjan Mohanty,

Aravind Reddy,

Konda Reddy Mopuri; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mohanty_2026_WACV, author = {Mohanty, Saumyaranjan and Reddy, Aravind and Mopuri, Konda Reddy}, title = {DiRe: Diversity-promoting Regularization for Dataset Condensation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2818-2827} }
PredMapNet: Future and Historical Reasoning for Consistent Online HD Vectorized Map Construction: Bo Lang,

Nirav Savaliya,

Zhihao Zheng,

Jinglun Feng,

Zheng-Hang Yeh,

Mooi Choo Chuah; [pdf] [arXiv]
[bibtex]
@InProceedings{Lang_2026_WACV, author = {Lang, Bo and Savaliya, Nirav and Zheng, Zhihao and Feng, Jinglun and Yeh, Zheng-Hang and Chuah, Mooi Choo}, title = {PredMapNet: Future and Historical Reasoning for Consistent Online HD Vectorized Map Construction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5477-5487} }
MM-TS: Multi-Modal Temperature and Margin Schedules for Contrastive Learning with Long-Tail Data: Siarhei Sheludzko,

Dhimitrios Duka,

Bernt Schiele,

Hilde Kuehne,

Anna Kukleva; [pdf] [supp]
[bibtex]
@InProceedings{Sheludzko_2026_WACV, author = {Sheludzko, Siarhei and Duka, Dhimitrios and Schiele, Bernt and Kuehne, Hilde and Kukleva, Anna}, title = {MM-TS: Multi-Modal Temperature and Margin Schedules for Contrastive Learning with Long-Tail Data}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7376-7386} }
Federated Model Synchronization for Diagnostic Redefinition through a Novel Selective Parameter Unlearning: Mayank Kumar Kundalwal,

Mamta Mamta,

Deepak Mishra,

Asif Ekbal; [pdf] [supp]
[bibtex]
@InProceedings{Kundalwal_2026_WACV, author = {Kundalwal, Mayank Kumar and Mamta, Mamta and Mishra, Deepak and Ekbal, Asif}, title = {Federated Model Synchronization for Diagnostic Redefinition through a Novel Selective Parameter Unlearning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1395-1404} }
VitaGlyph: Vitalizing Artistic Typography with Flexible Dual-branch Diffusion Models: Kailai Feng,

Yabo Zhang,

Haodong Yu,

Zhilong Ji,

Jinfeng Bai,

Hongzhi Zhang,

Wangmeng Zuo; [pdf] [arXiv]
[bibtex]
@InProceedings{Feng_2026_WACV, author = {Feng, Kailai and Zhang, Yabo and Yu, Haodong and Ji, Zhilong and Bai, Jinfeng and Zhang, Hongzhi and Zuo, Wangmeng}, title = {VitaGlyph: Vitalizing Artistic Typography with Flexible Dual-branch Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8220-8230} }
Feature Inversion as a Lens on Vision Encoders: Eduard Allakhverdov,

Dmitrii Tarasov,

Elizaveta Goncharova,

Andrey Kuznetsov; [pdf] [supp]
[bibtex]
@InProceedings{Allakhverdov_2026_WACV, author = {Allakhverdov, Eduard and Tarasov, Dmitrii and Goncharova, Elizaveta and Kuznetsov, Andrey}, title = {Feature Inversion as a Lens on Vision Encoders}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3598-3605} }
DTMIR-Pro: Domain Translation with Prompt-based Latent-Space Generalization for Multi-Weather Image Restoration: Ashutosh Kulkarni,

Prashant W. Patil,

Santosh Kumar Vipparthi,

Subrahmanyam Murala,

Balasubramanian Raman; [pdf] [supp]
[bibtex]
@InProceedings{Kulkarni_2026_WACV, author = {Kulkarni, Ashutosh and Patil, Prashant W. and Vipparthi, Santosh Kumar and Murala, Subrahmanyam and Raman, Balasubramanian}, title = {DTMIR-Pro: Domain Translation with Prompt-based Latent-Space Generalization for Multi-Weather Image Restoration}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3846-3856} }
Diffusion-Based Authentication of Copy Detection Patterns: A Multimodal Framework with Printer Signature Conditioning: Bolutife Atoki,

Iuliia Tkachenko,

Bertrand Kerautret,

Carlos Crispim Junior; [pdf]
[bibtex]
@InProceedings{Atoki_2026_WACV, author = {Atoki, Bolutife and Tkachenko, Iuliia and Kerautret, Bertrand and Junior, Carlos Crispim}, title = {Diffusion-Based Authentication of Copy Detection Patterns: A Multimodal Framework with Printer Signature Conditioning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1685-1694} }
BREEN: Bridge Data-Efficient Encoder-Free Multimodal Learning with Learnable Queries: Tianle Li,

Yongming Rao,

Winston Hu,

Yu Cheng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2026_WACV, author = {Li, Tianle and Rao, Yongming and Hu, Winston and Cheng, Yu}, title = {BREEN: Bridge Data-Efficient Encoder-Free Multimodal Learning with Learnable Queries}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5384-5395} }
GHOST: Getting to the Bottom of Hallucinations with A Multi-round Consistency Benchmark: Vibashan VS,

Nadine Chang,

Jenny Schmalfuss,

Vishal M. Patel,

Zhiding Yu,

Jose M. Alvarez; [pdf] [supp]
[bibtex]
@InProceedings{VS_2026_WACV, author = {VS, Vibashan and Chang, Nadine and Schmalfuss, Jenny and Patel, Vishal M. and Yu, Zhiding and Alvarez, Jose M.}, title = {GHOST: Getting to the Bottom of Hallucinations with A Multi-round Consistency Benchmark}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6163-6173} }
MorphXAI: An Explainable Framework for Morphological Analysis of Parasites in Blood Smear Images: Aqsa Yousaf,

Sint Sint Win,

Megan Coffee,

Habeeb Olufowobi; [pdf] [arXiv]
[bibtex]
@InProceedings{Yousaf_2026_WACV, author = {Yousaf, Aqsa and Win, Sint Sint and Coffee, Megan and Olufowobi, Habeeb}, title = {MorphXAI: An Explainable Framework for Morphological Analysis of Parasites in Blood Smear Images}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2125-2134} }
Optimizing against Infeasible Inclusions from Data for Semantic Segmentation through Morphology: Shamik Basu,

Luc Van Gool,

Christos Sakaridis; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Basu_2026_WACV, author = {Basu, Shamik and Van Gool, Luc and Sakaridis, Christos}, title = {Optimizing against Infeasible Inclusions from Data for Semantic Segmentation through Morphology}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7524-7533} }
MuSACo: Multimodal Subject-Specific Selection and Adaptation for Expression Recognition with Co-Training: Muhammad Osama Zeeshan,

Natacha Gillet,

Alessandro Lameiras Koerich,

Marco Pedersoli,

Francois Bremond,

Eric Granger; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zeeshan_2026_WACV, author = {Zeeshan, Muhammad Osama and Gillet, Natacha and Koerich, Alessandro Lameiras and Pedersoli, Marco and Bremond, Francois and Granger, Eric}, title = {MuSACo: Multimodal Subject-Specific Selection and Adaptation for Expression Recognition with Co-Training}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3606-3616} }
MANTA: Physics-Informed Generalized Underwater Object Tracking: Suhas Srinath,

Hemang Jamadagni,

Aditya Chandrasekar,

Prathosh A P; [pdf] [supp]
[bibtex]
@InProceedings{Srinath_2026_WACV, author = {Srinath, Suhas and Jamadagni, Hemang and Chandrasekar, Aditya and A P, Prathosh}, title = {MANTA: Physics-Informed Generalized Underwater Object Tracking}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3472-3482} }
Multimodal Medical Image Binding via Shared Text Embeddings: Yunhao Liu,

Suyang Xi,

Shiqi Liu,

Hong Ding,

Chicheng Jin,

Chong Zhong,

Junjun He,

Catherine C. Liu,

Yiqing Shen; [pdf] [arXiv]
[bibtex]
@InProceedings{Liu_2026_WACV, author = {Liu, Yunhao and Xi, Suyang and Liu, Shiqi and Ding, Hong and Jin, Chicheng and Zhong, Chong and He, Junjun and Liu, Catherine C. and Shen, Yiqing}, title = {Multimodal Medical Image Binding via Shared Text Embeddings}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1610-1620} }
Zero-Shot Audio-Visual Editing via Cross-Modal Delta Denoising: Yan-Bo Lin,

Kevin Lin,

Zhengyuan Yang,

Linjie Li,

Jianfeng Wang,

Chung-Ching Lin,

Xiaofei Wang,

Gedas Bertasius,

Lijuan Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lin_2026_WACV, author = {Lin, Yan-Bo and Lin, Kevin and Yang, Zhengyuan and Li, Linjie and Wang, Jianfeng and Lin, Chung-Ching and Wang, Xiaofei and Bertasius, Gedas and Wang, Lijuan}, title = {Zero-Shot Audio-Visual Editing via Cross-Modal Delta Denoising}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7344-7354} }
An improved architecture for part-based animal re-identification through semantic segmentation distillation: Eugênio Dias Ribeiro Neto,

Marc Chaumont,

Gérard Subsol,

Michel De Garine-Wichatitsky,

Hélène Guis; [pdf]
[bibtex]
@InProceedings{Neto_2026_WACV, author = {Neto, Eug\^enio Dias Ribeiro and Chaumont, Marc and Subsol, G\'erard and De Garine-Wichatitsky, Michel and Guis, H\'el\`ene}, title = {An improved architecture for part-based animal re-identification through semantic segmentation distillation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5280-5289} }
SegMango: Early Deep Mango Yield Prediction based on Flower Segmentation and Weather Data: Janaksinh Ven,

Charu Sharma,

Azeemuddin Syed; [pdf]
[bibtex]
@InProceedings{Ven_2026_WACV, author = {Ven, Janaksinh and Sharma, Charu and Syed, Azeemuddin}, title = {SegMango: Early Deep Mango Yield Prediction based on Flower Segmentation and Weather Data}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4984-4993} }
From Detection to Anticipation: Online Understanding of Struggles across Various Tasks and Activities: Shijia Feng,

Michael Wray,

Walterio Mayol-Cuevas; [pdf] [supp]
[bibtex]
@InProceedings{Feng_2026_WACV, author = {Feng, Shijia and Wray, Michael and Mayol-Cuevas, Walterio}, title = {From Detection to Anticipation: Online Understanding of Struggles across Various Tasks and Activities}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4036-4045} }
D2Mamba: Dual Domain Guided Informed Search in State Space Model for Underwater Image Enhancement: Alik Pramanick,

Soumajit Roy,

Arijit Sur; [pdf] [supp]
[bibtex]
@InProceedings{Pramanick_2026_WACV, author = {Pramanick, Alik and Roy, Soumajit and Sur, Arijit}, title = {D2Mamba: Dual Domain Guided Informed Search in State Space Model for Underwater Image Enhancement}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7126-7136} }
RAT4D: Rig and Animate Objects without Surface Templates in 4D: Mosam Dabhi,

Simon Lucey,

Laszlo A. Jeni; [pdf] [supp]
[bibtex]
@InProceedings{Dabhi_2026_WACV, author = {Dabhi, Mosam and Lucey, Simon and Jeni, Laszlo A.}, title = {RAT4D: Rig and Animate Objects without Surface Templates in 4D}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {393-401} }
Reinforcement Learning-based Adaptive Control of Classifier-Free Guidance and Timestep Embeddings in Diffusion Models: Haochen You,

Baojing Liu,

Hongyang He; [pdf]
[bibtex]
@InProceedings{You_2026_WACV, author = {You, Haochen and Liu, Baojing and He, Hongyang}, title = {Reinforcement Learning-based Adaptive Control of Classifier-Free Guidance and Timestep Embeddings in Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {43-53} }
ImageChain: Advancing Sequential Image-to-Text Reasoning in Multimodal Large Language Models: Danae Sanchez Villegas,

Ingo Ziegler,

Desmond Elliott; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Villegas_2026_WACV, author = {Villegas, Danae Sanchez and Ziegler, Ingo and Elliott, Desmond}, title = {ImageChain: Advancing Sequential Image-to-Text Reasoning in Multimodal Large Language Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5131-5141} }
Blur2Sharp: Human Novel Pose and View Synthesis with Generative Prior Refinement: Chia-Hern Lai,

I-Hsuan Lo,

Yen-Ku Yeh,

Thanh-Nguyen Truong,

Ching-Chun Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lai_2026_WACV, author = {Lai, Chia-Hern and Lo, I-Hsuan and Yeh, Yen-Ku and Truong, Thanh-Nguyen and Huang, Ching-Chun}, title = {Blur2Sharp: Human Novel Pose and View Synthesis with Generative Prior Refinement}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3350-3359} }
SkelSplat: Robust Multi-view 3D Human Pose Estimation with Differentiable Gaussian Rendering: Laura Bragagnolo,

Leonardo Barcellona,

Stefano Ghidoni; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bragagnolo_2026_WACV, author = {Bragagnolo, Laura and Barcellona, Leonardo and Ghidoni, Stefano}, title = {SkelSplat: Robust Multi-view 3D Human Pose Estimation with Differentiable Gaussian Rendering}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3036-3046} }
ControlEvents: Controllable Synthesis of Event Camera Data with Foundational Prior from Image Diffusion Models: Yixuan Hu,

Yuxuan Xue,

Simon Klenk,

Daniel Cremers,

Gerard Pons-Moll; [pdf] [supp]
[bibtex]
@InProceedings{Hu_2026_WACV, author = {Hu, Yixuan and Xue, Yuxuan and Klenk, Simon and Cremers, Daniel and Pons-Moll, Gerard}, title = {ControlEvents: Controllable Synthesis of Event Camera Data with Foundational Prior from Image Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5509-5519} }
TM-Adapter: Temporal Merge Adapter for Efficient Global Temporal Modeling: Woo Joo Hahm,

Seungwoo Jang,

Hyeon Tak Kim,

Daeun Lee,

Kwangsu Kim; [pdf] [supp]
[bibtex]
@InProceedings{Hahm_2026_WACV, author = {Hahm, Woo Joo and Jang, Seungwoo and Kim, Hyeon Tak and Lee, Daeun and Kim, Kwangsu}, title = {TM-Adapter: Temporal Merge Adapter for Efficient Global Temporal Modeling}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6121-6131} }
From Few-Shot to Zero-Shot Pallet Load Recognition: A Deployed Embedding-Based Vision System for Industrial Logistics: Juan Jesús Losada del Olmo,

Emilio Pardo Ballesteros,

Pedro E. López-de-Teruel,

Alberto Ruiz; [pdf] [supp]
[bibtex]
@InProceedings{del_Olmo_2026_WACV, author = {del Olmo, Juan Jes\'us Losada and Ballesteros, Emilio Pardo and L\'opez-de-Teruel, Pedro E. and Ruiz, Alberto}, title = {From Few-Shot to Zero-Shot Pallet Load Recognition: A Deployed Embedding-Based Vision System for Industrial Logistics}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2901-2911} }
AFRAgent : An Adaptive Feature Renormalization Based High Resolution Aware GUI agent: Neeraj Anand,

Rishabh Jain,

Sohan Patnaik,

Balaji Krishnamurthy,

Mausoom Sarkar; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Anand_2026_WACV, author = {Anand, Neeraj and Jain, Rishabh and Patnaik, Sohan and Krishnamurthy, Balaji and Sarkar, Mausoom}, title = {AFRAgent : An Adaptive Feature Renormalization Based High Resolution Aware GUI agent}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1147-1158} }
SUGAR: A Sweeter Spot for Generative Unlearning of Many Identities: Dung Thuy Nguyen,

Quang Nguyen,

Preston K. Robinette,

Eli Jiang,

Taylor T. Johnson,

Kevin Leach; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nguyen_2026_WACV, author = {Nguyen, Dung Thuy and Nguyen, Quang and Robinette, Preston K. and Jiang, Eli and Johnson, Taylor T. and Leach, Kevin}, title = {SUGAR: A Sweeter Spot for Generative Unlearning of Many Identities}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2731-2740} }
LASOR: Towards Clinically Transparent and Explainable Ophthalmic Report Generation via Lesion-Aware Segmentation: Jian Park,

Hyunseon Won,

JeeEun Kim,

Joon Seo Hwang,

Jeong Mo Han,

Ji In Park,

Daniel Duck-Jin Hwang,

Jinyoung Han; [pdf]
[bibtex]
@InProceedings{Park_2026_WACV, author = {Park, Jian and Won, Hyunseon and Kim, JeeEun and Hwang, Joon Seo and Han, Jeong Mo and Park, Ji In and Hwang, Daniel Duck-Jin and Han, Jinyoung}, title = {LASOR: Towards Clinically Transparent and Explainable Ophthalmic Report Generation via Lesion-Aware Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5194-5204} }
ST-Think: How Multimodal Large Language Models Reason About 4D Worlds from Ego-Centric Videos: Peiran Wu,

Yunze Liu,

Miao Liu,

Junxiao Shen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2026_WACV, author = {Wu, Peiran and Liu, Yunze and Liu, Miao and Shen, Junxiao}, title = {ST-Think: How Multimodal Large Language Models Reason About 4D Worlds from Ego-Centric Videos}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5174-5183} }
mmWEAVER: Environment-Specific mmWave Signal Synthesis from a Photo and Activity Description: Mahathir Monjur,

Shahriar Nirjon; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Monjur_2026_WACV, author = {Monjur, Mahathir and Nirjon, Shahriar}, title = {mmWEAVER: Environment-Specific mmWave Signal Synthesis from a Photo and Activity Description}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1875-1884} }
Optimizing LVLMs with On-Policy Data for Effective Hallucination Mitigation: Chengzhi Yu,

Yifan Xu,

Yifan Chen,

Wenyi Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2026_WACV, author = {Yu, Chengzhi and Xu, Yifan and Chen, Yifan and Zhang, Wenyi}, title = {Optimizing LVLMs with On-Policy Data for Effective Hallucination Mitigation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4733-4743} }
Overcoming Fine-Grained Visual Challenges in Animal Re-Identification via Semantic Feature Alignment: Yihao Wu,

Di Zhao,

Yuzhuo Li,

Matthew Alajas,

Alistair S. Glen,

Jingfeng Zhang,

Gillian Dobbie,

Daniel Wilson,

Yun Sing Koh; [pdf] [supp]
[bibtex]
@InProceedings{Wu_2026_WACV, author = {Wu, Yihao and Zhao, Di and Li, Yuzhuo and Alajas, Matthew and Glen, Alistair S. and Zhang, Jingfeng and Dobbie, Gillian and Wilson, Daniel and Koh, Yun Sing}, title = {Overcoming Fine-Grained Visual Challenges in Animal Re-Identification via Semantic Feature Alignment}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {371-381} }
Better Safe Than Sorry? Overreaction Problem of Vision Language Models in Visual Emergency Recognition: Dasol Choi,

Seunghyun Lee,

Youngsook Song; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Choi_2026_WACV, author = {Choi, Dasol and Lee, Seunghyun and Song, Youngsook}, title = {Better Safe Than Sorry? Overreaction Problem of Vision Language Models in Visual Emergency Recognition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4724-4732} }
Narrating For You: Prompt-guided Audio-visual Narrating Face Generation Employing Multi-entangled Latent Space: Aashish Chandra K,

Aashutosh A V,

Abhijit Das; [pdf] [supp]
[bibtex]
@InProceedings{K_2026_WACV, author = {K, Aashish Chandra and A V, Aashutosh and Das, Abhijit}, title = {Narrating For You: Prompt-guided Audio-visual Narrating Face Generation Employing Multi-entangled Latent Space}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1314-1323} }
Semi-Supervised Hierarchical Open-Set Classification: Erik Wallin,

Fredrik Kahl,

Lars Hammarstrand; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wallin_2026_WACV, author = {Wallin, Erik and Kahl, Fredrik and Hammarstrand, Lars}, title = {Semi-Supervised Hierarchical Open-Set Classification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1989-1998} }
BrightRate: Quality Assessment for User-Generated HDR Videos: Shreshth Saini,

Bowen Chen,

Yilin Wang,

Neil Birkbeck,

Balu Adsumilli,

Alan C. Bovik; [pdf] [supp]
[bibtex]
@InProceedings{Saini_2026_WACV, author = {Saini, Shreshth and Chen, Bowen and Wang, Yilin and Birkbeck, Neil and Adsumilli, Balu and Bovik, Alan C.}, title = {BrightRate: Quality Assessment for User-Generated HDR Videos}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1522-1532} }
Guiding What Not to Generate: Automated Negative Prompting for Text-Image Alignment: Sangha Park,

Eunji Kim,

Yeongtak Oh,

Jooyoung Choi,

Sungroh Yoon; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Park_2026_WACV, author = {Park, Sangha and Kim, Eunji and Oh, Yeongtak and Choi, Jooyoung and Yoon, Sungroh}, title = {Guiding What Not to Generate: Automated Negative Prompting for Text-Image Alignment}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6664-6675} }
LASER: Lip Landmark Assisted Speaker Detection for Robustness: Le Thien Phuc Nguyen,

Zhuoran Yu,

Yong Jae Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nguyen_2026_WACV, author = {Nguyen, Le Thien Phuc and Yu, Zhuoran and Lee, Yong Jae}, title = {LASER: Lip Landmark Assisted Speaker Detection for Robustness}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7291-7300} }
Spacewalk-18: A Benchmark for Multimodal and Long-form Procedural Video Understanding in Novel Domains: Zitian Tang,

Rohan Myer Krishnan,

Zhiqiu Yu,

Chen Sun; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tang_2026_WACV, author = {Tang, Zitian and Krishnan, Rohan Myer and Yu, Zhiqiu and Sun, Chen}, title = {Spacewalk-18: A Benchmark for Multimodal and Long-form Procedural Video Understanding in Novel Domains}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4472-4482} }
Extreme Amodal Face Detection: Changlin Song,

Yunzhong Hou,

Michael Randall Barnes,

Rahul Shome,

Dylan Campbell; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Song_2026_WACV, author = {Song, Changlin and Hou, Yunzhong and Barnes, Michael Randall and Shome, Rahul and Campbell, Dylan}, title = {Extreme Amodal Face Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2934-2943} }
Event-based Graph Representation with Spatial and Motion Vectors for Asynchronous Object Detection: Aayush Atul Verma,

Arpitsinh Vaghela,

Bharatesh Chakravarthi,

Kaustav Chanda,

Yezhou Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Verma_2026_WACV, author = {Verma, Aayush Atul and Vaghela, Arpitsinh and Chakravarthi, Bharatesh and Chanda, Kaustav and Yang, Yezhou}, title = {Event-based Graph Representation with Spatial and Motion Vectors for Asynchronous Object Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3781-3791} }
PHYSPLAT: a Framework for Photorealistic Hybrid Simulation of Real and Synthetic Elements using 3D Gaussian Splatting: Mario Alfonso-Arsuaga,

Henar Dominguez-Elvira,

Jorge Casas-Guerrero,

Andrea Castiella-Aguirrezabala,

Lorenzo Costábile Domínguez,

Jorge García-González,

Maria Naranjo-Almeida,

Marc Comino-Trinidad,

Jorge Lopez-Moreno; [pdf] [supp]
[bibtex]
@InProceedings{Alfonso-Arsuaga_2026_WACV, author = {Alfonso-Arsuaga, Mario and Dominguez-Elvira, Henar and Casas-Guerrero, Jorge and Castiella-Aguirrezabala, Andrea and Dom{\'\i}nguez, Lorenzo Cost\'abile and Garc{\'\i}a-Gonz\'alez, Jorge and Naranjo-Almeida, Maria and Comino-Trinidad, Marc and Lopez-Moreno, Jorge}, title = {PHYSPLAT: a Framework for Photorealistic Hybrid Simulation of Real and Synthetic Elements using 3D Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1621-1631} }
VOCAL: Visual Odometry via ContrAstive Learning: Chi-Yao Huang,

Zeel Bhatt,

Yezhou Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2026_WACV, author = {Huang, Chi-Yao and Bhatt, Zeel and Yang, Yezhou}, title = {VOCAL: Visual Odometry via ContrAstive Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3297-3309} }
Multi-view Stereo with Multiple Projectors for Oneshot Entire Shape Scan based on Neural SDF and DSSS Demultiplexing: Kota Nishihara,

Ryo Furukawa,

Ryusuke Sagawa,

Hiroshi Kawasaki; [pdf] [supp]
[bibtex]
@InProceedings{Nishihara_2026_WACV, author = {Nishihara, Kota and Furukawa, Ryo and Sagawa, Ryusuke and Kawasaki, Hiroshi}, title = {Multi-view Stereo with Multiple Projectors for Oneshot Entire Shape Scan based on Neural SDF and DSSS Demultiplexing}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5488-5497} }
Self-Supervised Visual Prompting for Cross-Domain Road Damage Detection: Xi Xiao,

Zhuxuanzi Wang,

Mingqiao Mo,

Chen Liu,

Chenrui Ma,

Yanshu Li,

Smita Krishnaswamy,

Xiao Wang,

Tianyang Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xiao_2026_WACV, author = {Xiao, Xi and Wang, Zhuxuanzi and Mo, Mingqiao and Liu, Chen and Ma, Chenrui and Li, Yanshu and Krishnaswamy, Smita and Wang, Xiao and Wang, Tianyang}, title = {Self-Supervised Visual Prompting for Cross-Domain Road Damage Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3514-3524} }
SpecGen: Neural Spectral BRDF Generation via Spectral-Spatial Tri-plane Aggregation: Zhenyu Jin,

Wenjie Li,

Zhanyu Ma,

Heng Guo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jin_2026_WACV, author = {Jin, Zhenyu and Li, Wenjie and Ma, Zhanyu and Guo, Heng}, title = {SpecGen: Neural Spectral BRDF Generation via Spectral-Spatial Tri-plane Aggregation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8323-8332} }
TimeRefine: Temporal Grounding with Time Refining Video LLM: Xizi Wang,

Feng Cheng,

Ziyang Wang,

Huiyu Wang,

Md Mohaiminul Islam,

Lorenzo Torresani,

Mohit Bansal,

Gedas Bertasius,

David Crandall; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2026_WACV, author = {Wang, Xizi and Cheng, Feng and Wang, Ziyang and Wang, Huiyu and Islam, Md Mohaiminul and Torresani, Lorenzo and Bansal, Mohit and Bertasius, Gedas and Crandall, David}, title = {TimeRefine: Temporal Grounding with Time Refining Video LLM}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5067-5078} }
Towards High-Fidelity, Identity-Preserving Real-Time Makeup Transfer: Decoupling Style Generation: Lydia Chau,

Zhi Yu,

Ruowei Jiang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chau_2026_WACV, author = {Chau, Lydia and Yu, Zhi and Jiang, Ruowei}, title = {Towards High-Fidelity, Identity-Preserving Real-Time Makeup Transfer: Decoupling Style Generation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3588-3597} }
OMeGa: Joint Optimization of Explicit Meshes and Gaussian Splats for Robust Scene-Level Surface Reconstruction: Yuhang Cao,

Haojun Yan,

Danya Yao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cao_2026_WACV, author = {Cao, Yuhang and Yan, Haojun and Yao, Danya}, title = {OMeGa: Joint Optimization of Explicit Meshes and Gaussian Splats for Robust Scene-Level Surface Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4386-4395} }
Feedback Alignment Meets Low-Rank Manifolds: A Structured Recipe for Local Learning: Arani Roy,

Marco P. Apolinario,

Shristi Das Biswas,

Kaushik Roy; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Roy_2026_WACV, author = {Roy, Arani and Apolinario, Marco P. and Das Biswas, Shristi and Roy, Kaushik}, title = {Feedback Alignment Meets Low-Rank Manifolds: A Structured Recipe for Local Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2984-2992} }
Edge-Aware Image Manipulation via Diffusion Models with a Novel Structure-Preservation Loss: Minsu Gong,

Nuri Ryu,

Jungseul Ok,

Sunghyun Cho; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gong_2026_WACV, author = {Gong, Minsu and Ryu, Nuri and Ok, Jungseul and Cho, Sunghyun}, title = {Edge-Aware Image Manipulation via Diffusion Models with a Novel Structure-Preservation Loss}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5142-5153} }
Comp4D: Compositional 4D Scene Generation: Hanwen Liang,

Dejia Xu,

Neel P. Bhatt,

Hezhen Hu,

Hanxue Liang,

Konstantinos N. Plataniotis; [pdf] [supp]
[bibtex]
@InProceedings{Liang_2026_WACV, author = {Liang, Hanwen and Xu, Dejia and Bhatt, Neel P. and Hu, Hezhen and Liang, Hanxue and Plataniotis, Konstantinos N.}, title = {Comp4D: Compositional 4D Scene Generation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3567-3577} }
One-Shot Fine-Grained Re-Identification of Paint Marked Honey Bees using Vision Foundation Models: Luke Meyers,

Josué A. Rodríguez-Cordero,

Rémi Mégret; [pdf]
[bibtex]
@InProceedings{Meyers_2026_WACV, author = {Meyers, Luke and Rodr{\'\i}guez-Cordero, Josu\'e A. and M\'egret, R\'emi}, title = {One-Shot Fine-Grained Re-Identification of Paint Marked Honey Bees using Vision Foundation Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {560-569} }
PaRaChute: Pathology-Radiology Cross-Modal Fusion for Missing-Modality-Robust Survival Prediction: Pietro Caforio,

Isabella Poles,

Marco D. Santambrogio; [pdf] [supp]
[bibtex]
@InProceedings{Caforio_2026_WACV, author = {Caforio, Pietro and Poles, Isabella and Santambrogio, Marco D.}, title = {PaRaChute: Pathology-Radiology Cross-Modal Fusion for Missing-Modality-Robust Survival Prediction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {718-728} }
Zero-Shot Table Extraction in Business Documents: A Unified Benchmark with Error Taxonomy and Ecological Analysis: Eliott Thomas,

Mickael Coustaty,

Aurélie Joseph,

Tri-Cong Pham,

Gaspar Deloin,

Elodie Carel,

Vincent Poulain D'andecy,

Jean-Marc Ogier; [pdf]
[bibtex]
@InProceedings{Thomas_2026_WACV, author = {Thomas, Eliott and Coustaty, Mickael and Joseph, Aur\'elie and Pham, Tri-Cong and Deloin, Gaspar and Carel, Elodie and D'andecy, Vincent Poulain and Ogier, Jean-Marc}, title = {Zero-Shot Table Extraction in Business Documents: A Unified Benchmark with Error Taxonomy and Ecological Analysis}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4974-4983} }
A Unified Diffusion-Based Framework for Multi-Agent Trajectory Prediction Integrating Structured Multi-Modal Representations: Chenxi Yang,

Suyang Xi,

Hong Ding,

Yiqing Shen,

Yunhao Liu; [pdf]
[bibtex]
@InProceedings{Yang_2026_WACV, author = {Yang, Chenxi and Xi, Suyang and Ding, Hong and Shen, Yiqing and Liu, Yunhao}, title = {A Unified Diffusion-Based Framework for Multi-Agent Trajectory Prediction Integrating Structured Multi-Modal Representations}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6442-6452} }
From Street to Orbit: Training-Free Cross-View Retrieval via Location Semantics and LLM Guidance: Jeongho Min,

Dongyoung Kim,

Jaehyup Lee; [pdf] [arXiv]
[bibtex]
@InProceedings{Min_2026_WACV, author = {Min, Jeongho and Kim, Dongyoung and Lee, Jaehyup}, title = {From Street to Orbit: Training-Free Cross-View Retrieval via Location Semantics and LLM Guidance}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {570-579} }
Training-free Detection of Text-to-video Generations via Over-coherence: Jonathan Brokman,

Oren Rachmil,

Omer Hofman,

Roy Betser,

Amit Giloni,

Roman Vainshtein,

Hisashi Kojima; [pdf]
[bibtex]
@InProceedings{Brokman_2026_WACV, author = {Brokman, Jonathan and Rachmil, Oren and Hofman, Omer and Betser, Roy and Giloni, Amit and Vainshtein, Roman and Kojima, Hisashi}, title = {Training-free Detection of Text-to-video Generations via Over-coherence}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3993-4003} }
Countering Multi-modal Representation Collapse through Rank-targeted Fusion: Seulgi Kim,

Kiran Kokilepersaud,

Mohit Prabhushankar,

Ghassan AlRegib; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2026_WACV, author = {Kim, Seulgi and Kokilepersaud, Kiran and Prabhushankar, Mohit and AlRegib, Ghassan}, title = {Countering Multi-modal Representation Collapse through Rank-targeted Fusion}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4744-4754} }
MSRTrack: LLM-Powered Object Tracking with Motion and Semantic Reasoning: Tong Shen,

Di Wang,

José M. F. Moura; [pdf]
[bibtex]
@InProceedings{Shen_2026_WACV, author = {Shen, Tong and Wang, Di and Moura, Jos\'e M. F.}, title = {MSRTrack: LLM-Powered Object Tracking with Motion and Semantic Reasoning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {838-848} }
MarineEval: Assessing the Marine Intelligence of Vision-Language Models: Yuk Kwan Wong,

Tuan-An To,

Jipeng Zhang,

Ziqiang Zheng,

Sai-Kit Yeung; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wong_2026_WACV, author = {Wong, Yuk Kwan and To, Tuan-An and Zhang, Jipeng and Zheng, Ziqiang and Yeung, Sai-Kit}, title = {MarineEval: Assessing the Marine Intelligence of Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1459-1470} }
MMHOI: Modeling Complex 3D Multi-Human Multi-Object Interactions: Kaen Kogashi,

Anoop Cherian,

Meng-Yu Jennifer Kuo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kogashi_2026_WACV, author = {Kogashi, Kaen and Cherian, Anoop and Kuo, Meng-Yu Jennifer}, title = {MMHOI: Modeling Complex 3D Multi-Human Multi-Object Interactions}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1512-1521} }
CLIP's Visual Embedding Projector is a Few-shot Cornucopia: Mohammad Fahes,

Tuan-Hung Vu,

Andrei Bursuc,

Patrick Perez,

Raoul De Charette; [pdf] [supp]
[bibtex]
@InProceedings{Fahes_2026_WACV, author = {Fahes, Mohammad and Vu, Tuan-Hung and Bursuc, Andrei and Perez, Patrick and De Charette, Raoul}, title = {CLIP's Visual Embedding Projector is a Few-shot Cornucopia}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3254-3264} }
MomentMix Augmentation with Length-Aware DETR for Temporally Robust Moment Retrieval: Seojeong Park,

Jiho Choi,

Kyungjune Baek,

Hyunjung Shim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Park_2026_WACV, author = {Park, Seojeong and Choi, Jiho and Baek, Kyungjune and Shim, Hyunjung}, title = {MomentMix Augmentation with Length-Aware DETR for Temporally Robust Moment Retrieval}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1127-1136} }
IMPACT: Interpretable Most Important Person Analysis and Classification using Transformer-based Models: Akshat Rampuria,

Kamakshya Prasad Nayak,

Kamalakar Vijay Thakare,

Tushar Joshi,

Aditya Dhananjay Singh,

Haesol Park,

Heeseung Choi,

Debi Prosad Dogra,

Ig-Jae Kim; [pdf] [supp]
[bibtex]
@InProceedings{Rampuria_2026_WACV, author = {Rampuria, Akshat and Nayak, Kamakshya Prasad and Thakare, Kamalakar Vijay and Joshi, Tushar and Singh, Aditya Dhananjay and Park, Haesol and Choi, Heeseung and Dogra, Debi Prosad and Kim, Ig-Jae}, title = {IMPACT: Interpretable Most Important Person Analysis and Classification using Transformer-based Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8179-8187} }
HOLO: Holistic Lightweight Optimization for Scene Understanding with Auto-Annotation and Multimodal Learning: Xiaoyun Hu,

Xiaohan Yan,

Nan Wang,

Gang Wei,

Zhicheng Wang; [pdf] [supp]
[bibtex]
@InProceedings{Hu_2026_WACV, author = {Hu, Xiaoyun and Yan, Xiaohan and Wang, Nan and Wei, Gang and Wang, Zhicheng}, title = {HOLO: Holistic Lightweight Optimization for Scene Understanding with Auto-Annotation and Multimodal Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7719-7729} }
UniVid: Unifying Vision Tasks with Pre-trained Video Generation Models: Lan Chen,

Yuchao Gu,

Qi Mao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2026_WACV, author = {Chen, Lan and Gu, Yuchao and Mao, Qi}, title = {UniVid: Unifying Vision Tasks with Pre-trained Video Generation Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6754-6763} }
Sea-CLIP: Mining Semantic-Aware Representations for Few-Shot Anomaly Detection with CLIP: Xiao Guo,

Zhimin Chen,

Carlos D. Castillo,

Hongcheng Wang,

Xiaoming Liu; [pdf] [supp]
[bibtex]
@InProceedings{Guo_2026_WACV, author = {Guo, Xiao and Chen, Zhimin and Castillo, Carlos D. and Wang, Hongcheng and Liu, Xiaoming}, title = {Sea-CLIP: Mining Semantic-Aware Representations for Few-Shot Anomaly Detection with CLIP}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3689-3699} }
CasTex: Cascaded Text-to-Texture Synthesis via Explicit Texture Maps and Physically-Based Shading: Mishan Aliev,

Dmitry Baranchuk,

Kirill Struminsky; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Aliev_2026_WACV, author = {Aliev, Mishan and Baranchuk, Dmitry and Struminsky, Kirill}, title = {CasTex: Cascaded Text-to-Texture Synthesis via Explicit Texture Maps and Physically-Based Shading}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3411-3420} }
SOPHY: Generating Simulation-Ready Objects with Physical Materials: Junyi Cao,

Evangelos Kalogerakis; [pdf] [supp]
[bibtex]
@InProceedings{Cao_2026_WACV, author = {Cao, Junyi and Kalogerakis, Evangelos}, title = {SOPHY: Generating Simulation-Ready Objects with Physical Materials}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4693-4704} }
SasMamba: A Lightweight Structure-Aware Stride State Space Model for 3D Human Pose Estimation: Hu Cui,

Wenqiang Hua,

Renjing Huang,

Shurui Jia,

Tessai Hayama; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cui_2026_WACV, author = {Cui, Hu and Hua, Wenqiang and Huang, Renjing and Jia, Shurui and Hayama, Tessai}, title = {SasMamba: A Lightweight Structure-Aware Stride State Space Model for 3D Human Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2721-2730} }
MedPEFT-CL: Dual-Phase Parameter-Efficient Continual Learning with Medical Semantic Adapter and Bidirectional Memory Consolidation: Ziyuan Gao,

Philippe Morel; [pdf]
[bibtex]
@InProceedings{Gao_2026_WACV, author = {Gao, Ziyuan and Morel, Philippe}, title = {MedPEFT-CL: Dual-Phase Parameter-Efficient Continual Learning with Medical Semantic Adapter and Bidirectional Memory Consolidation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7699-7708} }
ZebraPose: Zebra Detection and Pose Estimation using only Synthetic Data: Elia Bonetto,

Aamir Ahmad; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bonetto_2026_WACV, author = {Bonetto, Elia and Ahmad, Aamir}, title = {ZebraPose: Zebra Detection and Pose Estimation using only Synthetic Data}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6611-6620} }
Action Anticipation at a Glimpse: To What Extent Can Multimodal Cues Replace Video?: Manuel Benavent-Lledo,

Konstantinos Bacharidis,

Victoria Manousaki,

Konstantinos Papoutsakis,

Antonis Argyros,

Jose Garcia-Rodriguez; [pdf] [supp]
[bibtex]
@InProceedings{Benavent-Lledo_2026_WACV, author = {Benavent-Lledo, Manuel and Bacharidis, Konstantinos and Manousaki, Victoria and Papoutsakis, Konstantinos and Argyros, Antonis and Garcia-Rodriguez, Jose}, title = {Action Anticipation at a Glimpse: To What Extent Can Multimodal Cues Replace Video?}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {276-286} }
Systematic Analysis of the Unintentional CSAM-Generation-Potential of Text-to-Image Models: Nicolas Göller,

Martin Steinebach; [pdf]
[bibtex]
@InProceedings{Goller_2026_WACV, author = {G\"oller, Nicolas and Steinebach, Martin}, title = {Systematic Analysis of the Unintentional CSAM-Generation-Potential of Text-to-Image Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {493-502} }
Inpainting of Sparse Depth Maps from Monocular Depth-from-Focus on Pixel Processor Arrays: Maciej Lewandowski,

Piotr Dudek; [pdf] [supp]
[bibtex]
@InProceedings{Lewandowski_2026_WACV, author = {Lewandowski, Maciej and Dudek, Piotr}, title = {Inpainting of Sparse Depth Maps from Monocular Depth-from-Focus on Pixel Processor Arrays}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5612-5622} }
DM3Net: Dual-Camera Super-Resolution via Domain Modulation and Multi-scale Matching: Cong Guan,

Jiacheng Ying,

Yuya Ieiri,

Osamu Yoshie; [pdf] [supp]
[bibtex]
@InProceedings{Guan_2026_WACV, author = {Guan, Cong and Ying, Jiacheng and Ieiri, Yuya and Yoshie, Osamu}, title = {DM3Net: Dual-Camera Super-Resolution via Domain Modulation and Multi-scale Matching}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7472-7481} }
Similarity-aware Probabilistic Embeddings Modeling for Video-Text Retrieval: Yuliang Huang,

Pengxu Wei,

Zhicheng Dong,

Liang Lin; [pdf]
[bibtex]
@InProceedings{Huang_2026_WACV, author = {Huang, Yuliang and Wei, Pengxu and Dong, Zhicheng and Lin, Liang}, title = {Similarity-aware Probabilistic Embeddings Modeling for Video-Text Retrieval}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4451-4460} }
Distilling What and Why: Enhancing Driver Intention Prediction with MLLMs: Sainithin Artham,

Avijit Dasgupta,

Shankar Gangisetty,

C.V. Jawahar; [pdf] [supp]
[bibtex]
@InProceedings{Artham_2026_WACV, author = {Artham, Sainithin and Dasgupta, Avijit and Gangisetty, Shankar and Jawahar, C.V.}, title = {Distilling What and Why: Enhancing Driver Intention Prediction with MLLMs}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7281-7290} }
Towards Fast and Scalable Normal Integration using Continuous Components: Francesco Milano,

Jen Jen Chung,

Lionel Ott,

Roland Siegwart; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Milano_2026_WACV, author = {Milano, Francesco and Chung, Jen Jen and Ott, Lionel and Siegwart, Roland}, title = {Towards Fast and Scalable Normal Integration using Continuous Components}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {236-244} }
ViSTA: Visual Storytelling using Multi-modal Adapters for Text-to-Image Diffusion Models: Sibo Dong,

Ismail Shaheen,

Maggie Shen,

Rupayan Mallick,

Sarah Adel Bargal; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dong_2026_WACV, author = {Dong, Sibo and Shaheen, Ismail and Shen, Maggie and Mallick, Rupayan and Bargal, Sarah Adel}, title = {ViSTA: Visual Storytelling using Multi-modal Adapters for Text-to-Image Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {12-21} }
Diffusion-Based Action Recognition Generalizes to Untrained Domains: Rogério Guimarães,

Frank Xiao,

Pietro Perona,

Markus Marks; [pdf] [supp]
[bibtex]
@InProceedings{Guimaraes_2026_WACV, author = {Guimar\~aes, Rog\'erio and Xiao, Frank and Perona, Pietro and Marks, Markus}, title = {Diffusion-Based Action Recognition Generalizes to Untrained Domains}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5919-5933} }
EVTP-IVS: Effective Visual Token Pruning For Unifying Instruction Visual Segmentation In Multi-Modal Large Language Models: Wenhui Zhu,

Xiwen Chen,

Zhipeng Wang,

Shao Tang,

Sayan Ghosh,

Xuanzhao Dong,

Rajat Koner,

Yalin Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2026_WACV, author = {Zhu, Wenhui and Chen, Xiwen and Wang, Zhipeng and Tang, Shao and Ghosh, Sayan and Dong, Xuanzhao and Koner, Rajat and Wang, Yalin}, title = {EVTP-IVS: Effective Visual Token Pruning For Unifying Instruction Visual Segmentation In Multi-Modal Large Language Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7158-7167} }
Data-Driven Lipschitz Continuity: A Cost-Effective Approach to Improve Adversarial Robustness: Erh-Chung Chen,

Pin-Yu Chen,

I-Hsin Chung,

Che-Rung Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2026_WACV, author = {Chen, Erh-Chung and Chen, Pin-Yu and Chung, I-Hsin and Lee, Che-Rung}, title = {Data-Driven Lipschitz Continuity: A Cost-Effective Approach to Improve Adversarial Robustness}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {698-707} }
MixER: From Cross-Modal to Mixed-Modal Visible-Infrared Re-Identification: Mahdi Alehdaghi,

Rajarshi Bhattacharya,

Dai Yannick,

Pourya Shamsolmoali,

Rafael M. O. Cruz,

Eric Granger; [pdf] [supp]
[bibtex]
@InProceedings{Alehdaghi_2026_WACV, author = {Alehdaghi, Mahdi and Bhattacharya, Rajarshi and Yannick, Dai and Shamsolmoali, Pourya and Cruz, Rafael M. O. and Granger, Eric}, title = {MixER: From Cross-Modal to Mixed-Modal Visible-Infrared Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3431-3440} }
A Fast, Simple, and Flexible Scale Informative Feature Transform Module for Arbitrary Scale Image Super-Resolution: Aupendu Kar,

Prabir Kumar Biswas; [pdf] [supp]
[bibtex]
@InProceedings{Kar_2026_WACV, author = {Kar, Aupendu and Biswas, Prabir Kumar}, title = {A Fast, Simple, and Flexible Scale Informative Feature Transform Module for Arbitrary Scale Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1405-1414} }
ReFineVQA: Iterative Refinement of Video Description via Feedback Generation for Video Question Answering: Jeongwan Shin,

Chan Hur,

Seongmin Cho,

Jaeho Choi,

Hyeyoung Park; [pdf] [supp]
[bibtex]
@InProceedings{Shin_2026_WACV, author = {Shin, Jeongwan and Hur, Chan and Cho, Seongmin and Choi, Jaeho and Park, Hyeyoung}, title = {ReFineVQA: Iterative Refinement of Video Description via Feedback Generation for Video Question Answering}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7647-7657} }
DUDA: Distilled Unsupervised Domain Adaptation for Lightweight Semantic Segmentation: Beomseok Kang,

Niluthpol Chowdhury Mithun,

Abhinav Rajvanshi,

Han-Pang Chiu,

Supun Samarasekera; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kang_2026_WACV, author = {Kang, Beomseok and Mithun, Niluthpol Chowdhury and Rajvanshi, Abhinav and Chiu, Han-Pang and Samarasekera, Supun}, title = {DUDA: Distilled Unsupervised Domain Adaptation for Lightweight Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8124-8135} }
Human Knowledge Integrated Multi-modal Learning for Single Source Domain Generalization: Ayan Banerjee,

Kuntal Thakur,

Sandeep Gupta; [pdf] [supp]
[bibtex]
@InProceedings{Banerjee_2026_WACV, author = {Banerjee, Ayan and Thakur, Kuntal and Gupta, Sandeep}, title = {Human Knowledge Integrated Multi-modal Learning for Single Source Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2380-2391} }
Unified Alignment Protocol: Making Sense of the Unlabeled Data in New Domains: Sabbir Ahmed,

Mamshad Nayeem Rizve,

Abdullah Al Arafat,

Jacqueline Tiffany Liu,

Rahim Hossain,

Mohaiminul Al Nahian,

Adnan Siraj Rakin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ahmed_2026_WACV, author = {Ahmed, Sabbir and Rizve, Mamshad Nayeem and Al Arafat, Abdullah and Liu, Jacqueline Tiffany and Hossain, Rahim and Al Nahian, Mohaiminul and Rakin, Adnan Siraj}, title = {Unified Alignment Protocol: Making Sense of the Unlabeled Data in New Domains}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2974-2983} }
ART-ASyn: Anatomy-aware Realistic Texture-based Anomaly Synthesis Framework for Chest X-Rays: Qinyi Cao,

Jianan Fan,

Weidong Cai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cao_2026_WACV, author = {Cao, Qinyi and Fan, Jianan and Cai, Weidong}, title = {ART-ASyn: Anatomy-aware Realistic Texture-based Anomaly Synthesis Framework for Chest X-Rays}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3792-3802} }
OPFormer: Object Pose Estimation Leveraging Foundation Model with Geometric Encoding: Artem Moroz,

Vít Zeman,

Martin Mikšík,

Elizaveta Isianova,

Miroslav David,

Pavel Burget,

Varun Burde; [pdf] [supp]
[bibtex]
@InProceedings{Moroz_2026_WACV, author = {Moroz, Artem and Zeman, V{\'\i}t and Mik\v{s}{\'\i}k, Martin and Isianova, Elizaveta and David, Miroslav and Burget, Pavel and Burde, Varun}, title = {OPFormer: Object Pose Estimation Leveraging Foundation Model with Geometric Encoding}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6621-6632} }
AnyAnomaly: Zero-Shot Customizable Video Anomaly Detection with LVLM: Sunghyun Ahn,

Youngwan Jo,

Kijung Lee,

Sein Kwon,

Inpyo Hong,

Sanghyun Park; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ahn_2026_WACV, author = {Ahn, Sunghyun and Jo, Youngwan and Lee, Kijung and Kwon, Sein and Hong, Inpyo and Park, Sanghyun}, title = {AnyAnomaly: Zero-Shot Customizable Video Anomaly Detection with LVLM}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3026-3035} }
Global Focal and Radial Distortion Averaging from Radial Fundamental Matrices for Robust Self-Calibration: Sergei Solonets,

Daniil Sinitsyn,

Daniel Cremers; [pdf]
[bibtex]
@InProceedings{Solonets_2026_WACV, author = {Solonets, Sergei and Sinitsyn, Daniil and Cremers, Daniel}, title = {Global Focal and Radial Distortion Averaging from Radial Fundamental Matrices for Robust Self-Calibration}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4777-4786} }
Enhancing Reverse Distillation with Core Exemplar Learning for Unified Multi-Class Anomaly Detection: Heechul Lim,

Min-Soo Kim,

Hyun-Boo Lee,

Suk-Ju Kang,

Kang-Wook Chon,

Haeyun Lee; [pdf]
[bibtex]
@InProceedings{Lim_2026_WACV, author = {Lim, Heechul and Kim, Min-Soo and Lee, Hyun-Boo and Kang, Suk-Ju and Chon, Kang-Wook and Lee, Haeyun}, title = {Enhancing Reverse Distillation with Core Exemplar Learning for Unified Multi-Class Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7586-7595} }
AFL-PRF: Adaptive Federated Learning for Low-Quality Data: Enhancing Performance, Robustness, and Fairness: Pinrui Yu,

Yiming Xie,

Longtian Ye,

Geng Yuan,

Ningfang Mi,

Xue Lin; [pdf]
[bibtex]
@InProceedings{Yu_2026_WACV, author = {Yu, Pinrui and Xie, Yiming and Ye, Longtian and Yuan, Geng and Mi, Ningfang and Lin, Xue}, title = {AFL-PRF: Adaptive Federated Learning for Low-Quality Data: Enhancing Performance, Robustness, and Fairness}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {402-411} }
LightGazeNet: A Lightweight GNN-based Architecture for Gaze Estimation: Heena Patel,

Anirban Chowdhury,

Pooja Jigar Choksy,

Samiksha Pradeep Pachade,

Ajinkya Puar; [pdf]
[bibtex]
@InProceedings{Patel_2026_WACV, author = {Patel, Heena and Chowdhury, Anirban and Choksy, Pooja Jigar and Pachade, Samiksha Pradeep and Puar, Ajinkya}, title = {LightGazeNet: A Lightweight GNN-based Architecture for Gaze Estimation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3710-3719} }
CountingDINO: A Training-free Pipeline for Class-Agnostic Counting using Unsupervised Backbones: Giacomo Pacini,

Lorenzo Bianchi,

Luca Ciampi,

Nicola Messina,

Giuseppe Amato,

Fabrizio Falchi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pacini_2026_WACV, author = {Pacini, Giacomo and Bianchi, Lorenzo and Ciampi, Luca and Messina, Nicola and Amato, Giuseppe and Falchi, Fabrizio}, title = {CountingDINO: A Training-free Pipeline for Class-Agnostic Counting using Unsupervised Backbones}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {806-815} }
ENCORE : A Neural Collapse Perspective on Out-of-Distribution Detection in Deep Neural Networks: A. Q. M. Sazzad Sayyed,

Nathaniel D. Bastian,

Francesco Restuccia; [pdf] [supp]
[bibtex]
@InProceedings{Sayyed_2026_WACV, author = {Sayyed, A. Q. M. Sazzad and Bastian, Nathaniel D. and Restuccia, Francesco}, title = {ENCORE : A Neural Collapse Perspective on Out-of-Distribution Detection in Deep Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2944-2953} }
FAE-Net: Fashion Attribute Editing via Disentangled Latent Conditioning in Diffusion Models: P. Rajith Bhargav,

Gaurab Bhattacharya,

B S Vivek,

Jayavardhana Gubbi; [pdf] [supp]
[bibtex]
@InProceedings{Bhargav_2026_WACV, author = {Bhargav, P. Rajith and Bhattacharya, Gaurab and Vivek, B S and Gubbi, Jayavardhana}, title = {FAE-Net: Fashion Attribute Editing via Disentangled Latent Conditioning in Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {192-201} }
Robust Multimodal Emotion Recognition from Incomplete Modalities via Query-Based Unimodal and Cross-Modal Learning: Ryo Miyoshi,

Mayu Otani,

Yuki Okafuji; [pdf] [supp]
[bibtex]
@InProceedings{Miyoshi_2026_WACV, author = {Miyoshi, Ryo and Otani, Mayu and Okafuji, Yuki}, title = {Robust Multimodal Emotion Recognition from Incomplete Modalities via Query-Based Unimodal and Cross-Modal Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4901-4911} }
R3: Reconstruction, Raw, and Rain: Deraining Directly in the Bayer Domain: Nate Rothschild,

Moshe Kimhi,

Avi Mendelson,

Chaim Baskin; [pdf]
[bibtex]
@InProceedings{Rothschild_2026_WACV, author = {Rothschild, Nate and Kimhi, Moshe and Mendelson, Avi and Baskin, Chaim}, title = {R3: Reconstruction, Raw, and Rain: Deraining Directly in the Bayer Domain}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5313-5321} }
Joint Optimization of Camera Model and Deep Neural Network for Image Recognition: Youta Noboru,

Yuko Ozasa,

Masayuki Tanaka; [pdf] [supp]
[bibtex]
@InProceedings{Noboru_2026_WACV, author = {Noboru, Youta and Ozasa, Yuko and Tanaka, Masayuki}, title = {Joint Optimization of Camera Model and Deep Neural Network for Image Recognition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7626-7635} }
SCORP: Scene-Consistent Object Refinement via Proxy Generation and Tuning: Ziwei Chen,

Ziling Liu,

Zitong Huang,

Mingqi Gao,

Feng Zheng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2026_WACV, author = {Chen, Ziwei and Liu, Ziling and Huang, Zitong and Gao, Mingqi and Zheng, Feng}, title = {SCORP: Scene-Consistent Object Refinement via Proxy Generation and Tuning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {795-805} }
DirectDrag: High-Fidelity, Mask-Free, Prompt-Free Drag-based Image Editing via Readout-Guided Feature Alignment: Sheng-Hao Liao,

Shang-Fu Chen,

Tai-Ming Huang,

Wen-Huang Cheng,

Kai-Lung Hua; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liao_2026_WACV, author = {Liao, Sheng-Hao and Chen, Shang-Fu and Huang, Tai-Ming and Cheng, Wen-Huang and Hua, Kai-Lung}, title = {DirectDrag: High-Fidelity, Mask-Free, Prompt-Free Drag-based Image Editing via Readout-Guided Feature Alignment}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8252-8261} }
Single-step Diffusion for Image Compression at Ultra-Low Bitrates: Chanung Park,

Joo Chan Lee,

Jong Hwan Ko; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Park_2026_WACV, author = {Park, Chanung and Lee, Joo Chan and Ko, Jong Hwan}, title = {Single-step Diffusion for Image Compression at Ultra-Low Bitrates}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6391-6400} }
TED-4DGS: Temporally Activated and Embedding-based Deformation for 4DGS Compression: Cheng-Yuan Ho,

He-Bi Yang,

Jui-Chiu Chiang,

Yu-Lun Liu,

Wen-Hsiao Peng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ho_2026_WACV, author = {Ho, Cheng-Yuan and Yang, He-Bi and Chiang, Jui-Chiu and Liu, Yu-Lun and Peng, Wen-Hsiao}, title = {TED-4DGS: Temporally Activated and Embedding-based Deformation for 4DGS Compression}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6371-6380} }
The Perceptual Observatory Characterizing Robustness and Grounding in MLLMs: Tejas Anvekar,

Fenil Bardoliya,

Pavan K. Turaga,

Chitta Baral,

Vivek Gupta; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Anvekar_2026_WACV, author = {Anvekar, Tejas and Bardoliya, Fenil and Turaga, Pavan K. and Baral, Chitta and Gupta, Vivek}, title = {The Perceptual Observatory Characterizing Robustness and Grounding in MLLMs}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1653-1663} }
Seeing is Believing (and Predicting): Context-Aware Multi-Human Behavior Prediction with Vision Language Models: Utsav Panchal,

Yuchen Liu,

Luigi Palmieri,

Ilche Georgievski,

Marco Aiello; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Panchal_2026_WACV, author = {Panchal, Utsav and Liu, Yuchen and Palmieri, Luigi and Georgievski, Ilche and Aiello, Marco}, title = {Seeing is Believing (and Predicting): Context-Aware Multi-Human Behavior Prediction with Vision Language Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1959-1968} }
MAESTRO: Masked AutoEncoders for Multimodal, Multitemporal, and Multispectral Earth Observation Data: Antoine Labatie,

Michael Vaccaro,

Nina Lardiere,

Anatol Garioud,

Nicolas Gonthier; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Labatie_2026_WACV, author = {Labatie, Antoine and Vaccaro, Michael and Lardiere, Nina and Garioud, Anatol and Gonthier, Nicolas}, title = {MAESTRO: Masked AutoEncoders for Multimodal, Multitemporal, and Multispectral Earth Observation Data}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {212-224} }
ASC: Learning Augmentation Severity-Consistent Representations Improves Generalization via Augmentation Search: Amirhossein Alamdar,

Hossein Jafarinia,

Mahdi Noori,

Mohammad Hossein Rohban; [pdf] [supp]
[bibtex]
@InProceedings{Alamdar_2026_WACV, author = {Alamdar, Amirhossein and Jafarinia, Hossein and Noori, Mahdi and Rohban, Mohammad Hossein}, title = {ASC: Learning Augmentation Severity-Consistent Representations Improves Generalization via Augmentation Search}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1926-1936} }
View-aware Cross-modal Distillation for Multi-view Action Recognition: Trung Thanh Nguyen,

Yasutomo Kawanishi,

Vijay John,

Takahiro Komamizu,

Ichiro Ide; [pdf] [arXiv]
[bibtex]
@InProceedings{Nguyen_2026_WACV, author = {Nguyen, Trung Thanh and Kawanishi, Yasutomo and John, Vijay and Komamizu, Takahiro and Ide, Ichiro}, title = {View-aware Cross-modal Distillation for Multi-view Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7769-7778} }
Autoregressive Styled Text Image Generation, but Make it Reliable: Carmine Zaccagnino,

Fabio Quattrini,

Vittorio Pippi,

Silvia Cascianelli,

Alessio Tonioni,

Rita Cucchiara; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zaccagnino_2026_WACV, author = {Zaccagnino, Carmine and Quattrini, Fabio and Pippi, Vittorio and Cascianelli, Silvia and Tonioni, Alessio and Cucchiara, Rita}, title = {Autoregressive Styled Text Image Generation, but Make it Reliable}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3668-3678} }
FedEFC: Federated Learning Using Enhanced Forward Correction Against Noisy Labels: Seunghun Yu,

Jin-Hyun Ahn,

Joonhyuk Kang; [pdf] [arXiv]
[bibtex]
@InProceedings{Yu_2026_WACV, author = {Yu, Seunghun and Ahn, Jin-Hyun and Kang, Joonhyuk}, title = {FedEFC: Federated Learning Using Enhanced Forward Correction Against Noisy Labels}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8094-8102} }
More Than Memory Savings: Zeroth-Order Optimization Mitigates Forgetting in Continual Learning: Wanhao Yu,

Zheng Wang,

Shuteng Niu,

Sen Lin,

Li Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2026_WACV, author = {Yu, Wanhao and Wang, Zheng and Niu, Shuteng and Lin, Sen and Yang, Li}, title = {More Than Memory Savings: Zeroth-Order Optimization Mitigates Forgetting in Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4766-4776} }
Learning to Animate Images from A Few Videos to Portray Delicate Human Actions: Haoxin Li,

Yingchen Yu,

Qilong Wu,

Hanwang Zhang,

Song Bai,

Boyang Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2026_WACV, author = {Li, Haoxin and Yu, Yingchen and Wu, Qilong and Zhang, Hanwang and Bai, Song and Li, Boyang}, title = {Learning to Animate Images from A Few Videos to Portray Delicate Human Actions}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {547-559} }
UniCalib: Targetless LiDAR-camera Calibration via Probabilistic Flow on Unified Depth Representations: Shu Han,

Xubo Zhu,

Ji Wu,

Ximeng Cai,

Wen Yang,

Huai Yu,

Gui-Song Xia; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Han_2026_WACV, author = {Han, Shu and Zhu, Xubo and Wu, Ji and Cai, Ximeng and Yang, Wen and Yu, Huai and Xia, Gui-Song}, title = {UniCalib: Targetless LiDAR-camera Calibration via Probabilistic Flow on Unified Depth Representations}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1906-1915} }
StreetView-Waste: A Multi-Task Dataset for Urban Waste Management: Diogo J. Paulo,

João Martins,

Hugo Proença,

João C. Neves; [pdf] [supp]
[bibtex]
@InProceedings{Paulo_2026_WACV, author = {Paulo, Diogo J. and Martins, Jo\~ao and Proen\c{c}a, Hugo and Neves, Jo\~ao C.}, title = {StreetView-Waste: A Multi-Task Dataset for Urban Waste Management}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3015-3025} }
Beyond the Highlights: Video Retrieval with Salient and Surrounding Contexts: Jaehun Bang,

Moon Ye-Bin,

Tae-Hyun Oh,

Kyungdon Joo; [pdf] [supp]
[bibtex]
@InProceedings{Bang_2026_WACV, author = {Bang, Jaehun and Ye-Bin, Moon and Oh, Tae-Hyun and Joo, Kyungdon}, title = {Beyond the Highlights: Video Retrieval with Salient and Surrounding Contexts}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2188-2197} }
DF-Mamba: Deformable State Space Modeling for 3D Hand Pose Estimation in Interactions: Yifan Zhou,

Takehiko Ohkawa,

Guwenxiao Zhou,

Kanoko Goto,

Takumi Hirose,

Yusuke Sekikawa,

Nakamasa Inoue; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2026_WACV, author = {Zhou, Yifan and Ohkawa, Takehiko and Zhou, Guwenxiao and Goto, Kanoko and Hirose, Takumi and Sekikawa, Yusuke and Inoue, Nakamasa}, title = {DF-Mamba: Deformable State Space Modeling for 3D Hand Pose Estimation in Interactions}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5352-5363} }
Eye-for-an-eye: Appearance Transfer with Dense Semantic Correspondence in Diffusion Models: Sooyeon Go,

Kyungmook Choi,

Minjung Shin,

Youngjung Uh; [pdf] [supp]
[bibtex]
@InProceedings{Go_2026_WACV, author = {Go, Sooyeon and Choi, Kyungmook and Shin, Minjung and Uh, Youngjung}, title = {Eye-for-an-eye: Appearance Transfer with Dense Semantic Correspondence in Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4641-4650} }
PiSA: A Self-Augmented Data Engine and Training Strategy for 3D Understanding with Large Models: Zilu Guo,

Hongbin Lin,

Zhihao Yuan,

Chaoda Zheng,

Pengshuo Qiu,

Dongzhi Jiang,

Renrui Zhang,

Chun-Mei Feng,

Zhen Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guo_2026_WACV, author = {Guo, Zilu and Lin, Hongbin and Yuan, Zhihao and Zheng, Chaoda and Qiu, Pengshuo and Jiang, Dongzhi and Zhang, Renrui and Feng, Chun-Mei and Li, Zhen}, title = {PiSA: A Self-Augmented Data Engine and Training Strategy for 3D Understanding with Large Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1273-1283} }
Analysis of Text Accuracy and Visual Alignment in Vision-Language Models for Artistic Text Generation: Fatima Alderazi,

Motaz Alfarraj; [pdf]
[bibtex]
@InProceedings{Alderazi_2026_WACV, author = {Alderazi, Fatima and Alfarraj, Motaz}, title = {Analysis of Text Accuracy and Visual Alignment in Vision-Language Models for Artistic Text Generation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {879-887} }
Do Generative Video Models Understand Physical Principles?: Saman Motamed,

Laura Culp,

Kevin Swersky,

Priyank Jaini,

Robert Geirhos; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Motamed_2026_WACV, author = {Motamed, Saman and Culp, Laura and Swersky, Kevin and Jaini, Priyank and Geirhos, Robert}, title = {Do Generative Video Models Understand Physical Principles?}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {948-958} }
AnyBald: Toward Realistic Diffusion-Based Hair Removal In-The-Wild: Yongjun Choi,

Seungoh Han,

Soomin Kim,

Sumin Son,

Mohsen Rohani,

Edgar Maucourant,

Dongbo Min,

Kyungdon Joo; [pdf] [supp]
[bibtex]
@InProceedings{Choi_2026_WACV, author = {Choi, Yongjun and Han, Seungoh and Kim, Soomin and Son, Sumin and Rohani, Mohsen and Maucourant, Edgar and Min, Dongbo and Joo, Kyungdon}, title = {AnyBald: Toward Realistic Diffusion-Based Hair Removal In-The-Wild}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2220-2230} }
A Multi-Agent Diffusion Approach for MRI Anomaly Segmentation via Modality-Specific LoRA Specialization: Wafa Al Ghallabi,

Muhammad Zaigham Zaheer,

Ritesh Thawkar,

Omkar Thawakar,

Salman Khan,

Fahad Shahbaz Khan; [pdf]
[bibtex]
@InProceedings{Al_Ghallabi_2026_WACV, author = {Al Ghallabi, Wafa and Zaheer, Muhammad Zaigham and Thawkar, Ritesh and Thawakar, Omkar and Khan, Salman and Khan, Fahad Shahbaz}, title = {A Multi-Agent Diffusion Approach for MRI Anomaly Segmentation via Modality-Specific LoRA Specialization}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {128-137} }
ZonUI-3B: Competitive GUI Grounding with a 3B VLM Trained on a Single Consumer GPU: ZongHan Hsieh,

ShengJing Yang,

Tzer-Jen Wei; [pdf] [supp]
[bibtex]
@InProceedings{Hsieh_2026_WACV, author = {Hsieh, ZongHan and Yang, ShengJing and Wei, Tzer-Jen}, title = {ZonUI-3B: Competitive GUI Grounding with a 3B VLM Trained on a Single Consumer GPU}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {959-966} }
LogicCBMs: Logic-Enhanced Concept-Based Learning: Deepika SN Vemuri,

Gautham Bellamkonda,

Aditya Pola,

Vineeth N Balasubramanian; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Vemuri_2026_WACV, author = {Vemuri, Deepika SN and Bellamkonda, Gautham and Pola, Aditya and Balasubramanian, Vineeth N}, title = {LogicCBMs: Logic-Enhanced Concept-Based Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6039-6048} }
Sketch2Stitch: GANs for Abstract Sketch-Based Dress Synthesis: Faizan Farooq Khan,

Eslam Abdelrahman Bakr,

Davide Morelli,

Marcella Cornia,

Rita Cucchiara,

Mohamed Elhoseiny; [pdf] [supp]
[bibtex]
@InProceedings{Khan_2026_WACV, author = {Khan, Faizan Farooq and Bakr, Eslam Abdelrahman and Morelli, Davide and Cornia, Marcella and Cucchiara, Rita and Elhoseiny, Mohamed}, title = {Sketch2Stitch: GANs for Abstract Sketch-Based Dress Synthesis}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2209-2219} }
GAEA: A Geolocation Aware Conversational Assistant: Ron Campos,

Ashmal Vayani,

Parth Parag Kulkarni,

Rohit Gupta,

Aizan Zafar,

Aritra Dutta,

Mubarak Shah; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Campos_2026_WACV, author = {Campos, Ron and Vayani, Ashmal and Kulkarni, Parth Parag and Gupta, Rohit and Zafar, Aizan and Dutta, Aritra and Shah, Mubarak}, title = {GAEA: A Geolocation Aware Conversational Assistant}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5236-5246} }
FNOPT: Resolution-Agnostic, Self-Supervised Cloth Simulation using Meta-Optimization with Fourier Neural Operators: Ruochen Chen,

Thuy Tran,

Shaifali Parashar; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2026_WACV, author = {Chen, Ruochen and Tran, Thuy and Parashar, Shaifali}, title = {FNOPT: Resolution-Agnostic, Self-Supervised Cloth Simulation using Meta-Optimization with Fourier Neural Operators}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7116-7125} }
You May Speak Freely: Improving the Fine-Grained Visual Recognition Capabilities of Multimodal Large Language Models with Answer Extraction: Logan Lawrence,

Oindrila Saha,

Megan Wei,

Chen Sun,

Subhransu Maji,

Grant Van Horn; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lawrence_2026_WACV, author = {Lawrence, Logan and Saha, Oindrila and Wei, Megan and Sun, Chen and Maji, Subhransu and Van Horn, Grant}, title = {You May Speak Freely: Improving the Fine-Grained Visual Recognition Capabilities of Multimodal Large Language Models with Answer Extraction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1428-1437} }
Diversity Preserving Coresets for Image Quality Assessment: Arpita Nema,

Hanwei Zhu,

Xi Zhang,

Weisi Lin; [pdf] [supp]
[bibtex]
@InProceedings{Nema_2026_WACV, author = {Nema, Arpita and Zhu, Hanwei and Zhang, Xi and Lin, Weisi}, title = {Diversity Preserving Coresets for Image Quality Assessment}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7925-7934} }
Frequency Is What You Need: Considering Word Frequency When Text Masking Benefits Vision-Language Model Pre-training: Mingliang Liang,

Martha Larson; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liang_2026_WACV, author = {Liang, Mingliang and Larson, Martha}, title = {Frequency Is What You Need: Considering Word Frequency When Text Masking Benefits Vision-Language Model Pre-training}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3771-3780} }
RoadBench: A Vision-Language Foundation Model and Benchmark for Road Damage Understanding: Xi Xiao,

Yunbei Zhang,

Janet Wang,

Lin Zhao,

Yuxiang Wei,

Hengjia Li,

Yanshu Li,

Xiao Wang,

Swalpa Kumar Roy,

Hao Xu,

Tianyang Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Xiao_2026_WACV, author = {Xiao, Xi and Zhang, Yunbei and Wang, Janet and Zhao, Lin and Wei, Yuxiang and Li, Hengjia and Li, Yanshu and Wang, Xiao and Roy, Swalpa Kumar and Xu, Hao and Wang, Tianyang}, title = {RoadBench: A Vision-Language Foundation Model and Benchmark for Road Damage Understanding}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6016-6026} }
Evaluating Text-to-Image and Text-to-Video Synthesis with a Conditional Frechet Distance: Jaywon Koo,

Jefferson Hernandez,

Moayed Haji-Ali,

Ziyan Yang,

Vicente Ordonez; [pdf] [supp]
[bibtex]
@InProceedings{Koo_2026_WACV, author = {Koo, Jaywon and Hernandez, Jefferson and Haji-Ali, Moayed and Yang, Ziyan and Ordonez, Vicente}, title = {Evaluating Text-to-Image and Text-to-Video Synthesis with a Conditional Frechet Distance}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2052-2062} }
Optimization-Free Style Transfer for 3D Gaussian Splats: Raphael Du Sablon,

David Hart; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Du_Sablon_2026_WACV, author = {Du Sablon, Raphael and Hart, David}, title = {Optimization-Free Style Transfer for 3D Gaussian Splats}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8041-8051} }
AEON: Adaptive Embedding Optimized Noise for Robust Watermarking in Diffusion Models: Muhammad Shahid Muneer,

Simon S. Woo; [pdf] [supp]
[bibtex]
@InProceedings{Muneer_2026_WACV, author = {Muneer, Muhammad Shahid and Woo, Simon S.}, title = {AEON: Adaptive Embedding Optimized Noise for Robust Watermarking in Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5406-5415} }
mEOL: Training-Free Instruction-Guided Multimodal Embedder for Vector Graphics and Image Retrieval: Kyeong Seon Kim,

Baek Seong-Eun,

Lee Jung-Mok,

Tae-Hyun Oh; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2026_WACV, author = {Kim, Kyeong Seon and Seong-Eun, Baek and Jung-Mok, Lee and Oh, Tae-Hyun}, title = {mEOL: Training-Free Instruction-Guided Multimodal Embedder for Vector Graphics and Image Retrieval}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1191-1200} }
GateFusion: Hierarchical Gated Cross-Modal Fusion for Active Speaker Detection: Yu Wang,

Juhyung Ha,

Frangil M. Ramirez,

Yuchen Wang,

David J. Crandall; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2026_WACV, author = {Wang, Yu and Ha, Juhyung and Ramirez, Frangil M. and Wang, Yuchen and Crandall, David J.}, title = {GateFusion: Hierarchical Gated Cross-Modal Fusion for Active Speaker Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1074-1083} }
From Cognitive Priors to Instance Semantics: A Unified Framework for Multi-task Affective Computing: Guanyu Hu,

Dimitrios Kollias,

Xinyu Yang; [pdf]
[bibtex]
@InProceedings{Hu_2026_WACV, author = {Hu, Guanyu and Kollias, Dimitrios and Yang, Xinyu}, title = {From Cognitive Priors to Instance Semantics: A Unified Framework for Multi-task Affective Computing}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8551-8562} }
Detection-Driven Object Count Optimization for Text-to-Image Diffusion Models: Oz Zafar,

Yuval Cohen,

Lior Wolf,

Idan Schwartz; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zafar_2026_WACV, author = {Zafar, Oz and Cohen, Yuval and Wolf, Lior and Schwartz, Idan}, title = {Detection-Driven Object Count Optimization for Text-to-Image Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1885-1894} }
PoseAdapt: Sustainable Human Pose Estimation via Continual Learning Benchmarks and Toolkit: Muhammad Saif Ullah Khan,

Didier Stricker; [pdf] [arXiv]
[bibtex]
@InProceedings{Khan_2026_WACV, author = {Khan, Muhammad Saif Ullah and Stricker, Didier}, title = {PoseAdapt: Sustainable Human Pose Estimation via Continual Learning Benchmarks and Toolkit}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6840-6850} }
Fully Unsupervised Self-debiasing of Text-to-Image Diffusion Models: Korada Sri Vardhana,

Shrikrishna Lolla,

Soma Biswas; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Vardhana_2026_WACV, author = {Vardhana, Korada Sri and Lolla, Shrikrishna and Biswas, Soma}, title = {Fully Unsupervised Self-debiasing of Text-to-Image Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1221-1230} }
Cycle-Consistent Multi-Graph Matching for Self-Supervised Annotation of C. Elegans: Sebastian Stricker,

Christoph Karg,

Lisa Hutschenreiter,

Bogdan Savchynskyy,

Dagmar Kainmueller; [pdf] [supp]
[bibtex]
@InProceedings{Stricker_2026_WACV, author = {Stricker, Sebastian and Karg, Christoph and Hutschenreiter, Lisa and Savchynskyy, Bogdan and Kainmueller, Dagmar}, title = {Cycle-Consistent Multi-Graph Matching for Self-Supervised Annotation of C. Elegans}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7208-7217} }
Online Episodic Memory Visual Query Localization with Egocentric Streaming Object Memory: Zaira Manigrasso,

Matteo Dunnhofer,

Antonino Furnari,

Moritz Nottebaum,

Antonio Finocchiaro,

Davide Marana,

Rosario Forte,

Giovanni Maria Farinella,

Christian Micheloni; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Manigrasso_2026_WACV, author = {Manigrasso, Zaira and Dunnhofer, Matteo and Furnari, Antonino and Nottebaum, Moritz and Finocchiaro, Antonio and Marana, Davide and Forte, Rosario and Farinella, Giovanni Maria and Micheloni, Christian}, title = {Online Episodic Memory Visual Query Localization with Egocentric Streaming Object Memory}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3951-3960} }
Visual Detector Compression via Location-Aware Discriminant Analysis: Qizhen Lan,

Jung Im Choi,

Qing Tian; [pdf] [arXiv]
[bibtex]
@InProceedings{Lan_2026_WACV, author = {Lan, Qizhen and Choi, Jung Im and Tian, Qing}, title = {Visual Detector Compression via Location-Aware Discriminant Analysis}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3546-3555} }
Salience-SGG: Enhancing Unbiased Scene Graph Generation with Iterative Salience Estimation: Runfeng Qu,

Ole Hall,

Pia K Bideau,

Julie Ouerfelli-Ethier,

Martin Rolfs,

Klaus Obermayer,

Olaf Hellwich; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Qu_2026_WACV, author = {Qu, Runfeng and Hall, Ole and Bideau, Pia K and Ouerfelli-Ethier, Julie and Rolfs, Martin and Obermayer, Klaus and Hellwich, Olaf}, title = {Salience-SGG: Enhancing Unbiased Scene Graph Generation with Iterative Salience Estimation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1032-1042} }
SPAR-Det: Segmentation-guided and Prior-Aided Routing for Small Object Detection: Seungchan Kwon,

Gyuil Lim,

Youngjoon Han; [pdf] [supp]
[bibtex]
@InProceedings{Kwon_2026_WACV, author = {Kwon, Seungchan and Lim, Gyuil and Han, Youngjoon}, title = {SPAR-Det: Segmentation-guided and Prior-Aided Routing for Small Object Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2146-2155} }
Semi-supervised Key-Point Estimation for Echocardiography Video: Seok-Hwan Oh,

Hyeon-Jik Lee,

Guil Jung,

Myeong-Gee Kim,

Young-Min Kim,

Hyuksool Kwon,

Hyeon-Min Bae; [pdf] [supp]
[bibtex]
@InProceedings{Oh_2026_WACV, author = {Oh, Seok-Hwan and Lee, Hyeon-Jik and Jung, Guil and Kim, Myeong-Gee and Kim, Young-Min and Kwon, Hyuksool and Bae, Hyeon-Min}, title = {Semi-supervised Key-Point Estimation for Echocardiography Video}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5682-5692} }
Locally Explaining Prediction Behavior via Gradual Interventions and Measuring Property Gradients: Niklas Penzel,

Joachim Denzler; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Penzel_2026_WACV, author = {Penzel, Niklas and Denzler, Joachim}, title = {Locally Explaining Prediction Behavior via Gradual Interventions and Measuring Property Gradients}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7398-7408} }
Scalable Video Action Anticipation with Cross Linear Attentive Memory: Zeyun Zhong,

Manuel Martin,

David Schneider,

David J. Lerch,

Chengzhi Wu,

Frederik Diederichs,

Juergen Gall,

Jürgen Beyerer; [pdf] [supp]
[bibtex]
@InProceedings{Zhong_2026_WACV, author = {Zhong, Zeyun and Martin, Manuel and Schneider, David and Lerch, David J. and Wu, Chengzhi and Diederichs, Frederik and Gall, Juergen and Beyerer, J\"urgen}, title = {Scalable Video Action Anticipation with Cross Linear Attentive Memory}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8113-8123} }
Are All Marine Species Created Equal? Performance Disparities in Underwater Object Detection: Melanie Wille,

Tobias Fischer,

Scarlett Raine; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wille_2026_WACV, author = {Wille, Melanie and Fischer, Tobias and Raine, Scarlett}, title = {Are All Marine Species Created Equal? Performance Disparities in Underwater Object Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4556-4565} }
MoRe: Monocular Geometry Refinement via Graph Optimization for Cross-View Consistency: Dongki Jung,

Jaehoon Choi,

Yonghan Lee,

Sungmin Eum,

Heesung Kwon,

Dinesh Manocha; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jung_2026_WACV, author = {Jung, Dongki and Choi, Jaehoon and Lee, Yonghan and Eum, Sungmin and Kwon, Heesung and Manocha, Dinesh}, title = {MoRe: Monocular Geometry Refinement via Graph Optimization for Cross-View Consistency}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4838-4848} }
FLARES: Fast and Accurate LiDAR Multi-Range Semantic Segmentation: Bin Yang,

Alexandru Paul Condurache; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2026_WACV, author = {Yang, Bin and Condurache, Alexandru Paul}, title = {FLARES: Fast and Accurate LiDAR Multi-Range Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3451-3461} }
Mitigating the Modality Gap: Few-Shot Out-of-Distribution Detection with Multi-modal Prototypes and Image Bias Estimation: Yimu Wang,

Evelien Riddell,

Adrian Chow,

Sean Sedwards,

Krzysztof Czarnecki; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2026_WACV, author = {Wang, Yimu and Riddell, Evelien and Chow, Adrian and Sedwards, Sean and Czarnecki, Krzysztof}, title = {Mitigating the Modality Gap: Few-Shot Out-of-Distribution Detection with Multi-modal Prototypes and Image Bias Estimation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2741-2751} }
FairVLM: Enhancing Fairness and Prompt Sensitivity in Vision Language Models for Medical Image Segmentation: Md Motiur Rahman,

Saeka Rahman,

Smriti Bhatt,

Miad Faezipour; [pdf] [supp]
[bibtex]
@InProceedings{Rahman_2026_WACV, author = {Rahman, Md Motiur and Rahman, Saeka and Bhatt, Smriti and Faezipour, Miad}, title = {FairVLM: Enhancing Fairness and Prompt Sensitivity in Vision Language Models for Medical Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7450-7460} }
NRGMark: Localized Watermarking for Energy Transparency in Images: Shruti Agarwal,

Élie Michel,

Vishal Asnani,

Tania Mathern,

John Collomosse; [pdf]
[bibtex]
@InProceedings{Agarwal_2026_WACV, author = {Agarwal, Shruti and Michel, \'Elie and Asnani, Vishal and Mathern, Tania and Collomosse, John}, title = {NRGMark: Localized Watermarking for Energy Transparency in Images}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7779-7788} }
V2XScene: Multi-View Consistent 3D Scene Simulation for Collaborative Perception: Yanfei Li,

Yi Gong,

Yuan Zeng; [pdf]
[bibtex]
@InProceedings{Li_2026_WACV, author = {Li, Yanfei and Gong, Yi and Zeng, Yuan}, title = {V2XScene: Multi-View Consistent 3D Scene Simulation for Collaborative Perception}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6569-6579} }
SymNet: A Multi-Task Network for Joint Radio Map Reconstruction and Transmitter Localization: Lyuzhou Ye,

Thanh Dat Le,

Yan Huang; [pdf]
[bibtex]
@InProceedings{Ye_2026_WACV, author = {Ye, Lyuzhou and Le, Thanh Dat and Huang, Yan}, title = {SymNet: A Multi-Task Network for Joint Radio Map Reconstruction and Transmitter Localization}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {150-159} }
Safe Vision-Language Models via Unsafe Weights Manipulation: Moreno D'incà,

Elia Peruzzo,

Xingqian Xu,

Humphrey Shi,

Nicu Sebe,

Massimiliano Mancini; [pdf] [supp]
[bibtex]
@InProceedings{D'inca_2026_WACV, author = {D'inc\`a, Moreno and Peruzzo, Elia and Xu, Xingqian and Shi, Humphrey and Sebe, Nicu and Mancini, Massimiliano}, title = {Safe Vision-Language Models via Unsafe Weights Manipulation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4682-4692} }
CONCORD: Concept-Informed Diffusion for Dataset Distillation: Jianyang Gu,

Haonan Wang,

Ruoxi Jia,

Saeed Vahidian,

Vyacheslav Kungurtsev,

Wei Jiang,

Yiran Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gu_2026_WACV, author = {Gu, Jianyang and Wang, Haonan and Jia, Ruoxi and Vahidian, Saeed and Kungurtsev, Vyacheslav and Jiang, Wei and Chen, Yiran}, title = {CONCORD: Concept-Informed Diffusion for Dataset Distillation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5258-5268} }
CAPE: A CLIP-Aware Pointing Ensemble of Complementary Heatmap Cues for Embodied Reference Understanding: Fevziye Irem Eyiokur,

Dogucan Yaman,

Hazım Kemal Ekenel,

Alexander Waibel; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Eyiokur_2026_WACV, author = {Eyiokur, Fevziye Irem and Yaman, Dogucan and Ekenel, Haz{\i}m Kemal and Waibel, Alexander}, title = {CAPE: A CLIP-Aware Pointing Ensemble of Complementary Heatmap Cues for Embodied Reference Understanding}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3939-3950} }
Learning Action Hierarchies via Hybrid Geometric Diffusion: Arjun Ramesh Kaushik,

Nalini K. Ratha,

Venu Govindaraju; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kaushik_2026_WACV, author = {Kaushik, Arjun Ramesh and Ratha, Nalini K. and Govindaraju, Venu}, title = {Learning Action Hierarchies via Hybrid Geometric Diffusion}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3129-3139} }
Advancing Multimodal LLMs by Large-Scale 3D Visual Instruction Dataset Generation: Liu He,

Xiao Zeng,

Yizhi Song,

Albert Y. C. Chen,

Lu Xia,

Shashwat Verma,

Sankalp Dayal,

Min Sun,

Cheng-Hao Kuo,

Daniel Aliaga; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{He_2026_WACV, author = {He, Liu and Zeng, Xiao and Song, Yizhi and Chen, Albert Y. C. and Xia, Lu and Verma, Shashwat and Dayal, Sankalp and Sun, Min and Kuo, Cheng-Hao and Aliaga, Daniel}, title = {Advancing Multimodal LLMs by Large-Scale 3D Visual Instruction Dataset Generation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5886-5897} }
Bi-ICE: An Inner Interpretable Framework for Image Classification via Bi-directional Interactions between Concept and Input Embeddings: Jinyung Hong,

Yearim Kim,

Keun Hee Park,

Sangyu Han,

Nojun Kwak,

Theodore P. Pavlic; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hong_2026_WACV, author = {Hong, Jinyung and Kim, Yearim and Park, Keun Hee and Han, Sangyu and Kwak, Nojun and Pavlic, Theodore P.}, title = {Bi-ICE: An Inner Interpretable Framework for Image Classification via Bi-directional Interactions between Concept and Input Embeddings}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3835-3845} }
Transformer-Based Inpainting for Real-Time 3D Streaming in Sparse Multi-Camera Setups: Leif Van Holland,

Domenic Zingsheim,

Mana Takhsha,

Hannah Dröge,

Patrick Stotko,

Markus Plack,

Reinhard Klein; [pdf] [supp]
[bibtex]
@InProceedings{Van_Holland_2026_WACV, author = {Van Holland, Leif and Zingsheim, Domenic and Takhsha, Mana and Dr\"oge, Hannah and Stotko, Patrick and Plack, Markus and Klein, Reinhard}, title = {Transformer-Based Inpainting for Real-Time 3D Streaming in Sparse Multi-Camera Setups}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4587-4598} }
Test-Time Adaptation for Video Highlight Detection Using Meta-Auxiliary Learning and Cross-Modality Hallucinations: Zahidul Islam,

Sujoy Paul,

Mrigank Rochan; [pdf] [arXiv]
[bibtex]
@InProceedings{Islam_2026_WACV, author = {Islam, Zahidul and Paul, Sujoy and Rochan, Mrigank}, title = {Test-Time Adaptation for Video Highlight Detection Using Meta-Auxiliary Learning and Cross-Modality Hallucinations}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6893-6902} }
INRetouch: Context Aware Implicit Neural Representation for Photography Retouching: Omar Elezabi,

Marcos V. Conde,

Zongwei Wu,

Radu Timofte; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Elezabi_2026_WACV, author = {Elezabi, Omar and Conde, Marcos V. and Wu, Zongwei and Timofte, Radu}, title = {INRetouch: Context Aware Implicit Neural Representation for Photography Retouching}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5560-5569} }
3DSceneEditor: Controllable 3D Scene Editing with Gaussian Splatting: Ziyang Yan,

Yihua Shao,

Minwen Liao,

Siyu Chen,

Nan Wang,

Muyuan Lin,

Jenq-Neng Hwang,

Hao Zhao,

Fabio Remondino,

Lei Li; [pdf] [supp]
[bibtex]
@InProceedings{Yan_2026_WACV, author = {Yan, Ziyang and Shao, Yihua and Liao, Minwen and Chen, Siyu and Wang, Nan and Lin, Muyuan and Hwang, Jenq-Neng and Zhao, Hao and Remondino, Fabio and Li, Lei}, title = {3DSceneEditor: Controllable 3D Scene Editing with Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1852-1863} }
Grounding Degradations in Natural Language for All-In-One Video Restoration: Muhammad Kamran Janjua,

Amirhosein Ghasemabadi,

Kunlin Zhang,

Mohammad Salameh,

Chao Gao,

Di Niu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Janjua_2026_WACV, author = {Janjua, Muhammad Kamran and Ghasemabadi, Amirhosein and Zhang, Kunlin and Salameh, Mohammad and Gao, Chao and Niu, Di}, title = {Grounding Degradations in Natural Language for All-In-One Video Restoration}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5734-5743} }
Stabilizing Direct Training of Spiking Neural Networks: Membrane Potential Initialization and Threshold-robust Surrogate Gradient: Hyunho Kook,

Byeongho Yu,

Jeong Min Oh,

Eunhyeok Park; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kook_2026_WACV, author = {Kook, Hyunho and Yu, Byeongho and Oh, Jeong Min and Park, Eunhyeok}, title = {Stabilizing Direct Training of Spiking Neural Networks: Membrane Potential Initialization and Threshold-robust Surrogate Gradient}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8500-8510} }
RegionAligner: Bridging Ego-Exo Views for Object Correspondence via Unified Text-Visual Learning: Yuhao Su,

Ehsan Elhamifar; [pdf] [supp]
[bibtex]
@InProceedings{Su_2026_WACV, author = {Su, Yuhao and Elhamifar, Ehsan}, title = {RegionAligner: Bridging Ego-Exo Views for Object Correspondence via Unified Text-Visual Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3265-3274} }
Matching Semantically Similar Non-Identical Objects: Yusuke Marumo,

Kazuhiko Kawamoto,

Satomi Tanaka,

Shigenobu Hirano,

Hiroshi Kera; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Marumo_2026_WACV, author = {Marumo, Yusuke and Kawamoto, Kazuhiko and Tanaka, Satomi and Hirano, Shigenobu and Kera, Hiroshi}, title = {Matching Semantically Similar Non-Identical Objects}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2752-2764} }
SphereEdit: Spherical Semantic Editing in Diffusion Models: Salamata Konate,

Hassan Hamidi,

Elham Dolatabadi,

Frank Rudzicz,

Laleh Seyyed-Kalantari; [pdf] [supp]
[bibtex]
@InProceedings{Konate_2026_WACV, author = {Konate, Salamata and Hamidi, Hassan and Dolatabadi, Elham and Rudzicz, Frank and Seyyed-Kalantari, Laleh}, title = {SphereEdit: Spherical Semantic Editing in Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8084-8093} }
Pyramidal Spectrum: Frequency-based Hierarchically Vector Quantized VAE for Videos: Tushar Prakash,

Onkar Susladkar,

Sparsh Mittal,

Inderjit S Dhillon; [pdf] [supp]
[bibtex]
@InProceedings{Prakash_2026_WACV, author = {Prakash, Tushar and Susladkar, Onkar and Mittal, Sparsh and Dhillon, Inderjit S}, title = {Pyramidal Spectrum: Frequency-based Hierarchically Vector Quantized VAE for Videos}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2073-2082} }
Large Sign Language Models: Toward 3D American Sign Language Translation: Sen Zhang,

Xiaoxiao He,

Di Liu,

Zhaoyang Xia,

Mingyu Zhao,

Chaowei Tan,

Vivian Li,

Bo Liu,

Dimitris N. Metaxas,

Mubbasir Kapadia; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2026_WACV, author = {Zhang, Sen and He, Xiaoxiao and Liu, Di and Xia, Zhaoyang and Zhao, Mingyu and Tan, Chaowei and Li, Vivian and Liu, Bo and Metaxas, Dimitris N. and Kapadia, Mubbasir}, title = {Large Sign Language Models: Toward 3D American Sign Language Translation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3109-3119} }
Learning Mask-Aware Offsets: Two-branch Deformable Attention Networks for Inpainting with Masked Region Avoidance: Hyeongseok Oh,

Joonki Paik; [pdf] [supp]
[bibtex]
@InProceedings{Oh_2026_WACV, author = {Oh, Hyeongseok and Paik, Joonki}, title = {Learning Mask-Aware Offsets: Two-branch Deformable Attention Networks for Inpainting with Masked Region Avoidance}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1022-1031} }
QuadraNet V2: Efficient and Sustainable Training of High-Order Neural Networks with Quadratic Adaptation: Chenhui Xu,

Fuxun Yu,

Jinjun Xiong,

Xiang Chen; [pdf] [arXiv]
[bibtex]
@InProceedings{Xu_2026_WACV, author = {Xu, Chenhui and Yu, Fuxun and Xiong, Jinjun and Chen, Xiang}, title = {QuadraNet V2: Efficient and Sustainable Training of High-Order Neural Networks with Quadratic Adaptation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1365-1373} }
Occlusion Boundary and Depth: Mutual Enhancement via Multi-Task Learning: Lintao Xu,

Yinghao Wang,

Chaohui Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2026_WACV, author = {Xu, Lintao and Wang, Yinghao and Wang, Chaohui}, title = {Occlusion Boundary and Depth: Mutual Enhancement via Multi-Task Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4427-4437} }
3D Superquadric Splatting: Daniel MacSwayne,

Ales Leonardis,

Jianbo Jiao; [pdf] [supp]
[bibtex]
@InProceedings{MacSwayne_2026_WACV, author = {MacSwayne, Daniel and Leonardis, Ales and Jiao, Jianbo}, title = {3D Superquadric Splatting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5154-5163} }
S2O: Static to Openable Enhancement for Articulated 3D Objects: Denys Iliash,

Hanxiao Jiang,

Yiming Zhang,

Manolis Savva,

Angel X. Chang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Iliash_2026_WACV, author = {Iliash, Denys and Jiang, Hanxiao and Zhang, Yiming and Savva, Manolis and Chang, Angel X.}, title = {S2O: Static to Openable Enhancement for Articulated 3D Objects}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6785-6795} }
Personalized Image Privacy Advisors via Federated Daisy-Chaining: Sourasekhar Banerjee,

Vengateswaran Subramaniam,

Debaditya Roy,

Vigneshwaran Subbaraju,

Monowar Bhuyan; [pdf] [supp]
[bibtex]
@InProceedings{Banerjee_2026_WACV, author = {Banerjee, Sourasekhar and Subramaniam, Vengateswaran and Roy, Debaditya and Subbaraju, Vigneshwaran and Bhuyan, Monowar}, title = {Personalized Image Privacy Advisors via Federated Daisy-Chaining}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2808-2817} }
PoseGaussian: Pose-Driven Novel View Synthesis for Robust 3D Human Reconstruction: Ju Shen,

Chen Chen,

Tam V. Nguyen,

Vijayan K. Asari; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shen_2026_WACV, author = {Shen, Ju and Chen, Chen and Nguyen, Tam V. and Asari, Vijayan K.}, title = {PoseGaussian: Pose-Driven Novel View Synthesis for Robust 3D Human Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5004-5015} }
UniGaze: Towards Universal Gaze Estimation via Large-scale Pre-Training: Jiawei Qin,

Xucong Zhang,

Yusuke Sugano; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Qin_2026_WACV, author = {Qin, Jiawei and Zhang, Xucong and Sugano, Yusuke}, title = {UniGaze: Towards Universal Gaze Estimation via Large-scale Pre-Training}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5809-5820} }
One Model, Many Behaviors: Training-Induced Effects on Out-of-Distribution Detection: Gerhard Krumpl,

Henning Avenhaus,

Horst Possegger; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Krumpl_2026_WACV, author = {Krumpl, Gerhard and Avenhaus, Henning and Possegger, Horst}, title = {One Model, Many Behaviors: Training-Induced Effects on Out-of-Distribution Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4128-4138} }
DNA: Dual-branch Network with Adaptation for Open-Set Online Handwriting Generation: Tsai-Ling Huang,

Nhat-Tuong Do-Tran,

Ngoc-Hoang-Lam Le,

Hong-Han Shuai,

Ching-Chun Huang; [pdf] [supp]
[bibtex]
@InProceedings{Huang_2026_WACV, author = {Huang, Tsai-Ling and Do-Tran, Nhat-Tuong and Le, Ngoc-Hoang-Lam and Shuai, Hong-Han and Huang, Ching-Chun}, title = {DNA: Dual-branch Network with Adaptation for Open-Set Online Handwriting Generation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4170-4179} }
Universal Neural Architecture Space: Covering ConvNets, Transformers and Everything in Between: Ondrej Tybl,

Lukas Neumann; [pdf] [arXiv]
[bibtex]
@InProceedings{Tybl_2026_WACV, author = {Tybl, Ondrej and Neumann, Lukas}, title = {Universal Neural Architecture Space: Covering ConvNets, Transformers and Everything in Between}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3679-3688} }
Splatter Layout: Geometry-embedded 3D Reconstruction via Surface Unfolding: Bryan Heryanto,

Tackgeun You,

Chanwoo Kim,

Hwasup Lim; [pdf] [supp]
[bibtex]
@InProceedings{Heryanto_2026_WACV, author = {Heryanto, Bryan and You, Tackgeun and Kim, Chanwoo and Lim, Hwasup}, title = {Splatter Layout: Geometry-embedded 3D Reconstruction via Surface Unfolding}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7709-7718} }
Optimal Transport for Rectified Flow Image Editing: Unifying Inversion-Based and Direct Methods: Marian Lupaşcu,

Mihai Sorin Stupariu; [pdf] [supp]
[bibtex]
@InProceedings{Lupascu_2026_WACV, author = {Lupa\c{s}cu, Marian and Stupariu, Mihai Sorin}, title = {Optimal Transport for Rectified Flow Image Editing: Unifying Inversion-Based and Direct Methods}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6764-6774} }
Prompt-OT: An Optimal Transport Regularization Paradigm for Knowledge Preservation in Vision-Language Model Adaptation: Xiwen Chen,

Wenhui Zhu,

Peijie Qiu,

Hao Wang,

Huayu Li,

Haiyu Wu,

Xuanzhao Dong,

Aristeidis Sotiras,

Yalin Wang,

Abolfazl Razi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2026_WACV, author = {Chen, Xiwen and Zhu, Wenhui and Qiu, Peijie and Wang, Hao and Li, Huayu and Wu, Haiyu and Dong, Xuanzhao and Sotiras, Aristeidis and Wang, Yalin and Razi, Abolfazl}, title = {Prompt-OT: An Optimal Transport Regularization Paradigm for Knowledge Preservation in Vision-Language Model Adaptation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {667-676} }
Restora-Flow: Mask-Guided Image Restoration with Flow Matching: Arnela Hadzic,

Franz Thaler,

Lea Bogensperger,

Simon Johannes Joham,

Martin Urschler; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hadzic_2026_WACV, author = {Hadzic, Arnela and Thaler, Franz and Bogensperger, Lea and Joham, Simon Johannes and Urschler, Martin}, title = {Restora-Flow: Mask-Guided Image Restoration with Flow Matching}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4943-4952} }
Unsupervised Segmentation by Diffusing, Walking and Cutting: Daniela Ivanova,

Marco Aversa,

Paul Henderson,

John Williamson; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ivanova_2026_WACV, author = {Ivanova, Daniela and Aversa, Marco and Henderson, Paul and Williamson, John}, title = {Unsupervised Segmentation by Diffusing, Walking and Cutting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5110-5120} }
RobuMTL: Enhancing Multi-Task Learning Robustness Against Weather Conditions: Tasneem Shaffee,

Sherief Reda; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shaffee_2026_WACV, author = {Shaffee, Tasneem and Reda, Sherief}, title = {RobuMTL: Enhancing Multi-Task Learning Robustness Against Weather Conditions}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5591-5600} }
SCORE: Soft Label Compression-Centric Dataset Condensation via Coding Rate Optimization: Bowen Yuan,

Yuxia Fu,

Zijian Wang,

Yadan Luo,

Zi Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yuan_2026_WACV, author = {Yuan, Bowen and Fu, Yuxia and Wang, Zijian and Luo, Yadan and Huang, Zi}, title = {SCORE: Soft Label Compression-Centric Dataset Condensation via Coding Rate Optimization}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2198-2208} }
ICONIC-444: A 3.1-Million-Image Dataset for OOD Detection Research: Gerhard Krumpl,

Henning Avenhaus,

Horst Possegger; [pdf] [supp]
[bibtex]
@InProceedings{Krumpl_2026_WACV, author = {Krumpl, Gerhard and Avenhaus, Henning and Possegger, Horst}, title = {ICONIC-444: A 3.1-Million-Image Dataset for OOD Detection Research}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8427-8436} }
BAFIS: Dataset + Framework to Assess Occupational Bias and Human Preference in Modern Text-to-image Models: Thomas Klassert,

Adrian Ulges,

Biying Fu; [pdf] [supp]
[bibtex]
@InProceedings{Klassert_2026_WACV, author = {Klassert, Thomas and Ulges, Adrian and Fu, Biying}, title = {BAFIS: Dataset + Framework to Assess Occupational Bias and Human Preference in Modern Text-to-image Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2168-2177} }
Cosine Similarity is Almost All You Need (for Prototypical-Part Models): Luke Moffett,

Frank Willard,

Maximillian Machado,

Emmanuel Mokel,

Jon Donnelly,

Zhicheng Guo,

Adam Costarino,

Julia Yang,

Giyoung Kim,

Alina Jade Barnett,

Cynthia Rudin; [pdf] [supp]
[bibtex]
@InProceedings{Moffett_2026_WACV, author = {Moffett, Luke and Willard, Frank and Machado, Maximillian and Mokel, Emmanuel and Donnelly, Jon and Guo, Zhicheng and Costarino, Adam and Yang, Julia and Kim, Giyoung and Barnett, Alina Jade and Rudin, Cynthia}, title = {Cosine Similarity is Almost All You Need (for Prototypical-Part Models)}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1586-1596} }
Towards Photorealistic Style Transfer with Multimodal Guidance and Robustness to Content Images in Arbitrary Styles: Ruikai Zhou,

Yating Liu,

Yi Xu; [pdf] [supp]
[bibtex]
@InProceedings{Zhou_2026_WACV, author = {Zhou, Ruikai and Liu, Yating and Xu, Yi}, title = {Towards Photorealistic Style Transfer with Multimodal Guidance and Robustness to Content Images in Arbitrary Styles}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4651-4660} }
Decomposition Sampling for Efficient Region Annotations in Active Learning: Jingna Qiu,

Frauke Wilm,

Mathias Öttl,

Jonas Utz,

Maja Schlereth,

Moritz Schillinger,

Marc Aubreville,

Katharina Breininger; [pdf] [supp]
[bibtex]
@InProceedings{Qiu_2026_WACV, author = {Qiu, Jingna and Wilm, Frauke and \"Ottl, Mathias and Utz, Jonas and Schlereth, Maja and Schillinger, Moritz and Aubreville, Marc and Breininger, Katharina}, title = {Decomposition Sampling for Efficient Region Annotations in Active Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4160-4169} }
Codebook Knowledge with Mamba-Transformer For Low-Light Image Enhancement: Runhua Deng,

Aiwen Jiang,

Long Peng,

Qiuhai Yan; [pdf]
[bibtex]
@InProceedings{Deng_2026_WACV, author = {Deng, Runhua and Jiang, Aiwen and Peng, Long and Yan, Qiuhai}, title = {Codebook Knowledge with Mamba-Transformer For Low-Light Image Enhancement}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3720-3729} }
Illuminating Darkness: Learning to Enhance Low-light Images In-the-Wild: S. M. A. Sharif,

Abdur Rehman,

Zain Ul Abidin,

Fayaz Ali Dharejo,

Radu Timofte,

Rizwan Ali Naqvi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sharif_2026_WACV, author = {Sharif, S. M. A. and Rehman, Abdur and Abidin, Zain Ul and Dharejo, Fayaz Ali and Timofte, Radu and Naqvi, Rizwan Ali}, title = {Illuminating Darkness: Learning to Enhance Low-light Images In-the-Wild}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2263-2272} }
Food Image Generation on Multi-Noun Categories: Xinyue Pan,

Yuhao Chen,

Jiangpeng He,

Fengqing Zhu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pan_2026_WACV, author = {Pan, Xinyue and Chen, Yuhao and He, Jiangpeng and Zhu, Fengqing}, title = {Food Image Generation on Multi-Noun Categories}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5581-5590} }
FuLLaMa: Training-free Diffusion-based Object Removal with Context Preservation: Ilke Demir,

Umur Aybars Ciftci; [pdf] [supp]
[bibtex]
@InProceedings{Demir_2026_WACV, author = {Demir, Ilke and Ciftci, Umur Aybars}, title = {FuLLaMa: Training-free Diffusion-based Object Removal with Context Preservation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8563-8573} }
Augmenting with NeRFs: Fast Relocalization on Densified Datasets: Michael Tomadakis,

Rebecca Borissova,

Yuxuan Zhang,

Sanjeev Koppal; [pdf] [supp]
[bibtex]
@InProceedings{Tomadakis_2026_WACV, author = {Tomadakis, Michael and Borissova, Rebecca and Zhang, Yuxuan and Koppal, Sanjeev}, title = {Augmenting with NeRFs: Fast Relocalization on Densified Datasets}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3067-3076} }
FCC: Fully Connected Correlation for One-Shot Segmentation: Seonghyeon Moon,

Haein Kong,

Muhammad Haris Khan,

Mubbasir Kapadia,

Yuewei Lin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Moon_2026_WACV, author = {Moon, Seonghyeon and Kong, Haein and Khan, Muhammad Haris and Kapadia, Mubbasir and Lin, Yuewei}, title = {FCC: Fully Connected Correlation for One-Shot Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4827-4837} }
Imitating the Functionality of Image-to-Image Models Using a Single Example: Nurit Spingarn,

Tomer Michaeli; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Spingarn_2026_WACV, author = {Spingarn, Nurit and Michaeli, Tomer}, title = {Imitating the Functionality of Image-to-Image Models Using a Single Example}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2178-2187} }
Performance of Conformal Prediction in Capturing Aleatoric Uncertainty: Misgina Tsighe Hagos,

Claes Lundström; [pdf] [supp]
[bibtex]
@InProceedings{Hagos_2026_WACV, author = {Hagos, Misgina Tsighe and Lundstr\"om, Claes}, title = {Performance of Conformal Prediction in Capturing Aleatoric Uncertainty}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2954-2963} }
HEART-PFL: Stable Personalized Federated Learning under Heterogeneity with Hierarchical Directional Alignment and Adversarial Knowledge Transfer: Minjun Kim,

Minje Kim; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2026_WACV, author = {Kim, Minjun and Kim, Minje}, title = {HEART-PFL: Stable Personalized Federated Learning under Heterogeneity with Hierarchical Directional Alignment and Adversarial Knowledge Transfer}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3370-3379} }
ArchitectHead: Continuous Level of Detail Control for 3D Gaussian Head Avatars: Peizhi Yan,

Rabab Ward,

Qiang Tang,

Shan Du; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yan_2026_WACV, author = {Yan, Peizhi and Ward, Rabab and Tang, Qiang and Du, Shan}, title = {ArchitectHead: Continuous Level of Detail Control for 3D Gaussian Head Avatars}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1632-1642} }
Where is the Watermark? Interpretable Watermark Detection at the Block Level: Maria Bulychev,

Neil G. Marchant,

Benjamin I. P. Rubinstein; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bulychev_2026_WACV, author = {Bulychev, Maria and Marchant, Neil G. and Rubinstein, Benjamin I. P.}, title = {Where is the Watermark? Interpretable Watermark Detection at the Block Level}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7420-7429} }
HABIT: Human Action Benchmark for Interactive Traffic in CARLA: Mohan Ramesh,

Mark Azer,

Fabian Flohr; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ramesh_2026_WACV, author = {Ramesh, Mohan and Azer, Mark and Flohr, Fabian}, title = {HABIT: Human Action Benchmark for Interactive Traffic in CARLA}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7148-7157} }
SimForce: Force and Surface Electromyography from Full Body Video with Graph Neural Nets: Esha Dasgupta,

Boeun Kim,

Sang Hoon Yeo,

Hyung Jin Chang; [pdf]
[bibtex]
@InProceedings{Dasgupta_2026_WACV, author = {Dasgupta, Esha and Kim, Boeun and Yeo, Sang Hoon and Chang, Hyung Jin}, title = {SimForce: Force and Surface Electromyography from Full Body Video with Graph Neural Nets}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3320-3329} }
SAFER-AiD: Saccade-Assisted Foveal-peripheral vision Enhanced Reconstruction for Adversarial Defense: Jiayang Liu,

Daniel Ts'o,

Yiming Bu,

Qinru Qiu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2026_WACV, author = {Liu, Jiayang and Ts'o, Daniel and Bu, Yiming and Qiu, Qinru}, title = {SAFER-AiD: Saccade-Assisted Foveal-peripheral vision Enhanced Reconstruction for Adversarial Defense}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1726-1735} }
Patch Your Matcher: Correspondence-Aware Image-to-Image Translation Unlocks Cross-Modal Matching via Single-Modality Priors: Anton Frolov,

Volker Rodehorst; [pdf] [supp]
[bibtex]
@InProceedings{Frolov_2026_WACV, author = {Frolov, Anton and Rodehorst, Volker}, title = {Patch Your Matcher: Correspondence-Aware Image-to-Image Translation Unlocks Cross-Modal Matching via Single-Modality Priors}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7913-7924} }
Structured Context Learning for Generic Event Boundary Detection: Xin Gu,

Congcong Li,

Xinyao Wang,

Dexiang Hong,

Libo Zhang,

Tiejian Luo,

Longyin Wen,

Heng Fan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gu_2026_WACV, author = {Gu, Xin and Li, Congcong and Wang, Xinyao and Hong, Dexiang and Zhang, Libo and Luo, Tiejian and Wen, Longyin and Fan, Heng}, title = {Structured Context Learning for Generic Event Boundary Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4808-4817} }
A Deep Network for Object Detection on Inland Waters: Dennis Griesser,

Bastian Goldluecke,

Matthias O. Franz,

Georg Umlauf; [pdf] [supp]
[bibtex]
@InProceedings{Griesser_2026_WACV, author = {Griesser, Dennis and Goldluecke, Bastian and Franz, Matthias O. and Umlauf, Georg}, title = {A Deep Network for Object Detection on Inland Waters}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6590-6599} }
Geo3DVQA: Evaluating Vision-Language Models for 3D Geospatial Reasoning from Aerial Imagery: Mai Tsujimoto,

Junjue Wang,

Weihao Xuan,

Naoto Yokoya; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tsujimoto_2026_WACV, author = {Tsujimoto, Mai and Wang, Junjue and Xuan, Weihao and Yokoya, Naoto}, title = {Geo3DVQA: Evaluating Vision-Language Models for 3D Geospatial Reasoning from Aerial Imagery}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4994-5003} }
Logit-Adjusted Test-Time Adaptation under Partial Class Imbalance: Thilina Weerasinghe,

Ruwan Tennakoon,

WeiQin Chuah,

Alireza Bab-Hadiashar; [pdf] [supp]
[bibtex]
@InProceedings{Weerasinghe_2026_WACV, author = {Weerasinghe, Thilina and Tennakoon, Ruwan and Chuah, WeiQin and Bab-Hadiashar, Alireza}, title = {Logit-Adjusted Test-Time Adaptation under Partial Class Imbalance}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5977-5985} }
BlendCLIP: Bridging Synthetic and Real Domains for Zero-Shot 3D Object Classification with Multimodal Pretraining: Ajinkya Khoche,

Gergő László Nagy,

Maciej Wozniak,

Thomas Gustafsson,

Patric Jensfelt; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Khoche_2026_WACV, author = {Khoche, Ajinkya and Nagy, Gerg\H{o} L\'aszl\'o and Wozniak, Maciej and Gustafsson, Thomas and Jensfelt, Patric}, title = {BlendCLIP: Bridging Synthetic and Real Domains for Zero-Shot 3D Object Classification with Multimodal Pretraining}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5766-5775} }
Saliency-Guided DETR for Moment Retrieval and Highlight Detection: Aleksandr Gordeev,

Vladimir Dokholyan,

Irina Tolstykh,

Maksim Kuprashevich; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gordeev_2026_WACV, author = {Gordeev, Aleksandr and Dokholyan, Vladimir and Tolstykh, Irina and Kuprashevich, Maksim}, title = {Saliency-Guided DETR for Moment Retrieval and Highlight Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {907-916} }
MooTrack360: A Novel Fisheye Camera Dataset for Robust Multi Diary Cow Detection and Tracking: Rasmus Gjerlund K. Christiansen,

Toan Van Nguyen,

Lasse Rose Malskær,

Leon Bodenhagen,

Dirk Kraft; [pdf]
[bibtex]
@InProceedings{Christiansen_2026_WACV, author = {Christiansen, Rasmus Gjerlund K. and Van Nguyen, Toan and Malsk{\ae}r, Lasse Rose and Bodenhagen, Leon and Kraft, Dirk}, title = {MooTrack360: A Novel Fisheye Camera Dataset for Robust Multi Diary Cow Detection and Tracking}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {451-460} }
Histopath-C: Towards Realistic Domain Shifts for Histopathology Vision-Language Adaptation: Mehrdad Noori,

Gustavo A. Vargas Hakim,

David Osowiechi,

Fereshteh Shakeri,

Ali Bahri,

Moslem Yazdanpanah,

Sahar Dastani,

Ismail Ben Ayed,

Christian Desrosiers; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Noori_2026_WACV, author = {Noori, Mehrdad and Hakim, Gustavo A. Vargas and Osowiechi, David and Shakeri, Fereshteh and Bahri, Ali and Yazdanpanah, Moslem and Dastani, Sahar and Ben Ayed, Ismail and Desrosiers, Christian}, title = {Histopath-C: Towards Realistic Domain Shifts for Histopathology Vision-Language Adaptation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4890-4900} }
Tables Decoded: DELTA for Structure, TARQA for Understanding: Jahanvi Rajput,

Dhruv Kudale,

Saikiran Kasturi,

Utkarsh Verma,

Ganesh Ramakrishnan; [pdf] [supp]
[bibtex]
@InProceedings{Rajput_2026_WACV, author = {Rajput, Jahanvi and Kudale, Dhruv and Kasturi, Saikiran and Verma, Utkarsh and Ramakrishnan, Ganesh}, title = {Tables Decoded: DELTA for Structure, TARQA for Understanding}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2775-2785} }
HumanGuideNet: Adapter-Based Alignment of Deep Neural Networks with Human Similarity Judgments: Xufu Liu,

Yifan Yang,

Zhengxin Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2026_WACV, author = {Liu, Xufu and Yang, Yifan and Zhang, Zhengxin}, title = {HumanGuideNet: Adapter-Based Alignment of Deep Neural Networks with Human Similarity Judgments}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1798-1808} }
Broadcast2Pitch: Game State Reconstruction from Unconstrained Soccer Videos: Yin May Oo,

Yewon Hwang,

Muhammad Amrulloh Robbani,

Vanyi Chao,

Ankhzaya Jamsrandorj,

Hoang Quoc Nguyen,

Kyung-Ryoul Mun,

Jinwook Kim; [pdf] [supp]
[bibtex]
@InProceedings{Oo_2026_WACV, author = {Oo, Yin May and Hwang, Yewon and Robbani, Muhammad Amrulloh and Chao, Vanyi and Jamsrandorj, Ankhzaya and Nguyen, Hoang Quoc and Mun, Kyung-Ryoul and Kim, Jinwook}, title = {Broadcast2Pitch: Game State Reconstruction from Unconstrained Soccer Videos}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4483-4493} }
Mixed Diffusion for 3D Indoor Scene Synthesis: Siyi Hu,

Diego Martín Arroyo,

Stephanie Debats,

Fabian Manhardt,

Luca Carlone,

Federico Tombari; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hu_2026_WACV, author = {Hu, Siyi and Arroyo, Diego Mart{\'\i}n and Debats, Stephanie and Manhardt, Fabian and Carlone, Luca and Tombari, Federico}, title = {Mixed Diffusion for 3D Indoor Scene Synthesis}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1262-1272} }
NERVE: Neighbourhood & Entropy-Guided Random-Walk for Training Free Open-Vocabulary Segmentation: Kunal Mahatha,

Jose Dolz,

Christian Desrosiers; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mahatha_2026_WACV, author = {Mahatha, Kunal and Dolz, Jose and Desrosiers, Christian}, title = {NERVE: Neighbourhood \& Entropy-Guided Random-Walk for Training Free Open-Vocabulary Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3243-3253} }
PSA-MIL: A Probabilistic Spatial Attention-Based Multiple Instance Learning for Whole Slide Image Classification: Sharon Peled,

Yosef E. Maruvka,

Moti Freiman; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Peled_2026_WACV, author = {Peled, Sharon and Maruvka, Yosef E. and Freiman, Moti}, title = {PSA-MIL: A Probabilistic Spatial Attention-Based Multiple Instance Learning for Whole Slide Image Classification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1211-1220} }
Diverse Sketch Colorization with Content-Enhanced Style Representation and Recolorization Distillation: Shuangming Mao,

Haixiang Zhu; [pdf] [supp]
[bibtex]
@InProceedings{Mao_2026_WACV, author = {Mao, Shuangming and Zhu, Haixiang}, title = {Diverse Sketch Colorization with Content-Enhanced Style Representation and Recolorization Distillation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1064-1073} }
STEG-AIW: Spatio-Temporal Gating and Adaptive-Timestep Inference for Efficient Spiking Neural Networks: Gulfam Ahmed Saju,

Anton Spirkin,

Felipe Marcelino,

Yuchou Chang; [pdf]
[bibtex]
@InProceedings{Saju_2026_WACV, author = {Saju, Gulfam Ahmed and Spirkin, Anton and Marcelino, Felipe and Chang, Yuchou}, title = {STEG-AIW: Spatio-Temporal Gating and Adaptive-Timestep Inference for Efficient Spiking Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4180-4189} }
Perception-Inspired Color Space Design for Photo White Balance Editing: Yang Cheng,

Ziteng Cui,

Lin Gu,

Shenghan Su,

Zenghui Zhang; [pdf] [arXiv]
[bibtex]
@InProceedings{Cheng_2026_WACV, author = {Cheng, Yang and Cui, Ziteng and Gu, Lin and Su, Shenghan and Zhang, Zenghui}, title = {Perception-Inspired Color Space Design for Photo White Balance Editing}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3741-3749} }
A Framework for Real-Time Surgical Phase Recognition with Application to Robot-Assisted Partial Nephrectomy: Marco Mezzina,

Tom Vercauteren,

Tinne Tuytelaars,

Matthew B. Blaschko; [pdf] [supp]
[bibtex]
@InProceedings{Mezzina_2026_WACV, author = {Mezzina, Marco and Vercauteren, Tom and Tuytelaars, Tinne and Blaschko, Matthew B.}, title = {A Framework for Real-Time Surgical Phase Recognition with Application to Robot-Assisted Partial Nephrectomy}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {245-254} }
WiSE-OD: Benchmarking Robustness in Infrared Object Detection: Heitor R. Medeiros,

Atif Belal,

Masih Aminbeidokhti,

Eric Granger,

Marco Pedersoli; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Medeiros_2026_WACV, author = {Medeiros, Heitor R. and Belal, Atif and Aminbeidokhti, Masih and Granger, Eric and Pedersoli, Marco}, title = {WiSE-OD: Benchmarking Robustness in Infrared Object Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4912-4921} }
AuthGuard: Generalizable Deepfake Detection via Language Guidance: Guangyu Shen,

Zhihua Li,

Xiang Xu,

Tianchen Zhao,

Zheng Zhang,

Dongsheng An,

Zhuowen Tu,

Yifan Xing,

Qin Zhang; [pdf] [arXiv]
[bibtex]
@InProceedings{Shen_2026_WACV, author = {Shen, Guangyu and Li, Zhihua and Xu, Xiang and Zhao, Tianchen and Zhang, Zheng and An, Dongsheng and Tu, Zhuowen and Xing, Yifan and Zhang, Qin}, title = {AuthGuard: Generalizable Deepfake Detection via Language Guidance}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6215-6225} }
Improving Out-of-Distribution Detection Using Segmented Images and Cross-View Attention Fusion: Alexander Politowicz,

Sahisnu Mazumder,

Bing Liu; [pdf] [supp]
[bibtex]
@InProceedings{Politowicz_2026_WACV, author = {Politowicz, Alexander and Mazumder, Sahisnu and Liu, Bing}, title = {Improving Out-of-Distribution Detection Using Segmented Images and Cross-View Attention Fusion}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5269-5279} }
VIZOR: Viewpoint-Invariant Zero-Shot Scene Graph Generation for 3D Scene Reasoning: Vivek Madhavaram,

Vartika Sengar,

Arkadipta De,

Charu Sharma; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Madhavaram_2026_WACV, author = {Madhavaram, Vivek and Sengar, Vartika and De, Arkadipta and Sharma, Charu}, title = {VIZOR: Viewpoint-Invariant Zero-Shot Scene Graph Generation for 3D Scene Reasoning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8584-8595} }
Understanding Generative AI Capabilities in Everyday Image Editing Tasks: Brandon Collins,

Mohammad Reza Taesiri,

Logan Bolton,

Viet Dac Lai,

Franck Dernoncourt,

Trung Bui,

Anh Totti Nguyen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Collins_2026_WACV, author = {Collins, Brandon and Taesiri, Mohammad Reza and Bolton, Logan and Lai, Viet Dac and Dernoncourt, Franck and Bui, Trung and Nguyen, Anh Totti}, title = {Understanding Generative AI Capabilities in Everyday Image Editing Tasks}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2231-2241} }
Gaussian Splatting Map Registration with Orthographic Bird's-Eye-View Renderings: H. Leblond,

G. Simon,

R. Martins,

C. Demonceaux,

M.-O. Berger; [pdf] [supp]
[bibtex]
@InProceedings{Leblond_2026_WACV, author = {Leblond, H. and Simon, G. and Martins, R. and Demonceaux, C. and Berger, M.-O.}, title = {Gaussian Splatting Map Registration with Orthographic Bird's-Eye-View Renderings}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6080-6089} }
IPCD: Intrinsic Point-Cloud Decomposition: Shogo Sato,

Takuhiro Kaneko,

Shoichiro Takeda,

Tomoyasu Shimada,

Kazuhiko Murasaki,

Taiga Yoshida,

Ryuichi Tanida,

Akisato Kimura; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sato_2026_WACV, author = {Sato, Shogo and Kaneko, Takuhiro and Takeda, Shoichiro and Shimada, Tomoyasu and Murasaki, Kazuhiko and Yoshida, Taiga and Tanida, Ryuichi and Kimura, Akisato}, title = {IPCD: Intrinsic Point-Cloud Decomposition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7094-7103} }
Diffusion Noise Optimization for Synthetic VLM Training: Ren Ohkubo,

Rintaro Yanagi,

Hirokatsu Kataoka,

Yutaka Satoh; [pdf] [supp]
[bibtex]
@InProceedings{Ohkubo_2026_WACV, author = {Ohkubo, Ren and Yanagi, Rintaro and Kataoka, Hirokatsu and Satoh, Yutaka}, title = {Diffusion Noise Optimization for Synthetic VLM Training}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6412-6421} }
DCSHARP: 3D Gaussian Splatting with Direction Cosine Spherical Harmonics and Shape-Aware Pruning: Ahmed Hasssan,

Jian Meng,

Yuanbo Xiangli,

Jae-sun Seo; [pdf] [supp]
[bibtex]
@InProceedings{Hasssan_2026_WACV, author = {Hasssan, Ahmed and Meng, Jian and Xiangli, Yuanbo and Seo, Jae-sun}, title = {DCSHARP: 3D Gaussian Splatting with Direction Cosine Spherical Harmonics and Shape-Aware Pruning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3628-3637} }
Distilling Diversity and Control in Diffusion Models: Rohit Gandikota,

David Bau; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gandikota_2026_WACV, author = {Gandikota, Rohit and Bau, David}, title = {Distilling Diversity and Control in Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1304-1313} }
KFS-Bench: Comprehensive Evaluation of Key Frame Sampling in Long Video Understanding: Zongyao Li,

Kengo Ishida,

Satoshi Yamazaki,

Xiaotong Ji,

Jianquan Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2026_WACV, author = {Li, Zongyao and Ishida, Kengo and Yamazaki, Satoshi and Ji, Xiaotong and Liu, Jianquan}, title = {KFS-Bench: Comprehensive Evaluation of Key Frame Sampling in Long Video Understanding}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5643-5652} }
TacticalCalib: End-to-End 6-DoF Camera Pose Regression for Tactical Camera Calibration: Liang Fan,

Xiaoqian Liu,

Zhi Chen,

Lingkai Yang; [pdf]
[bibtex]
@InProceedings{Fan_2026_WACV, author = {Fan, Liang and Liu, Xiaoqian and Chen, Zhi and Yang, Lingkai}, title = {TacticalCalib: End-to-End 6-DoF Camera Pose Regression for Tactical Camera Calibration}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6547-6556} }
FlowCLAS: Enhancing Normalizing Flow-Based Anomaly Segmentation Via Contrastive Learning: Chang Won Lee,

Selina Leveugle,

Paul Grouchy,

Chris Langley,

Svetlana Stolpner,

Jonathan Kelly,

Steven L. Waslander; [pdf] [supp]
[bibtex]
@InProceedings{Lee_2026_WACV, author = {Lee, Chang Won and Leveugle, Selina and Grouchy, Paul and Langley, Chris and Stolpner, Svetlana and Kelly, Jonathan and Waslander, Steven L.}, title = {FlowCLAS: Enhancing Normalizing Flow-Based Anomaly Segmentation Via Contrastive Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6998-7007} }
SuperRivolution: Fine-Scale Rivers from Coarse Temporal Satellite Imagery: Rangel Daroya,

Subhransu Maji; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Daroya_2026_WACV, author = {Daroya, Rangel and Maji, Subhransu}, title = {SuperRivolution: Fine-Scale Rivers from Coarse Temporal Satellite Imagery}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7482-7492} }
Network-agnostic Distortion-robust Projections for Wide-angle Image Understanding: Akshaya Athwale,

Ola Ahmad,

Jean-Francois Lalonde; [pdf] [supp]
[bibtex]
@InProceedings{Athwale_2026_WACV, author = {Athwale, Akshaya and Ahmad, Ola and Lalonde, Jean-Francois}, title = {Network-agnostic Distortion-robust Projections for Wide-angle Image Understanding}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {591-601} }
Interleaved Vision-and-Language Generation via Generative Voken: Kaizhi Zheng,

Xuehai He,

Xin Eric Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zheng_2026_WACV, author = {Zheng, Kaizhi and He, Xuehai and Wang, Xin Eric}, title = {Interleaved Vision-and-Language Generation via Generative Voken}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {472-482} }
R-MMA: Enhancing Vision-Language Models with Recurrent Adapters for Few-Shot and Cross-Domain Generalization: Md Fahim,

Md Farhan Ishmam,

Mir Sazzat Hossain,

M Ashraful Amin,

Amin Ahsan Ali,

AKM Mahbubur Rahman; [pdf] [supp]
[bibtex]
@InProceedings{Fahim_2026_WACV, author = {Fahim, Md and Ishmam, Md Farhan and Hossain, Mir Sazzat and Amin, M Ashraful and Ali, Amin Ahsan and Rahman, AKM Mahbubur}, title = {R-MMA: Enhancing Vision-Language Models with Recurrent Adapters for Few-Shot and Cross-Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6496-6506} }
TRACE: Confounder-free Adversarial Fine-tuning for Robust Object Detection: Wonho Lee,

Jisu Lee,

Hyunsik Na,

Sohee Park,

Daeseon Choi; [pdf] [supp]
[bibtex]
@InProceedings{Lee_2026_WACV, author = {Lee, Wonho and Lee, Jisu and Na, Hyunsik and Park, Sohee and Choi, Daeseon}, title = {TRACE: Confounder-free Adversarial Fine-tuning for Robust Object Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6705-6714} }
PrevMatch: Revisiting and Maximizing Temporal Knowledge in Semi-Supervised Semantic Segmentation: Wooseok Shin,

Hyun Joon Park,

Jin Sob Kim,

Juan Yun,

Se Hong Park,

Sung Won Han; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shin_2026_WACV, author = {Shin, Wooseok and Park, Hyun Joon and Kim, Jin Sob and Yun, Juan and Park, Se Hong and Han, Sung Won}, title = {PrevMatch: Revisiting and Maximizing Temporal Knowledge in Semi-Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4953-4963} }
SaccadeX: Directed Acyclic Graph-based Semi-Supervised Learning of Continuous Ocular Dynamics from Sparse Neuromorphic Streams: Nuwan Bandara,

Thivya Kandappu,

Archan Misra; [pdf] [supp]
[bibtex]
@InProceedings{Bandara_2026_WACV, author = {Bandara, Nuwan and Kandappu, Thivya and Misra, Archan}, title = {SaccadeX: Directed Acyclic Graph-based Semi-Supervised Learning of Continuous Ocular Dynamics from Sparse Neuromorphic Streams}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1384-1394} }
CAAC: Confidence-Aware Attention Calibration to Reduce Hallucinations in Large Vision-Language Models: Mehrdad Fazli,

Bowen Wei,

Ahmet Sari,

Ziwei Zhu; [pdf] [supp]
[bibtex]
@InProceedings{Fazli_2026_WACV, author = {Fazli, Mehrdad and Wei, Bowen and Sari, Ahmet and Zhu, Ziwei}, title = {CAAC: Confidence-Aware Attention Calibration to Reduce Hallucinations in Large Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1242-1251} }
UCDSC: Open Set UnCertainty aware Deep Simplex Classifier for Medical Image Datasets: Arnav Aditya,

Nitin Kumar,

Saurabh Shigwan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Aditya_2026_WACV, author = {Aditya, Arnav and Kumar, Nitin and Shigwan, Saurabh}, title = {UCDSC: Open Set UnCertainty aware Deep Simplex Classifier for Medical Image Datasets}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4787-4796} }
SOLAR: Switchable Output Layer for Accuracy and Robustness in Once-for-All Training: Shaharyar Ahmed Khan Tareen,

Lei Fan,

Xiaojing Yuan,

Qin Lin,

Bin Hu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tareen_2026_WACV, author = {Tareen, Shaharyar Ahmed Khan and Fan, Lei and Yuan, Xiaojing and Lin, Qin and Hu, Bin}, title = {SOLAR: Switchable Output Layer for Accuracy and Robustness in Once-for-All Training}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7893-7902} }
Towards Streaming LiDAR Object Detection with Point Clouds as Egocentric Sequences: Mellon M. Zhang,

Glen Chou,

Saibal Mukhopadhyay; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2026_WACV, author = {Zhang, Mellon M. and Chou, Glen and Mukhopadhyay, Saibal}, title = {Towards Streaming LiDAR Object Detection with Point Clouds as Egocentric Sequences}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3275-3284} }
Subspace-Guided Knowledge Distillation for Efficient Model Transfer: Zeeshan Hayder,

Ali Cheraghian,

Lars Petersson,

Mehrtash Harandi; [pdf]
[bibtex]
@InProceedings{Hayder_2026_WACV, author = {Hayder, Zeeshan and Cheraghian, Ali and Petersson, Lars and Harandi, Mehrtash}, title = {Subspace-Guided Knowledge Distillation for Efficient Model Transfer}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5057-5066} }
DexAvatar: 3D Sign Language Reconstruction with Hand and Body Pose Priors: Kaustubh Kundu,

Hrishav Bakul Barua,

Lucy Robertson-Bell,

Zhixi Cai,

Kalin Stefanov; [pdf] [supp]
[bibtex]
@InProceedings{Kundu_2026_WACV, author = {Kundu, Kaustubh and Barua, Hrishav Bakul and Robertson-Bell, Lucy and Cai, Zhixi and Stefanov, Kalin}, title = {DexAvatar: 3D Sign Language Reconstruction with Hand and Body Pose Priors}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5842-5852} }
EmojiDiff: Advanced Facial Expression Control with High Identity Preservation in Portrait Generation: Liangwei Jiang,

Ruida Li,

Zhifeng Zhang,

Shuo Fang,

Chenguang Ma; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jiang_2026_WACV, author = {Jiang, Liangwei and Li, Ruida and Zhang, Zhifeng and Fang, Shuo and Ma, Chenguang}, title = {EmojiDiff: Advanced Facial Expression Control with High Identity Preservation in Portrait Generation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {328-338} }
FairScene: Learning Class-Disentangled 2D/3D Representations for Semantic Scene Completion: Dian Jia,

Pei Yu,

Wei Tang; [pdf] [supp]
[bibtex]
@InProceedings{Jia_2026_WACV, author = {Jia, Dian and Yu, Pei and Tang, Wei}, title = {FairScene: Learning Class-Disentangled 2D/3D Representations for Semantic Scene Completion}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3760-3770} }
A Universal Self-Attention Enhancement for Bridging Low-bit Quantization and Vision Transformers: Jiahe Qian,

Peisong Wang,

Zhengyang Zhuge,

Qinghao Hu,

Jian Cheng; [pdf]
[bibtex]
@InProceedings{Qian_2026_WACV, author = {Qian, Jiahe and Wang, Peisong and Zhuge, Zhengyang and Hu, Qinghao and Cheng, Jian}, title = {A Universal Self-Attention Enhancement for Bridging Low-bit Quantization and Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {360-370} }
SegMo: Segment-aligned Text to 3D Human Motion Generation: Bowen Dang,

Lin Wu,

Xiaohang Yang,

Zheng Yuan,

Zhixiang Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dang_2026_WACV, author = {Dang, Bowen and Wu, Lin and Yang, Xiaohang and Yuan, Zheng and Chen, Zhixiang}, title = {SegMo: Segment-aligned Text to 3D Human Motion Generation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6946-6955} }
SceneProp: Combining Neural Network and Markov Random Field for Scene-Graph Grounding: Keita Otani,

Tatsuya Harada; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Otani_2026_WACV, author = {Otani, Keita and Harada, Tatsuya}, title = {SceneProp: Combining Neural Network and Markov Random Field for Scene-Graph Grounding}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6153-6162} }
JOCA: Task-Driven Joint Optimisation of Camera Hardware and Adaptive Camera Control Algorithms: Chengyang Yan,

Mitch Bryson,

Donald G. Dansereau; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yan_2026_WACV, author = {Yan, Chengyang and Bryson, Mitch and Dansereau, Donald G.}, title = {JOCA: Task-Driven Joint Optimisation of Camera Hardware and Adaptive Camera Control Algorithms}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3928-3938} }
TiCLS: Tightly Coupled Language Text Spotter: Leeje Jang,

Yijun Lin,

Yao-Yi Chiang,

Jerod Weinman; [pdf] [arXiv]
[bibtex]
@InProceedings{Jang_2026_WACV, author = {Jang, Leeje and Lin, Yijun and Chiang, Yao-Yi and Weinman, Jerod}, title = {TiCLS: Tightly Coupled Language Text Spotter}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3730-3740} }
WiSAR3D - Aerial LiDAR Dataset for 3D Object Detection: Oren Shrout,

Ori Nizan,

Yizhak Ben-Shabat,

Ayellet Tal; [pdf] [supp]
[bibtex]
@InProceedings{Shrout_2026_WACV, author = {Shrout, Oren and Nizan, Ori and Ben-Shabat, Yizhak and Tal, Ayellet}, title = {WiSAR3D - Aerial LiDAR Dataset for 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6580-6589} }
ORCA: Object Recognition and Comprehension for Archiving Marine Species: Yuk-Kwan Wong,

Haixin Liang,

Zeyu Ma,

Yiwei Chen,

Ziqiang Zheng,

Rinaldi Gotama,

Pascal Sebastian,

Lauren D. Sparks,

Sai-Kit Yeung; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wong_2026_WACV, author = {Wong, Yuk-Kwan and Liang, Haixin and Ma, Zeyu and Chen, Yiwei and Zheng, Ziqiang and Gotama, Rinaldi and Sebastian, Pascal and Sparks, Lauren D. and Yeung, Sai-Kit}, title = {ORCA: Object Recognition and Comprehension for Archiving Marine Species}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1597-1609} }
Unsupervised Modular Adaptive Region Growing and RegionMix Classification for Wind Turbine Segmentation: Raül Pérez-Gonzalo,

Riccardo Magro,

Andreas Espersen,

Antonio Agudo; [pdf] [supp]
[bibtex]
@InProceedings{Perez-Gonzalo_2026_WACV, author = {P\'erez-Gonzalo, Ra\"ul and Magro, Riccardo and Espersen, Andreas and Agudo, Antonio}, title = {Unsupervised Modular Adaptive Region Growing and RegionMix Classification for Wind Turbine Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3878-3888} }
Learnable Query-Enhanced Pose Transformation: Yi-Zhen Wang,

Hong-Han Shuai; [pdf]
[bibtex]
@InProceedings{Wang_2026_WACV, author = {Wang, Yi-Zhen and Shuai, Hong-Han}, title = {Learnable Query-Enhanced Pose Transformation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2032-2041} }
Exploiting Label-Independent Regularization from Spatial Patterns for Whole Slide Image Analysis: Weiyi Wu,

Xinwen Xu,

Chongyang Gao,

Xingjian Diao,

Siting Li,

Jiang Gui; [pdf] [supp]
[bibtex]
@InProceedings{Wu_2026_WACV, author = {Wu, Weiyi and Xu, Xinwen and Gao, Chongyang and Diao, Xingjian and Li, Siting and Gui, Jiang}, title = {Exploiting Label-Independent Regularization from Spatial Patterns for Whole Slide Image Analysis}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8639-8649} }
Co-STAR: Collaborative Curriculum Self-Training with Adaptive Regularization for Source-Free Video Domain Adaptation: Amirhossein Dadashzadeh,

Parsa Esmati,

Majid Mirmehdi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dadashzadeh_2026_WACV, author = {Dadashzadeh, Amirhossein and Esmati, Parsa and Mirmehdi, Majid}, title = {Co-STAR: Collaborative Curriculum Self-Training with Adaptive Regularization for Source-Free Video Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7821-7831} }
A Novel Metric for Detecting Memorization in Generative Models for Brain MRI Synthesis: Antonio Scardace,

Lemuel Puglisi,

Francesco Guarnera,

Sebastiano Battiato,

Daniele Ravi; [pdf] [arXiv]
[bibtex]
@InProceedings{Scardace_2026_WACV, author = {Scardace, Antonio and Puglisi, Lemuel and Guarnera, Francesco and Battiato, Sebastiano and Ravi, Daniele}, title = {A Novel Metric for Detecting Memorization in Generative Models for Brain MRI Synthesis}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3868-3877} }
FLoMo-Net: A Novel Task-Adaptive Mixture of Experts Routing Framework with Frequency and Uncertainty Correction for Medical Image Segmentation: Md Rayhan Ahmed,

Patricia Lasserre; [pdf] [supp]
[bibtex]
@InProceedings{Ahmed_2026_WACV, author = {Ahmed, Md Rayhan and Lasserre, Patricia}, title = {FLoMo-Net: A Novel Task-Adaptive Mixture of Experts Routing Framework with Frequency and Uncertainty Correction for Medical Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4025-4035} }
Detecting Out-of-Distribution Objects through Class-Conditioned Inpainting: Quang-Huy Nguyen,

Jin Peng Zhou,

Zhenzhen Liu,

Khanh-Huyen Bui,

Kilian Q. Weinberger,

Wei-Lun Chao,

Dung D. Le; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nguyen_2026_WACV, author = {Nguyen, Quang-Huy and Zhou, Jin Peng and Liu, Zhenzhen and Bui, Khanh-Huyen and Weinberger, Kilian Q. and Chao, Wei-Lun and Le, Dung D.}, title = {Detecting Out-of-Distribution Objects through Class-Conditioned Inpainting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1937-1947} }
GrounDiff: Diffusion-Based Ground Surface Generation from Digital Surface Models: Oussema Dhaouadi,

Johannes Meier,

Jacques Kaiser,

Daniel Cremers; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dhaouadi_2026_WACV, author = {Dhaouadi, Oussema and Meier, Johannes and Kaiser, Jacques and Cremers, Daniel}, title = {GrounDiff: Diffusion-Based Ground Surface Generation from Digital Surface Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1355-1364} }
QuEENet: Quantum-Enhanced Expressive Network for Image Classification: Shashank Bayal,

Rushikesh Govind Dawane,

Komal Komal,

Santosh Kumar Vipparthi,

Subrahmanyam Murala; [pdf] [supp]
[bibtex]
@InProceedings{Bayal_2026_WACV, author = {Bayal, Shashank and Dawane, Rushikesh Govind and Komal, Komal and Vipparthi, Santosh Kumar and Murala, Subrahmanyam}, title = {QuEENet: Quantum-Enhanced Expressive Network for Image Classification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7883-7892} }
What Happens When: Learning Temporal Orders of Events in Videos: Daechul Ahn,

Yura Choi,

Hyeonbeom Choi,

Seongwon Cho,

San Kim,

Jonghyun Choi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ahn_2026_WACV, author = {Ahn, Daechul and Choi, Yura and Choi, Hyeonbeom and Cho, Seongwon and Kim, San and Choi, Jonghyun}, title = {What Happens When: Learning Temporal Orders of Events in Videos}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2786-2796} }
Identity Verification from Human Scent using Channel Representation of 2D Gas Chromatography-Mass Spectrometry Data: Radim Spetlik,

Jan Hlavsa,

Jana Čechová,

Petra Pojmanová,

Jiri Matas,

Štěpán Urban; [pdf] [supp]
[bibtex]
@InProceedings{Spetlik_2026_WACV, author = {Spetlik, Radim and Hlavsa, Jan and \v{C}echov\'a, Jana and Pojmanov\'a, Petra and Matas, Jiri and Urban, \v{S}t\v{e}p\'an}, title = {Identity Verification from Human Scent using Channel Representation of 2D Gas Chromatography-Mass Spectrometry Data}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1471-1480} }
CLUE: Bringing Machine Unlearning to Mobile Devices: A.Q.M. Sazzad Sayyed,

Nathaniel D. Bastian,

Michael De Lucia,

Ananthram Swami,

Francesco Restuccia; [pdf] [supp]
[bibtex]
@InProceedings{Sayyed_2026_WACV, author = {Sayyed, A.Q.M. Sazzad and Bastian, Nathaniel D. and De Lucia, Michael and Swami, Ananthram and Restuccia, Francesco}, title = {CLUE: Bringing Machine Unlearning to Mobile Devices}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3750-3759} }
SHaSaM: Submodular Hard Sample Mining for Fair Facial Attribute Recognition: Anay Majee,

Rishabh Iyer; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Majee_2026_WACV, author = {Majee, Anay and Iyer, Rishabh}, title = {SHaSaM: Submodular Hard Sample Mining for Fair Facial Attribute Recognition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7461-7471} }
Unified Control for Inference-Time Guidance of Denoising Diffusion Models: Maurya Goyal,

Anuj Singh,

Hadi Jamali-Rad; [pdf] [supp]
[bibtex]
@InProceedings{Goyal_2026_WACV, author = {Goyal, Maurya and Singh, Anuj and Jamali-Rad, Hadi}, title = {Unified Control for Inference-Time Guidance of Denoising Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5437-5446} }
Hierarchical Adaptive networks with Task vectors for Test-Time Adaptation: Sameer Ambekar,

Marta Hasny,

Laura Alexandra Daza,

Daniel M. Lang,

Julia Schnabel; [pdf] [supp]
[bibtex]
@InProceedings{Ambekar_2026_WACV, author = {Ambekar, Sameer and Hasny, Marta and Daza, Laura Alexandra and Lang, Daniel M. and Schnabel, Julia}, title = {Hierarchical Adaptive networks with Task vectors for Test-Time Adaptation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4661-4672} }
SGD-Mix: Enhancing Domain-Specific Image Classification with Label-Preserving Data Augmentation: Yixuan Dong,

Fang-Yi Su,

Jung-Hsien Chiang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dong_2026_WACV, author = {Dong, Yixuan and Su, Fang-Yi and Chiang, Jung-Hsien}, title = {SGD-Mix: Enhancing Domain-Specific Image Classification with Label-Preserving Data Augmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7051-7061} }
Unsupervised Discovery of Long-Term Spatiotemporal Periodic Workflows in Human Activities: Fan Yang,

Quanting Xie,

Atsunori Moteki,

Shoichi Masui,

Shan Jiang,

Kanji Uchino,

Yonatan Bisk,

Graham Neubig; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2026_WACV, author = {Yang, Fan and Xie, Quanting and Moteki, Atsunori and Masui, Shoichi and Jiang, Shan and Uchino, Kanji and Bisk, Yonatan and Neubig, Graham}, title = {Unsupervised Discovery of Long-Term Spatiotemporal Periodic Workflows in Human Activities}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5821-5832} }
DoTA: Latent Distribution Conditioned Data Attribution for Diffusion Models: Ninad Joshi,

Vivek Srivastava,

Shirish Karande; [pdf] [supp]
[bibtex]
@InProceedings{Joshi_2026_WACV, author = {Joshi, Ninad and Srivastava, Vivek and Karande, Shirish}, title = {DoTA: Latent Distribution Conditioned Data Attribution for Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2022-2031} }
Face-LLaVA: Facial Expression and Attribute Understanding through Instruction Tuning: Ashutosh Chaubey,

Xulang Guan,

Mohammad Soleymani; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chaubey_2026_WACV, author = {Chaubey, Ashutosh and Guan, Xulang and Soleymani, Mohammad}, title = {Face-LLaVA: Facial Expression and Attribute Understanding through Instruction Tuning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2648-2660} }
Revisiting an Old Perspective Projection for Monocular 3D Morphable Models Regression: Toby Chong,

Ryota Nakajima; [pdf]
[bibtex]
@InProceedings{Chong_2026_WACV, author = {Chong, Toby and Nakajima, Ryota}, title = {Revisiting an Old Perspective Projection for Monocular 3D Morphable Models Regression}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7799-7808} }
SafeguardGS: 3D Gaussian Primitive Pruning While Avoiding Catastrophic Scene Destruction: Yongjae Lee,

Zhaoliang Zhang,

Deliang Fan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2026_WACV, author = {Lee, Yongjae and Zhang, Zhaoliang and Fan, Deliang}, title = {SafeguardGS: 3D Gaussian Primitive Pruning While Avoiding Catastrophic Scene Destruction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8479-8489} }
UI-Styler: Ultrasound Image Style Transfer with Class-Aware Prompts for Cross-Device Diagnosis Using a Frozen Black-Box Inference Network: Nhat-Tuong Do-Tran,

Ngoc-Hoang-Lam Le,

Ching-Chun Huang; [pdf] [supp]
[bibtex]
@InProceedings{Do-Tran_2026_WACV, author = {Do-Tran, Nhat-Tuong and Le, Ngoc-Hoang-Lam and Huang, Ching-Chun}, title = {UI-Styler: Ultrasound Image Style Transfer with Class-Aware Prompts for Cross-Device Diagnosis Using a Frozen Black-Box Inference Network}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2765-2774} }
Dressing the Imagination: A Dataset for AI-Powered Translation of Text into Fashion Outfits and A Novel NeRA Adapter for Enhanced Feature Adaptation: Gayatri Deshmukh,

Somsubhra De,

Chirag Sehgal,

Jishu Sen Gupta,

Sparsh Mittal; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Deshmukh_2026_WACV, author = {Deshmukh, Gayatri and De, Somsubhra and Sehgal, Chirag and Gupta, Jishu Sen and Mittal, Sparsh}, title = {Dressing the Imagination: A Dataset for AI-Powered Translation of Text into Fashion Outfits and A Novel NeRA Adapter for Enhanced Feature Adaptation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2094-2103} }
SENCA-st: Integrating Spatial Transcriptomics and Histopathology with Cross Attention Shared Encoder for Region Identification in Cancer Pathology: Shanaka Liyanaarachchi,

Chathurya Wijethunga,

Shihab Aaqil Ahamed,

Akthas Absar,

Ranga Rodrigo; [pdf] [arXiv]
[bibtex]
@InProceedings{Liyanaarachchi_2026_WACV, author = {Liyanaarachchi, Shanaka and Wijethunga, Chathurya and Ahamed, Shihab Aaqil and Absar, Akthas and Rodrigo, Ranga}, title = {SENCA-st: Integrating Spatial Transcriptomics and Histopathology with Cross Attention Shared Encoder for Region Identification in Cancer Pathology}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3578-3587} }
UniDiff: Parameter-Efficient Adaptation of Diffusion Models for Land Cover Classification with Multi-Modal Remotely Sensed Imagery and Sparse Annotations: Yuzhen Hu,

Saurabh Prasad; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hu_2026_WACV, author = {Hu, Yuzhen and Prasad, Saurabh}, title = {UniDiff: Parameter-Efficient Adaptation of Diffusion Models for Land Cover Classification with Multi-Modal Remotely Sensed Imagery and Sparse Annotations}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4611-4620} }
Show Me: Unifying Instructional Image and Video Generation with Diffusion Models: Yujiang Pu,

Zhanbo Huang,

Vishnu Boddeti,

Yu Kong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pu_2026_WACV, author = {Pu, Yujiang and Huang, Zhanbo and Boddeti, Vishnu and Kong, Yu}, title = {Show Me: Unifying Instructional Image and Video Generation with Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3285-3296} }
Marshaled Learning: Bridging Large Neural Networks with Memory-Constrained Trusted Execution Environments in Federated Learning: Shiwei Ding,

Xiaoyong Yuan,

Zhenlin Wang,

Lan Emily Zhang,

Giuseppe Ateniese; [pdf] [supp]
[bibtex]
@InProceedings{Ding_2026_WACV, author = {Ding, Shiwei and Yuan, Xiaoyong and Wang, Zhenlin and Zhang, Lan Emily and Ateniese, Giuseppe}, title = {Marshaled Learning: Bridging Large Neural Networks with Memory-Constrained Trusted Execution Environments in Federated Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {647-656} }
Reconstructing Realistic and Relightable Eyes: Wesley Khademi,

Jogendra Kundu,

Yatong An,

Alexander Fix,

David Colmenares; [pdf] [supp]
[bibtex]
@InProceedings{Khademi_2026_WACV, author = {Khademi, Wesley and Kundu, Jogendra and An, Yatong and Fix, Alexander and Colmenares, David}, title = {Reconstructing Realistic and Relightable Eyes}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2242-2252} }
Deep Image Decomposition for Medical Imaging Anonymization and Curation: Yael Elkin,

Gal Ben-Arie,

Tammy Riklin-Raviv; [pdf] [supp]
[bibtex]
@InProceedings{Elkin_2026_WACV, author = {Elkin, Yael and Ben-Arie, Gal and Riklin-Raviv, Tammy}, title = {Deep Image Decomposition for Medical Imaging Anonymization and Curation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7229-7238} }
An Efficient Multi-Rater Setup Towards Personalized and Diversified Medical Image Segmentation: Sajed Almorsy,

Ayman Khalafallah,

Marwan Torki; [pdf] [supp]
[bibtex]
@InProceedings{Almorsy_2026_WACV, author = {Almorsy, Sajed and Khalafallah, Ayman and Torki, Marwan}, title = {An Efficient Multi-Rater Setup Towards Personalized and Diversified Medical Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5322-5331} }
Clear Sights on Site: A Spatial-Adaptive Channel Network for Deblurring Construction Site Images: Mahdi Bonyani,

Maryam Soleymani,

Chao Wang; [pdf] [supp]
[bibtex]
@InProceedings{Bonyani_2026_WACV, author = {Bonyani, Mahdi and Soleymani, Maryam and Wang, Chao}, title = {Clear Sights on Site: A Spatial-Adaptive Channel Network for Deblurring Construction Site Images}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6936-6945} }
GRAPE (Gaussian Rendering for Accelerated Pixel Enhancement) Brings Fast and Lightweight Arbitrary Super-Resolution: Jung In Jang,

Kyong Hwan Jin; [pdf] [supp]
[bibtex]
@InProceedings{Jang_2026_WACV, author = {Jang, Jung In and Jin, Kyong Hwan}, title = {GRAPE (Gaussian Rendering for Accelerated Pixel Enhancement) Brings Fast and Lightweight Arbitrary Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7750-7758} }
HodgeFormer: Transformers for Learnable Operators on Triangular Meshes through Data-Driven Hodge Matrices: Akis Nousias,

Stavros Nousias; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nousias_2026_WACV, author = {Nousias, Akis and Nousias, Stavros}, title = {HodgeFormer: Transformers for Learnable Operators on Triangular Meshes through Data-Driven Hodge Matrices}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6796-6805} }
Revisiting Vision-Language Foundations for No-Reference Image Quality Assessment: Ankit Yadav,

Ta Duc Huy,

Lingqiao Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yadav_2026_WACV, author = {Yadav, Ankit and Huy, Ta Duc and Liu, Lingqiao}, title = {Revisiting Vision-Language Foundations for No-Reference Image Quality Assessment}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5416-5425} }
PS3: Part Level Instance Segmentation in 3D: Hong-Xuan Yen,

Chiamin Chen,

Yanqing Wang,

Yu-Lun Liu,

Min Sun; [pdf] [supp]
[bibtex]
@InProceedings{Yen_2026_WACV, author = {Yen, Hong-Xuan and Chen, Chiamin and Wang, Yanqing and Liu, Yu-Lun and Sun, Min}, title = {PS3: Part Level Instance Segmentation in 3D}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {898-906} }
UNO: Unifying One-stage Video Scene Graph Generation via Object-Centric Visual Representation Learning: Huy Le,

Nhat Chung,

Tung Kieu,

Jingkang Yang,

Ngan Le; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Le_2026_WACV, author = {Le, Huy and Chung, Nhat and Kieu, Tung and Yang, Jingkang and Le, Ngan}, title = {UNO: Unifying One-stage Video Scene Graph Generation via Object-Centric Visual Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2797-2807} }
ITSELF: Attention Guided Fine-Grained Alignment for Vision-Language Retrieval: Tien-Huy Nguyen,

Huu-Loc Tran,

Thanh Duc Ngo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nguyen_2026_WACV, author = {Nguyen, Tien-Huy and Tran, Huu-Loc and Ngo, Thanh Duc}, title = {ITSELF: Attention Guided Fine-Grained Alignment for Vision-Language Retrieval}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1448-1458} }
Structure-Aware Feature Rectification with Region Adjacency Graphs for Training-free Open-Vocabulary Semantic Segmentation: Qiming Huang,

Hao Ai,

Jianbo Jiao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2026_WACV, author = {Huang, Qiming and Ai, Hao and Jiao, Jianbo}, title = {Structure-Aware Feature Rectification with Region Adjacency Graphs for Training-free Open-Vocabulary Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4118-4127} }
Uplifting Table Tennis: A Robust, Real-World Application for 3D Trajectory and Spin Estimation: Daniel Kienzle,

Katja Ludwig,

Julian Lorenz,

Shin'Ichi Satoh,

Rainer Lienhart; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kienzle_2026_WACV, author = {Kienzle, Daniel and Ludwig, Katja and Lorenz, Julian and Satoh, Shin'Ichi and Lienhart, Rainer}, title = {Uplifting Table Tennis: A Robust, Real-World Application for 3D Trajectory and Spin Estimation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7440-7449} }
Empowering Source-Free Domain Adaptation via MLLM-Guided Reliability-Based Curriculum Learning: Dongjie Chen,

Kartik Patwari,

Zhengfeng Lai,

Xiaoguang Zhu,

Sen-ching Cheung,

Chen-Nee Chuah; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2026_WACV, author = {Chen, Dongjie and Patwari, Kartik and Lai, Zhengfeng and Zhu, Xiaoguang and Cheung, Sen-ching and Chuah, Chen-Nee}, title = {Empowering Source-Free Domain Adaptation via MLLM-Guided Reliability-Based Curriculum Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4262-4272} }
LighthouseGS: Indoor Structure-aware 3D Gaussian Splatting for Panorama-Style Mobile Captures: Seungoh Han,

Jaehoon Jang,

Hyunsu Kim,

Jaeheung Surh,

Junhyung Kwak,

Hyowon Ha,

Kyungdon Joo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Han_2026_WACV, author = {Han, Seungoh and Jang, Jaehoon and Kim, Hyunsu and Surh, Jaeheung and Kwak, Junhyung and Ha, Hyowon and Joo, Kyungdon}, title = {LighthouseGS: Indoor Structure-aware 3D Gaussian Splatting for Panorama-Style Mobile Captures}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3441-3450} }
Mitigating Object and Action Hallucinations in Multimodal LLMs via Self-Augmented Contrastive Alignment: Kai-Po Chang,

Wei-Yuan Cheng,

Chi-Pin Huang,

Fu-En Yang,

Yu-Chiang Frank Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chang_2026_WACV, author = {Chang, Kai-Po and Cheng, Wei-Yuan and Huang, Chi-Pin and Yang, Fu-En and Wang, Yu-Chiang Frank}, title = {Mitigating Object and Action Hallucinations in Multimodal LLMs via Self-Augmented Contrastive Alignment}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3172-3181} }
Segmentation-Aware Latent Diffusion for Satellite Image Super-Resolution: Enabling Smallholder Farm Boundary Delineation: Aditi Agarwal,

Anjali Jain,

Nikita Saxena,

Ishan Deshpande,

Michal Kazmierski,

Abigail Annkah,

Nadav Sherman,

Karthikeyan Shanmugam,

Alok Talekar,

Vaibhav Rajan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Agarwal_2026_WACV, author = {Agarwal, Aditi and Jain, Anjali and Saxena, Nikita and Deshpande, Ishan and Kazmierski, Michal and Annkah, Abigail and Sherman, Nadav and Shanmugam, Karthikeyan and Talekar, Alok and Rajan, Vaibhav}, title = {Segmentation-Aware Latent Diffusion for Satellite Image Super-Resolution: Enabling Smallholder Farm Boundary Delineation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1864-1874} }
Eff-GRot: Efficient and Generalizable Rotation Estimation with Transformers: Fanis Mathioulakis,

Gorjan Radevski,

Tinne Tuytelaars; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mathioulakis_2026_WACV, author = {Mathioulakis, Fanis and Radevski, Gorjan and Tuytelaars, Tinne}, title = {Eff-GRot: Efficient and Generalizable Rotation Estimation with Transformers}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {412-421} }
Roadside Monocular 3D Detection Prompted by 2D Detection: Yechi Ma,

Wei Hua,

Yanan Li,

Shu Kong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ma_2026_WACV, author = {Ma, Yechi and Hua, Wei and Li, Yanan and Kong, Shu}, title = {Roadside Monocular 3D Detection Prompted by 2D Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1895-1905} }
Divide and Refine: Enhancing Multimodal Representation and Explainability for Emotion Recognition in Conversation: Anh-Tuan Mai,

Cam-Van Thi Nguyen,

Duc-Trong Le; [pdf] [arXiv]
[bibtex]
@InProceedings{Mai_2026_WACV, author = {Mai, Anh-Tuan and Nguyen, Cam-Van Thi and Le, Duc-Trong}, title = {Divide and Refine: Enhancing Multimodal Representation and Explainability for Emotion Recognition in Conversation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2700-2709} }
End-to-End Fine-Tuning of 3D Texture Generation using Differentiable Rewards: AmirHossein Zamani,

Tianhao Xie,

Amir G. Aghdam,

Tiberiu Popa,

Eugene Belilovsky; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zamani_2026_WACV, author = {Zamani, AmirHossein and Xie, Tianhao and Aghdam, Amir G. and Popa, Tiberiu and Belilovsky, Eugene}, title = {End-to-End Fine-Tuning of 3D Texture Generation using Differentiable Rewards}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {171-180} }
ImageNet-sES: A First Systematic Study of Sensor-Environment Simulation Anchored by Real Recaptures: Ji-yoon Kim,

Eunsu Baek,

Hyung-Sin Kim; [pdf]
[bibtex]
@InProceedings{Kim_2026_WACV, author = {Kim, Ji-yoon and Baek, Eunsu and Kim, Hyung-Sin}, title = {ImageNet-sES: A First Systematic Study of Sensor-Environment Simulation Anchored by Real Recaptures}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1117-1126} }
LVM-Lite: Training Large Vision Models with Efficient Sequential Modeling: Xianhang Li,

Hongru Zhu,

Sucheng Ren,

Linjie Yang,

Peng Wang,

Heng Wang,

Xiaohui Shen,

Qing Liu,

Cihang Xie; [pdf] [supp]
[bibtex]
@InProceedings{Li_2026_WACV, author = {Li, Xianhang and Zhu, Hongru and Ren, Sucheng and Yang, Linjie and Wang, Peng and Wang, Heng and Shen, Xiaohui and Liu, Qing and Xie, Cihang}, title = {LVM-Lite: Training Large Vision Models with Efficient Sequential Modeling}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4566-4576} }
MEDAL: multi-modal MEta-space Distillation and ALignment for Visual Compatibility Learning: Dween Rabius Sanny,

Vinay Kumar Verma,

Prateek Sircar,

Deepak Gupta; [pdf] [supp]
[bibtex]
@InProceedings{Sanny_2026_WACV, author = {Sanny, Dween Rabius and Verma, Vinay Kumar and Sircar, Prateek and Gupta, Deepak}, title = {MEDAL: multi-modal MEta-space Distillation and ALignment for Visual Compatibility Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {888-897} }
Rank-based Geographical Regularization: Revisiting Contrastive Self-Supervised Learning for Multispectral Remote Sensing Imagery: Tom Burgert,

Leonard Hackel,

Paolo Rota,

Begüm Demir; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Burgert_2026_WACV, author = {Burgert, Tom and Hackel, Leonard and Rota, Paolo and Demir, Beg\"um}, title = {Rank-based Geographical Regularization: Revisiting Contrastive Self-Supervised Learning for Multispectral Remote Sensing Imagery}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4375-4385} }
LiDAR-DHMT: LiDAR-Adaptive Dual Hierarchical Mask Transformer for Robust Freespace Detection and Semantic Segmentation: Siyu Chen,

Ting Han,

Changshe Zhang,

Xin Luo,

Huan Chen,

Meiliu Wu,

Guorong Cai,

Jinhe Su; [pdf]
[bibtex]
@InProceedings{Chen_2026_WACV, author = {Chen, Siyu and Han, Ting and Zhang, Changshe and Luo, Xin and Chen, Huan and Wu, Meiliu and Cai, Guorong and Su, Jinhe}, title = {LiDAR-DHMT: LiDAR-Adaptive Dual Hierarchical Mask Transformer for Robust Freespace Detection and Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1252-1261} }
SCATR: Mitigating New Instance Suppression in LiDAR-based Tracking-by-Attention via Second Chance Assignment and Track Query Dropout: Brian Cheong,

Letian Wang,

Sandro Papais,

Steven L. Waslander; [pdf] [supp]
[bibtex]
@InProceedings{Cheong_2026_WACV, author = {Cheong, Brian and Wang, Letian and Papais, Sandro and Waslander, Steven L.}, title = {SCATR: Mitigating New Instance Suppression in LiDAR-based Tracking-by-Attention via Second Chance Assignment and Track Query Dropout}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3330-3339} }
GeneVA: A Dataset of Human Annotations for Generative Text to Video Artifacts: Jenna Kang,

Maria Beatriz Silva,

Patsorn Sangkloy,

Kenneth Chen,

Niall L. Williams,

Qi Sun; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kang_2026_WACV, author = {Kang, Jenna and Silva, Maria Beatriz and Sangkloy, Patsorn and Chen, Kenneth and Williams, Niall L. and Sun, Qi}, title = {GeneVA: A Dataset of Human Annotations for Generative Text to Video Artifacts}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6174-6183} }
Domain Generalizing DINO for Visual Regression via Latent Distractor Subspace Consistency: Nikhil Reddy,

Chetan Arora,

Mahsa Baktashmotlagh; [pdf] [supp]
[bibtex]
@InProceedings{Reddy_2026_WACV, author = {Reddy, Nikhil and Arora, Chetan and Baktashmotlagh, Mahsa}, title = {Domain Generalizing DINO for Visual Regression via Latent Distractor Subspace Consistency}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4057-4066} }
Dragonite: Single-Step Drag-based Image Editing with Geometric-Semantic Guidance: Meng-Ting Jhong,

Tai-Ming Huang,

Shang-Fu Chen,

Wen-Huang Cheng,

Kai-Lung Hua; [pdf] [supp]
[bibtex]
@InProceedings{Jhong_2026_WACV, author = {Jhong, Meng-Ting and Huang, Tai-Ming and Chen, Shang-Fu and Cheng, Wen-Huang and Hua, Kai-Lung}, title = {Dragonite: Single-Step Drag-based Image Editing with Geometric-Semantic Guidance}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3057-3066} }
Synthesizing Compositional Videos from Text Description: Prajwal Singh,

Kuldeep Kulkarni,

Shanmuganathan Raman,

Harsh Rangwani; [pdf] [supp]
[bibtex]
@InProceedings{Singh_2026_WACV, author = {Singh, Prajwal and Kulkarni, Kuldeep and Raman, Shanmuganathan and Rangwani, Harsh}, title = {Synthesizing Compositional Videos from Text Description}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6775-6784} }
Layout Anything: One Transformer for Universal Room Layout Estimation: Md Sohag Mia,

Muhammad Abdullah Adnan; [pdf] [arXiv]
[bibtex]
@InProceedings{Mia_2026_WACV, author = {Mia, Md Sohag and Adnan, Muhammad Abdullah}, title = {Layout Anything: One Transformer for Universal Room Layout Estimation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1565-1574} }
TS-PCI: Point Cloud Frame Interpolation with Time-Aware Point Cloud Sampling and Self-Supervised Learning Strategy: Kohei Matsuzaki,

Keisuke Nonaka; [pdf]
[bibtex]
@InProceedings{Matsuzaki_2026_WACV, author = {Matsuzaki, Kohei and Nonaka, Keisuke}, title = {TS-PCI: Point Cloud Frame Interpolation with Time-Aware Point Cloud Sampling and Self-Supervised Learning Strategy}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {54-65} }
UniCoRN: Latent Diffusion-based Unified Controllable Image Restoration Network across Multiple Degradations: Debabrata Mandal,

Soumitri Chattopadhyay,

Guansen Tong,

Praneeth Chakravarthula; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mandal_2026_WACV, author = {Mandal, Debabrata and Chattopadhyay, Soumitri and Tong, Guansen and Chakravarthula, Praneeth}, title = {UniCoRN: Latent Diffusion-based Unified Controllable Image Restoration Network across Multiple Degradations}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1543-1553} }
MergeSlide: Continual Model Merging and Task-to-Class Prompt-Aligned Inference for Lifelong Learning on Whole Slide Images: Doanh C. Bui,

Ba Hung Ngo,

Hoai Luan Pham,

Khang Nguyen,

Maï K. Nguyen,

Yasuhiko Nakashima; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bui_2026_WACV, author = {Bui, Doanh C. and Ngo, Ba Hung and Pham, Hoai Luan and Nguyen, Khang and Nguyen, Ma{\"\i} K. and Nakashima, Yasuhiko}, title = {MergeSlide: Continual Model Merging and Task-to-Class Prompt-Aligned Inference for Lifelong Learning on Whole Slide Images}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4859-4868} }
Quantifying the Limits of Segmentation Foundation Models: Modeling Challenges in Segmenting Tree-Like and Low-Contrast Objects: Yixin Zhang,

Nicholas Konz,

Kevin Kramer,

Maciej A. Mazurowski; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2026_WACV, author = {Zhang, Yixin and Konz, Nicholas and Kramer, Kevin and Mazurowski, Maciej A.}, title = {Quantifying the Limits of Segmentation Foundation Models: Modeling Challenges in Segmenting Tree-Like and Low-Contrast Objects}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5205-5215} }
Spec-Gloss Surfels and Normal-Diffuse Priors for Relightable Glossy Objects: Georgios Kouros,

Minye Wu,

Tinne Tuytelaars; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kouros_2026_WACV, author = {Kouros, Georgios and Wu, Minye and Tuytelaars, Tinne}, title = {Spec-Gloss Surfels and Normal-Diffuse Priors for Relightable Glossy Objects}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4417-4426} }
WorkZone3D: A Multimodal Dataset for 3D Work Zone Perception in Autonomous Driving: Shounak Sural,

Nishad Sahu,

Ragunathan Rajkumar; [pdf] [supp]
[bibtex]
@InProceedings{Sural_2026_WACV, author = {Sural, Shounak and Sahu, Nishad and Rajkumar, Ragunathan}, title = {WorkZone3D: A Multimodal Dataset for 3D Work Zone Perception in Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3972-3981} }
Learning Compact Video Representations for Efficient Long-form Video Understanding in Large Multimodal Models: Yuxiao Chen,

Jue Wang,

Zhikang Zhang,

Jingru Yi,

Xu Zhang,

Yang Zou,

Zhaowei Cai,

Jianbo Yuan,

Xinyu Li,

Hao Yang,

Davide Modolo; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2026_WACV, author = {Chen, Yuxiao and Wang, Jue and Zhang, Zhikang and Yi, Jingru and Zhang, Xu and Zou, Yang and Cai, Zhaowei and Yuan, Jianbo and Li, Xinyu and Yang, Hao and Modolo, Davide}, title = {Learning Compact Video Representations for Efficient Long-form Video Understanding in Large Multimodal Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4242-4252} }
CURIO: Curvature-Aligned and Efficient OCR for Low-Resource Historical Manuscripts: Sai Madhusudan Gunda,

Tathagata Ghosh,

Simran Singh Sandral,

Ravi Kiran Sarvadevabhatla; [pdf] [supp]
[bibtex]
@InProceedings{Gunda_2026_WACV, author = {Gunda, Sai Madhusudan and Ghosh, Tathagata and Sandral, Simran Singh and Sarvadevabhatla, Ravi Kiran}, title = {CURIO: Curvature-Aligned and Efficient OCR for Low-Resource Historical Manuscripts}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2011-2021} }
Surgical Gaussian Surfels: Highly Accurate Real-time Surgical Scene Rendering using Gaussian Surfels: Idris O. Sunmola,

Zhenjun Zhao,

Samuel Schmidgall,

Yumeng Wang,

Paul Maria Scheikl,

Viet Pham,

Axel Krieger; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sunmola_2026_WACV, author = {Sunmola, Idris O. and Zhao, Zhenjun and Schmidgall, Samuel and Wang, Yumeng and Scheikl, Paul Maria and Pham, Viet and Krieger, Axel}, title = {Surgical Gaussian Surfels: Highly Accurate Real-time Surgical Scene Rendering using Gaussian Surfels}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4515-4524} }
InteracTalker: Prompt-Based Human-Object Interaction with Co-Speech Gesture Generation: Sreehari Rajan,

Kunal Bhosikar,

Charu Sharma; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Rajan_2026_WACV, author = {Rajan, Sreehari and Bhosikar, Kunal and Sharma, Charu}, title = {InteracTalker: Prompt-Based Human-Object Interaction with Co-Speech Gesture Generation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1438-1447} }
SSMT-Net: A Semi-Supervised Multitask Transformer-Based Network for Thyroid Nodule Segmentation in Ultrasound Images: Muhammad Umar Farooq,

Abd Ur Rehman,

Azka Rehman,

Muhammad Usman,

Dong-Kyu Chae; [pdf]
[bibtex]
@InProceedings{Farooq_2026_WACV, author = {Farooq, Muhammad Umar and Rehman, Abd Ur and Rehman, Azka and Usman, Muhammad and Chae, Dong-Kyu}, title = {SSMT-Net: A Semi-Supervised Multitask Transformer-Based Network for Thyroid Nodule Segmentation in Ultrasound Images}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6069-6079} }
SAVE: Sparse Autoencoder-Driven Visual Information Enhancement for Mitigating Object Hallucination: Sangha Park,

Seungryong Yoo,

Jisoo Mok,

Sungroh Yoon; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Park_2026_WACV, author = {Park, Sangha and Yoo, Seungryong and Mok, Jisoo and Yoon, Sungroh}, title = {SAVE: Sparse Autoencoder-Driven Visual Information Enhancement for Mitigating Object Hallucination}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7935-7944} }
Non-Aligned Reference Image Quality Assessment for Novel View Synthesis: Abhijay Ghildyal,

Rajesh Sureddi,

Nabajeet Barman,

Saman Zadtootaghaj,

Alan C Bovik; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ghildyal_2026_WACV, author = {Ghildyal, Abhijay and Sureddi, Rajesh and Barman, Nabajeet and Zadtootaghaj, Saman and Bovik, Alan C}, title = {Non-Aligned Reference Image Quality Assessment for Novel View Synthesis}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6350-6359} }
PSDiffusion: Harmonized Multi-Layer Image Generation via Layout and Appearance Alignment: Dingbang Huang,

Wenbo Li,

Yifei Zhao,

Xinyu Pan,

Yanhong Zeng,

Bo Dai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2026_WACV, author = {Huang, Dingbang and Li, Wenbo and Zhao, Yifei and Pan, Xinyu and Zeng, Yanhong and Dai, Bo}, title = {PSDiffusion: Harmonized Multi-Layer Image Generation via Layout and Appearance Alignment}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3233-3242} }
HiMix : Hierarchical Visual-Textual Mixing Network for Lesion Segmentation: Soojin Hwang,

Jaeyoon Sim,

Won Hwa Kim; [pdf] [supp]
[bibtex]
@InProceedings{Hwang_2026_WACV, author = {Hwang, Soojin and Sim, Jaeyoon and Kim, Won Hwa}, title = {HiMix : Hierarchical Visual-Textual Mixing Network for Lesion Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5332-5341} }
EllipssianNet: Image-guided Sampling of 2D Gaussians for Gaussian Splatting: MyoungGon Kim,

JeongHyeon Ahn,

Seohyeon Park,

Hyemi Kim,

Seunghyun Park,

Jung Ho Hwang,

JungHyun Han; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2026_WACV, author = {Kim, MyoungGon and Ahn, JeongHyeon and Park, Seohyeon and Kim, Hyemi and Park, Seunghyun and Hwang, Jung Ho and Han, JungHyun}, title = {EllipssianNet: Image-guided Sampling of 2D Gaussians for Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2104-2113} }
BAFLE-DCT: Bypassing Adversarial Filters via Frequency-Selective Embedding in the DCT Domain: Thilina Mendis,

Farah Kandah,

Sathyanarayanan N. Aakur; [pdf]
[bibtex]
@InProceedings{Mendis_2026_WACV, author = {Mendis, Thilina and Kandah, Farah and Aakur, Sathyanarayanan N.}, title = {BAFLE-DCT: Bypassing Adversarial Filters via Frequency-Selective Embedding in the DCT Domain}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5967-5976} }
SSplain: Sparse and Smooth Explainer for Retinopathy of Prematurity Classification: Elifnur Sunger,

Tales Imbiriba,

Peter Campbell,

Deniz Erdogmus,

Stratis Ioannidis,

Jennifer Dy; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sunger_2026_WACV, author = {Sunger, Elifnur and Imbiriba, Tales and Campbell, Peter and Erdogmus, Deniz and Ioannidis, Stratis and Dy, Jennifer}, title = {SSplain: Sparse and Smooth Explainer for Retinopathy of Prematurity Classification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1705-1715} }
VLMDiff: Leveraging Vision-Language Models for Multi-Class Anomaly Detection with Diffusion: Samet Hicsonmez,

Abd El Rahman Shabayek,

Djamila Aouada; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hicsonmez_2026_WACV, author = {Hicsonmez, Samet and El Rahman Shabayek, Abd and Aouada, Djamila}, title = {VLMDiff: Leveraging Vision-Language Models for Multi-Class Anomaly Detection with Diffusion}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6309-6319} }
MapVerse: A Benchmark for Geospatial Question Answering on Diverse Real-World Maps: Sharat Bhat,

Harshita Khandelwal,

Tushar Kataria,

Vivek Gupta; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bhat_2026_WACV, author = {Bhat, Sharat and Khandelwal, Harshita and Kataria, Tushar and Gupta, Vivek}, title = {MapVerse: A Benchmark for Geospatial Question Answering on Diverse Real-World Maps}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8168-8178} }
Integrating Multi-scale and Multi-filtration Topological Features for Medical Image Classification: Pengfei Gu,

Huimin Li,

Haoteng Tang,

Dongkuan Xu,

Erik Enriquez,

DongChul Kim,

Bin Fu,

Danny Z Chen; [pdf] [arXiv]
[bibtex]
@InProceedings{Gu_2026_WACV, author = {Gu, Pengfei and Li, Huimin and Tang, Haoteng and Xu, Dongkuan and Enriquez, Erik and Kim, DongChul and Fu, Bin and Chen, Danny Z}, title = {Integrating Multi-scale and Multi-filtration Topological Features for Medical Image Classification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8660-8669} }
FlyPose: Towards Robust Human Pose Estimation From Aerial Views: Hassaan Farooq,

Marvin Brenner,

Peter Stütz; [pdf]
[bibtex]
@InProceedings{Farooq_2026_WACV, author = {Farooq, Hassaan and Brenner, Marvin and St\"utz, Peter}, title = {FlyPose: Towards Robust Human Pose Estimation From Aerial Views}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8617-8627} }
AdaptViG: Adaptive Vision GNN with Exponential Decay Gating: Mustafa Munir,

Md Mostafijur Rahman,

Radu Marculescu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Munir_2026_WACV, author = {Munir, Mustafa and Rahman, Md Mostafijur and Marculescu, Radu}, title = {AdaptViG: Adaptive Vision GNN with Exponential Decay Gating}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {440-450} }
SAVeD: Learning to Denoise Low-SNR Video for Improved Downstream Performance: Suzanne Stathatos,

Michael Hobley,

Pietro Perona,

Markus Marks; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Stathatos_2026_WACV, author = {Stathatos, Suzanne and Hobley, Michael and Perona, Pietro and Marks, Markus}, title = {SAVeD: Learning to Denoise Low-SNR Video for Improved Downstream Performance}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6851-6861} }
See, Record, Do: Automated Generation of UI Workflows from Tutorial Videos: Adam Beauchaine,

Craig Shue; [pdf]
[bibtex]
@InProceedings{Beauchaine_2026_WACV, author = {Beauchaine, Adam and Shue, Craig}, title = {See, Record, Do: Automated Generation of UI Workflows from Tutorial Videos}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6256-6265} }
VADER: Towards Causal Video Anomaly Understanding with Relation-Aware Large Language Models: Ying Cheng,

Yu-Ho Lin,

Min-Hung Chen,

Fu-En Yang,

Shang-Hong Lai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cheng_2026_WACV, author = {Cheng, Ying and Lin, Yu-Ho and Chen, Min-Hung and Yang, Fu-En and Lai, Shang-Hong}, title = {VADER: Towards Causal Video Anomaly Understanding with Relation-Aware Large Language Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7301-7311} }
Pretraining Helps When Capacity Allows: Evidence from Ultra-Small ConvNets: Srikanth Muralidharan,

Heitor R. Medeiros,

Masih Aminbeidokhti,

Eric Granger,

Marco Pedersoli; [pdf] [supp]
[bibtex]
@InProceedings{Muralidharan_2026_WACV, author = {Muralidharan, Srikanth and Medeiros, Heitor R. and Aminbeidokhti, Masih and Granger, Eric and Pedersoli, Marco}, title = {Pretraining Helps When Capacity Allows: Evidence from Ultra-Small ConvNets}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8333-8342} }
SmoothDiffusion-VE: Real-time Generative Video Editing Using Adaptive Feature Cache: Mustafa Munir,

Sophia Zalewski,

Shiqiu Liu,

David Tarjan,

Sushmitha Belede,

Anjul Patney,

Radu Marculescu; [pdf] [supp]
[bibtex]
@InProceedings{Munir_2026_WACV, author = {Munir, Mustafa and Zalewski, Sophia and Liu, Shiqiu and Tarjan, David and Belede, Sushmitha and Patney, Anjul and Marculescu, Radu}, title = {SmoothDiffusion-VE: Real-time Generative Video Editing Using Adaptive Feature Cache}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8468-8478} }
CropAT: Leveraging Diffusion-Generated Target-Like Cropped Objects for Pseudo-Label Refinement in Domain-Adaptive Object Detection: Chen-Che Huang,

Tzuhsuan Huang,

Jun-Cheng Chen; [pdf] [supp]
[bibtex]
@InProceedings{Huang_2026_WACV, author = {Huang, Chen-Che and Huang, Tzuhsuan and Chen, Jun-Cheng}, title = {CropAT: Leveraging Diffusion-Generated Target-Like Cropped Objects for Pseudo-Label Refinement in Domain-Adaptive Object Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4621-4630} }
Leveraging Sparsity for Privacy in Collaborative Inference: Maximilian Andreas Hoefler,

Karsten Mueller,

Wojciech Samek; [pdf] [supp]
[bibtex]
@InProceedings{Hoefler_2026_WACV, author = {Hoefler, Maximilian Andreas and Mueller, Karsten and Samek, Wojciech}, title = {Leveraging Sparsity for Privacy in Collaborative Inference}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7596-7604} }
Rethinking Real Image Editing: Unleashing Diverse Editing Operators via Multi-Objective Optimization: Siyuan Wang,

Xi Yang,

Zihao Zhou,

Huiru Shao,

Rui Zhang,

Qiufeng Wang,

Guangliang Cheng,

Kaizhu Huang; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2026_WACV, author = {Wang, Siyuan and Yang, Xi and Zhou, Zihao and Shao, Huiru and Zhang, Rui and Wang, Qiufeng and Cheng, Guangliang and Huang, Kaizhu}, title = {Rethinking Real Image Editing: Unleashing Diverse Editing Operators via Multi-Objective Optimization}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4150-4159} }
UltraClean: A Simple Framework to Train Robust Neural Networks against Backdoor Attacks: Bingyin Zhao,

Yingjie Lao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2026_WACV, author = {Zhao, Bingyin and Lao, Yingjie}, title = {UltraClean: A Simple Framework to Train Robust Neural Networks against Backdoor Attacks}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8353-8363} }
A Little More Like This: Text-to-Image Retrieval with Vision-Language Models Using Relevance Feedback: Bulat Khaertdinov,

Mirela Popa,

Nava Tintarev; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Khaertdinov_2026_WACV, author = {Khaertdinov, Bulat and Popa, Mirela and Tintarev, Nava}, title = {A Little More Like This: Text-to-Image Retrieval with Vision-Language Models Using Relevance Feedback}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3825-3834} }
CONSTANT: Towards High-Quality One-Shot Handwriting Generation with Patch Contrastive Enhancement and Style-Aware Quantization: Anh-Duy Le,

Van-Linh Pham,

Thanh-Nam Vo,

Xuan Toan Mai,

Tuan-Anh Tran; [pdf] [supp]
[bibtex]
@InProceedings{Le_2026_WACV, author = {Le, Anh-Duy and Pham, Van-Linh and Vo, Thanh-Nam and Mai, Xuan Toan and Tran, Tuan-Anh}, title = {CONSTANT: Towards High-Quality One-Shot Handwriting Generation with Patch Contrastive Enhancement and Style-Aware Quantization}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4295-4304} }
QAL : A Loss for Recall-Precision Balance in 3D Reconstruction: Pranay Meshram,

Yash Turkar,

Kartikeya Singh,

Praveen Raj Masilamani,

Charuvahan Adhivarahan,

Karthik Dantu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Meshram_2026_WACV, author = {Meshram, Pranay and Turkar, Yash and Singh, Kartikeya and Masilamani, Praveen Raj and Adhivarahan, Charuvahan and Dantu, Karthik}, title = {QAL : A Loss for Recall-Precision Balance in 3D Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7965-7974} }
PADM: A Physics-aware Diffusion Model for Attenuation Correction: Trung Kien Pham,

Hoang Minh Vu,

Anh Duc Chu,

Dac Thai Nguyen,

Trung Thanh Nguyen,

Thao Nguyen Truong,

Mai Hong Son,

Thanh Trung Nguyen,

Phi Le Nguyen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pham_2026_WACV, author = {Pham, Trung Kien and Vu, Hoang Minh and Chu, Anh Duc and Nguyen, Dac Thai and Nguyen, Trung Thanh and Truong, Thao Nguyen and Son, Mai Hong and Nguyen, Thanh Trung and Le Nguyen, Phi}, title = {PADM: A Physics-aware Diffusion Model for Attenuation Correction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2606-2615} }
FB-4D: Spatial-Temporal Coherent Dynamic 3D Content Generation with Feature Banks: Jinwei Li,

Huan-Ang Gao,

Wenyi Li,

Haohan Chi,

Chenyu Liu,

Chenxi Du,

Yiqian Liu,

Mingju Gao,

Guiyu Zhang,

Zongzheng Zhang,

Li Yi,

Yao Yao,

Jingwei Zhao,

Hongyang Li,

Yikai Wang,

Hao Zhao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2026_WACV, author = {Li, Jinwei and Gao, Huan-Ang and Li, Wenyi and Chi, Haohan and Liu, Chenyu and Du, Chenxi and Liu, Yiqian and Gao, Mingju and Zhang, Guiyu and Zhang, Zongzheng and Yi, Li and Yao, Yao and Zhao, Jingwei and Li, Hongyang and Wang, Yikai and Zhao, Hao}, title = {FB-4D: Spatial-Temporal Coherent Dynamic 3D Content Generation with Feature Banks}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5290-5301} }
MEGA-PCC: A Mamba-based Efficient Approach for Joint Geometry and Attribute Point Cloud Compression: Kai-Hsiang Hsieh,

Monyneath Yim,

Wen-Hsiao Peng,

Jui-Chiu Chiang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hsieh_2026_WACV, author = {Hsieh, Kai-Hsiang and Yim, Monyneath and Peng, Wen-Hsiao and Chiang, Jui-Chiu}, title = {MEGA-PCC: A Mamba-based Efficient Approach for Joint Geometry and Attribute Point Cloud Compression}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1820-1830} }
CalibBEV: LiDAR-Camera Calibration via BEV Alignment: Filippo D'Addeo,

Lorenzo Cipelli,

Adriano Cardace,

Emanuele Ghelfi,

Andrea Zinelli,

Massimo Bertozzi; [pdf] [supp]
[bibtex]
@InProceedings{D'Addeo_2026_WACV, author = {D'Addeo, Filippo and Cipelli, Lorenzo and Cardace, Adriano and Ghelfi, Emanuele and Zinelli, Andrea and Bertozzi, Massimo}, title = {CalibBEV: LiDAR-Camera Calibration via BEV Alignment}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4345-4354} }
Interaction-via-Actions: Cattle Interaction Detection with Joint Learning of Action-Interaction Latent Space: Ren Nakagawa,

Yang Yang,

Risa Shinoda,

Hiroaki Santo,

Kenji Oyama,

Fumio Okura,

Takenao Ohkawa; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nakagawa_2026_WACV, author = {Nakagawa, Ren and Yang, Yang and Shinoda, Risa and Santo, Hiroaki and Oyama, Kenji and Okura, Fumio and Ohkawa, Takenao}, title = {Interaction-via-Actions: Cattle Interaction Detection with Joint Learning of Action-Interaction Latent Space}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1979-1988} }
RobustGait: Robustness Analysis for Appearance Based Gait Recognition: Reeshoon Sayera,

Akash Kumar,

Sirshapan Mitra,

Prudvi Kamtam,

Yogesh S Rawat; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sayera_2026_WACV, author = {Sayera, Reeshoon and Kumar, Akash and Mitra, Sirshapan and Kamtam, Prudvi and Rawat, Yogesh S}, title = {RobustGait: Robustness Analysis for Appearance Based Gait Recognition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2541-2552} }
DualRes: Production-ready Dynamic Object Detection: Jibril El Hassani,

Thomas Verelst; [pdf]
[bibtex]
@InProceedings{El_Hassani_2026_WACV, author = {El Hassani, Jibril and Verelst, Thomas}, title = {DualRes: Production-ready Dynamic Object Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7842-7851} }
DMS2F-HAD: A Dual-branch Mamba-based Spatial-Spectral Fusion Network for Hyperspectral Anomaly Detection: Aayushma Pant,

Lakpa Tamang,

Tsz-Kwan Lee,

Sunil Aryal; [pdf] [arXiv]
[bibtex]
@InProceedings{Pant_2026_WACV, author = {Pant, Aayushma and Tamang, Lakpa and Lee, Tsz-Kwan and Aryal, Sunil}, title = {DMS2F-HAD: A Dual-branch Mamba-based Spatial-Spectral Fusion Network for Hyperspectral Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5623-5632} }
FedSCAl: Leveraging Server and Client Alignment for Unsupervised Federated Source-Free Domain Adaptation: M. Yashwanth,

Sampath Koti,

Arunabh Singh,

Shyam Marjit,

Anirban Chakraborty; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yashwanth_2026_WACV, author = {Yashwanth, M. and Koti, Sampath and Singh, Arunabh and Marjit, Shyam and Chakraborty, Anirban}, title = {FedSCAl: Leveraging Server and Client Alignment for Unsupervised Federated Source-Free Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4108-4117} }
Meta-YOLO: Metadata-Guided Real-Time Object Detector in Aerial Imagery: Deukryeol Yoon,

Seonghak Kim,

Young Hwa Sung,

Jinho Jung; [pdf] [supp]
[bibtex]
@InProceedings{Yoon_2026_WACV, author = {Yoon, Deukryeol and Kim, Seonghak and Sung, Young Hwa and Jung, Jinho}, title = {Meta-YOLO: Metadata-Guided Real-Time Object Detector in Aerial Imagery}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7975-7984} }
SAIL: Self-supervised Learning of Lighting-Invariant Representations from Real Images with Latent Diffusion: Hala Djeghim,

Céline Loscos,

Désiré Sidibé; [pdf] [supp]
[bibtex]
@InProceedings{Djeghim_2026_WACV, author = {Djeghim, Hala and Loscos, C\'eline and Sidib\'e, D\'esir\'e}, title = {SAIL: Self-supervised Learning of Lighting-Invariant Representations from Real Images with Latent Diffusion}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3223-3232} }
Zero-Shot Video Deraining with Video Diffusion Models: Tuomas Varanka,

Juan Luis Gonzalez,

Hyeongwoo Kim,

Pablo Garrido,

Xu Yao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Varanka_2026_WACV, author = {Varanka, Tuomas and Gonzalez, Juan Luis and Kim, Hyeongwoo and Garrido, Pablo and Yao, Xu}, title = {Zero-Shot Video Deraining with Video Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {677-687} }
Generalized Category Discovery for LiDAR Semantic Segmentation: Minseok Kim,

Jiyong Boo,

Kuk-Jin Yoon; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2026_WACV, author = {Kim, Minseok and Boo, Jiyong and Yoon, Kuk-Jin}, title = {Generalized Category Discovery for LiDAR Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8416-8426} }
GrowTAS: Progressive Expansion from Small to Large Subnets for Efficient ViT Architecture Search: Hyunju Lee,

Youngmin Oh,

Jeimin Jeon,

Donghyeon Baek,

Bumsub Ham; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2026_WACV, author = {Lee, Hyunju and Oh, Youngmin and Jeon, Jeimin and Baek, Donghyeon and Ham, Bumsub}, title = {GrowTAS: Progressive Expansion from Small to Large Subnets for Efficient ViT Architecture Search}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5047-5056} }
NeuroBridge: Few-Shot Cross-Modal Neuron Re-identification via Dual-Channel Deep Metric Learning: Wenwei Li,

Mingwei Liao,

Lingyi Cai,

Anan Li; [pdf] [supp]
[bibtex]
@InProceedings{Li_2026_WACV, author = {Li, Wenwei and Liao, Mingwei and Cai, Lingyi and Li, Anan}, title = {NeuroBridge: Few-Shot Cross-Modal Neuron Re-identification via Dual-Channel Deep Metric Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8670-8679} }
IPTQ-ViT: Post-Training Quantization of Non-linear Functions for Integer-only Vision Transformers: Gihwan Kim,

Jemin Lee,

Hyungshin Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2026_WACV, author = {Kim, Gihwan and Lee, Jemin and Kim, Hyungshin}, title = {IPTQ-ViT: Post-Training Quantization of Non-linear Functions for Integer-only Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7366-7375} }
DynaGSLAM: Real-Time Gaussian-Splatting SLAM for Online Rendering, Tracking, Motion Predictions of Moving Objects in Dynamic Scenes: Runfa Blark Li,

Mahdi Shaghaghi,

Keito Suzuki,

Xinshuang Liu,

Varun Moparthi,

Bang Du,

Walker Curtis,

Martin Renschler,

Ki Myung Brian Lee,

Nikolay Atanasov,

Truong Nguyen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2026_WACV, author = {Li, Runfa Blark and Shaghaghi, Mahdi and Suzuki, Keito and Liu, Xinshuang and Moparthi, Varun and Du, Bang and Curtis, Walker and Renschler, Martin and Lee, Ki Myung Brian and Atanasov, Nikolay and Nguyen, Truong}, title = {DynaGSLAM: Real-Time Gaussian-Splatting SLAM for Online Rendering, Tracking, Motion Predictions of Moving Objects in Dynamic Scenes}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2434-2444} }
Denoise, Divide, Distill, and Predict (D3P): Towards Forecasting Long-horizon Real-world Anomaly from Normalcy: Quentin Mérilleau,

Snehashis Majhi,

Antitza Dantcheva,

Quan Kong,

Lorenzo Garattoni,

Gianpiero Francesca,

Francois Bremond; [pdf]
[bibtex]
@InProceedings{Merilleau_2026_WACV, author = {M\'erilleau, Quentin and Majhi, Snehashis and Dantcheva, Antitza and Kong, Quan and Garattoni, Lorenzo and Francesca, Gianpiero and Bremond, Francois}, title = {Denoise, Divide, Distill, and Predict (D3P): Towards Forecasting Long-horizon Real-world Anomaly from Normalcy}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6246-6255} }
Zero-Shot Domain Generalisation via Prompt-Driven Feature Refinement: Tingrui Qiao,

Di Zhao,

Caroline Walker,

Chris Cunningham,

Yun Sing Koh; [pdf]
[bibtex]
@InProceedings{Qiao_2026_WACV, author = {Qiao, Tingrui and Zhao, Di and Walker, Caroline and Cunningham, Chris and Koh, Yun Sing}, title = {Zero-Shot Domain Generalisation via Prompt-Driven Feature Refinement}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6184-6193} }
Generalizing Sports Feedback Generation by Watching Competitions and Reading Books: A Rock Climbing Case Study: Arushi Rai,

Adriana Kovashka; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Rai_2026_WACV, author = {Rai, Arushi and Kovashka, Adriana}, title = {Generalizing Sports Feedback Generation by Watching Competitions and Reading Books: A Rock Climbing Case Study}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8136-8145} }
ChameleonTuner: Automatic ISP Color Tuning in Subjective Scenarios: Zijie Tan,

Yuxin Yue,

Bahador Rashidi; [pdf]
[bibtex]
@InProceedings{Tan_2026_WACV, author = {Tan, Zijie and Yue, Yuxin and Rashidi, Bahador}, title = {ChameleonTuner: Automatic ISP Color Tuning in Subjective Scenarios}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {297-307} }
ControlVP: Interactive Geometric Refinement of AI-Generated Images with Consistent Vanishing Points: Ryota Okumura,

Kaede Shiohara,

Toshihiko Yamasaki; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Okumura_2026_WACV, author = {Okumura, Ryota and Shiohara, Kaede and Yamasaki, Toshihiko}, title = {ControlVP: Interactive Geometric Refinement of AI-Generated Images with Consistent Vanishing Points}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5744-5753} }
UnderWater SLAM with Laser-light sectioning method using ST-GAT: Heyang Gao,

Kazuto Ichimaru,

Takafumi Iwaguchi,

Hiroshi Kawasaki; [pdf] [supp]
[bibtex]
@InProceedings{Gao_2026_WACV, author = {Gao, Heyang and Ichimaru, Kazuto and Iwaguchi, Takafumi and Kawasaki, Hiroshi}, title = {UnderWater SLAM with Laser-light sectioning method using ST-GAT}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {88-96} }
Non-Contact Blood Pressure Estimation from Face Videos via Physiology-Aware Contrastive Learning: JaeHyuk Son,

Young-Seok Choi; [pdf]
[bibtex]
@InProceedings{Son_2026_WACV, author = {Son, JaeHyuk and Choi, Young-Seok}, title = {Non-Contact Blood Pressure Estimation from Face Videos via Physiology-Aware Contrastive Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2414-2423} }
Shift-Equivariant Complex-Valued Convolutional Neural Networks: Quentin Gabot,

Teck-Yian Lim,

Jeremy Fix,

Joana Frontera-Pons,

Chengfang Ren,

Jean-Philippe Ovarlez; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gabot_2026_WACV, author = {Gabot, Quentin and Lim, Teck-Yian and Fix, Jeremy and Frontera-Pons, Joana and Ren, Chengfang and Ovarlez, Jean-Philippe}, title = {Shift-Equivariant Complex-Valued Convolutional Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2575-2584} }
HiGlassRM: Learning to Remove High-prescription Glasses via Synthetic Dataset Generation: Sebin Lee,

Heewon Kim; [pdf] [supp]
[bibtex]
@InProceedings{Lee_2026_WACV, author = {Lee, Sebin and Kim, Heewon}, title = {HiGlassRM: Learning to Remove High-prescription Glasses via Synthetic Dataset Generation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4577-4586} }
Neural Geometry Image-Based Representations with Optimal Transport (OT): Xiang Gao,

Yuanpeng Liu,

Jiazhi Li,

Xinmu Wang,

Minghao Guo,

Yu Guo,

Xiyun Song,

Heather Yu,

Zhiqiang Lao,

Xianfeng David Gu; [pdf] [arXiv]
[bibtex]
@InProceedings{Gao_2026_WACV, author = {Gao, Xiang and Liu, Yuanpeng and Li, Jiazhi and Wang, Xinmu and Guo, Minghao and Guo, Yu and Song, Xiyun and Yu, Heather and Lao, Zhiqiang and Gu, Xianfeng David}, title = {Neural Geometry Image-Based Representations with Optimal Transport (OT)}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6676-6686} }
Multimodal Adversarial Defense for Vision-Language Models by Leveraging One-To-Many Relationships: Futa Waseda,

Antonio Tejero-de-Pablos,

Isao Echizen; [pdf] [supp]
[bibtex]
@InProceedings{Waseda_2026_WACV, author = {Waseda, Futa and Tejero-de-Pablos, Antonio and Echizen, Isao}, title = {Multimodal Adversarial Defense for Vision-Language Models by Leveraging One-To-Many Relationships}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6968-6977} }
FujiView: Multimodal Late-Fusion for Predicting Scenic Visibility: Bryceton Bible,

Nehal Hasnaeen,

Hairong Qi; [pdf]
[bibtex]
@InProceedings{Bible_2026_WACV, author = {Bible, Bryceton and Hasnaeen, Nehal and Qi, Hairong}, title = {FujiView: Multimodal Late-Fusion for Predicting Scenic Visibility}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5653-5661} }
Sketch3R: Rapid and Realistic 3D VR Sketch Creation to Shape Retrieval: Mritunjoy Halder,

Shivam Ashok Shukla,

Lokender Tiwari,

Raghav Mittal,

Brojeshwar Bhowmick; [pdf] [supp]
[bibtex]
@InProceedings{Halder_2026_WACV, author = {Halder, Mritunjoy and Shukla, Shivam Ashok and Tiwari, Lokender and Mittal, Raghav and Bhowmick, Brojeshwar}, title = {Sketch3R: Rapid and Realistic 3D VR Sketch Creation to Shape Retrieval}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8680-8689} }
MapleGrasp: Mask-guided Feature Pooling for Language-driven Efficient Robotic Grasping: Vineet Bhat,

Naman Patel,

Prashanth Krishnamurthy,

Ramesh Karri,

Farshad Khorrami; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bhat_2026_WACV, author = {Bhat, Vineet and Patel, Naman and Krishnamurthy, Prashanth and Karri, Ramesh and Khorrami, Farshad}, title = {MapleGrasp: Mask-guided Feature Pooling for Language-driven Efficient Robotic Grasping}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7554-7564} }
Explaining the Unseen: Multimodal Vision-Language Reasoning for Situational Awareness in Underground Mining Disasters: Mizanur Rahman Jewel,

Mohamed Elmahallawy,

Sanjay Madria,

Samuel Frimpong; [pdf] [arXiv]
[bibtex]
@InProceedings{Jewel_2026_WACV, author = {Jewel, Mizanur Rahman and Elmahallawy, Mohamed and Madria, Sanjay and Frimpong, Samuel}, title = {Explaining the Unseen: Multimodal Vision-Language Reasoning for Situational Awareness in Underground Mining Disasters}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1324-1333} }
ReBrain: Brain MRI Reconstruction from Sparse CT Slice via Retrieval-Augmented Diffusion: Junming Liu,

Yifei Sun,

Weihua Cheng,

Yujin Kang,

Yirong Chen,

Ding Wang,

Guosun Zeng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2026_WACV, author = {Liu, Junming and Sun, Yifei and Cheng, Weihua and Kang, Yujin and Chen, Yirong and Wang, Ding and Zeng, Guosun}, title = {ReBrain: Brain MRI Reconstruction from Sparse CT Slice via Retrieval-Augmented Diffusion}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4004-4014} }
QUOTA: Quantifying Objects with Text-to-Image Models for Any Domain: Wenfang Sun,

Yingjun Du,

Gaowen Liu,

Yefeng Zheng,

Cees G. M. Snoek; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sun_2026_WACV, author = {Sun, Wenfang and Du, Yingjun and Liu, Gaowen and Zheng, Yefeng and Snoek, Cees G. M.}, title = {QUOTA: Quantifying Objects with Text-to-Image Models for Any Domain}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6381-6390} }
Chain-of-Look Spatial Reasoning for Dense Surgical Instrument Counting: Rishikesh Bhyri,

Brian R Quaranto,

Junsong Yuan,

Peter C W Kim,

Nan Xi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bhyri_2026_WACV, author = {Bhyri, Rishikesh and Quaranto, Brian R and Yuan, Junsong and Kim, Peter C W and Xi, Nan}, title = {Chain-of-Look Spatial Reasoning for Dense Surgical Instrument Counting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8521-8530} }
Towards Fine-Grained Adaptation of CLIP via a Self-Trained Alignment Score: Eman Ali,

Sathira Silva,

Chetan Arora,

Muhammad Haris Khan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ali_2026_WACV, author = {Ali, Eman and Silva, Sathira and Arora, Chetan and Khan, Muhammad Haris}, title = {Towards Fine-Grained Adaptation of CLIP via a Self-Trained Alignment Score}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5875-5885} }
Zero-Shot Coreset Selection via Iterative Subspace Sampling: Brent A. Griffin,

Jacob Marks,

Jason J. Corso; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Griffin_2026_WACV, author = {Griffin, Brent A. and Marks, Jacob and Corso, Jason J.}, title = {Zero-Shot Coreset Selection via Iterative Subspace Sampling}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2114-2124} }
Mobile-Oriented Video Diffusion: Enabling Text-to-Video Generation on Mobile Devices Without Retraining, Compression, or Pruning: Bosung Kim,

Kyuhwan Lee,

Isu Jeong,

Jungmin Cheon,

Yeojin Lee,

Seulki Lee; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2026_WACV, author = {Kim, Bosung and Lee, Kyuhwan and Jeong, Isu and Cheon, Jungmin and Lee, Yeojin and Lee, Seulki}, title = {Mobile-Oriented Video Diffusion: Enabling Text-to-Video Generation on Mobile Devices Without Retraining, Compression, or Pruning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3961-3971} }
Efficient Vision Transformers via Token Merging with Head-wise Attention Correction: Yuki Ichikawa,

Masato Motomura,

Thiem Van Chu,

Daichi Fujiki; [pdf] [supp]
[bibtex]
@InProceedings{Ichikawa_2026_WACV, author = {Ichikawa, Yuki and Motomura, Masato and Van Chu, Thiem and Fujiki, Daichi}, title = {Efficient Vision Transformers via Token Merging with Head-wise Attention Correction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3908-3917} }
GFT-GCN: Privacy-Preserving 3D Face Mesh Recognition with Spectral Diffusion: Hichem Felouat,

Hanrui Wang,

Isao Echizen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Felouat_2026_WACV, author = {Felouat, Hichem and Wang, Hanrui and Echizen, Isao}, title = {GFT-GCN: Privacy-Preserving 3D Face Mesh Recognition with Spectral Diffusion}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6236-6245} }
Disentangle and Regularize: Sign Language Production with Articulator-Based Disentanglement and Channel-Aware Regularization: Sümeyye Meryem Taşyürek,

Tuğçe Kızıltepe,

Hacer Yalim Keles; [pdf] [supp]
[bibtex]
@InProceedings{Tasyurek_2026_WACV, author = {Ta\c{s}y\"urek, S\"umeyye Meryem and K{\i}z{\i}ltepe, Tu\u{g}\c{c}e and Keles, Hacer Yalim}, title = {Disentangle and Regularize: Sign Language Production with Articulator-Based Disentanglement and Channel-Aware Regularization}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8458-8467} }
Test-Time Adaptation through Semantically-guided Feature Decomposition for Few-shot Chest X-ray Diagnosis: Jayant Mahawar,

Angshuman Paul; [pdf] [supp]
[bibtex]
@InProceedings{Mahawar_2026_WACV, author = {Mahawar, Jayant and Paul, Angshuman}, title = {Test-Time Adaptation through Semantically-guided Feature Decomposition for Few-shot Chest X-ray Diagnosis}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2445-2454} }
Self-Supervised Compression and Artifact Correction for Streaming Underwater Imaging Sonar: Rongsheng Qian,

Chi Xu,

Xiaoqiang Ma,

Hao Fang,

Yili Jin,

William I. Atlas,

Jiangchuan Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Qian_2026_WACV, author = {Qian, Rongsheng and Xu, Chi and Ma, Xiaoqiang and Fang, Hao and Jin, Yili and Atlas, William I. and Liu, Jiangchuan}, title = {Self-Supervised Compression and Artifact Correction for Streaming Underwater Imaging Sonar}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4201-4211} }
PointNet4D: A Lightweight 4D Point Cloud Video Backbone for Online and Offline Perception in Robotic Applications: Yunze Liu,

Zifan Wang,

Peiran Wu,

Jiayang Ao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2026_WACV, author = {Liu, Yunze and Wang, Zifan and Wu, Peiran and Ao, Jiayang}, title = {PointNet4D: A Lightweight 4D Point Cloud Video Backbone for Online and Offline Perception in Robotic Applications}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3203-3212} }
MIST: Multilingual Incidental Dataset for Scene Text Detection: Saumya Mundra,

Ajoy Mondal,

C.V. Jawahar; [pdf] [supp]
[bibtex]
@InProceedings{Mundra_2026_WACV, author = {Mundra, Saumya and Mondal, Ajoy and Jawahar, C.V.}, title = {MIST: Multilingual Incidental Dataset for Scene Text Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7658-7667} }
Unsupervised Memorability Modeling from Tip-of-the-Tongue Retrieval Queries: Sree Bhattacharyya,

Yaman K. Singla,

Sudhir Yarram,

Somesh Singh,

Harini SI,

James Z. Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bhattacharyya_2026_WACV, author = {Bhattacharyya, Sree and Singla, Yaman K. and Yarram, Sudhir and Singh, Somesh and SI, Harini and Wang, James Z.}, title = {Unsupervised Memorability Modeling from Tip-of-the-Tongue Retrieval Queries}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4234-4241} }
VAST-ReID: A Low-Light Benchmark Dataset for Person Re-Identification with Visual and Attribute-Rich Semantic Tracking: Hammad Khan,

Rakesh Kumar Giri,

Kamalakar Vijay Thakare,

Heeseung Choi,

Hyungjoo Jung,

Debi Prosad Dogra,

Ig-Jae Kim; [pdf] [supp]
[bibtex]
@InProceedings{Khan_2026_WACV, author = {Khan, Hammad and Giri, Rakesh Kumar and Thakare, Kamalakar Vijay and Choi, Heeseung and Jung, Hyungjoo and Dogra, Debi Prosad and Kim, Ig-Jae}, title = {VAST-ReID: A Low-Light Benchmark Dataset for Person Re-Identification with Visual and Attribute-Rich Semantic Tracking}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5833-5841} }
Robust Scene Coordinate Regression via Geometrically-Consistent Global Descriptors: Son Tung Nguyen,

Alejandro Fontan,

Michael Milford,

Tobias Fischer; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nguyen_2026_WACV, author = {Nguyen, Son Tung and Fontan, Alejandro and Milford, Michael and Fischer, Tobias}, title = {Robust Scene Coordinate Regression via Geometrically-Consistent Global Descriptors}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8209-8219} }
PointSt3R: Point Tracking through 3D Ground Correspondence: Rhodri Guerrier,

Adam W. Harley,

Dima Damen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guerrier_2026_WACV, author = {Guerrier, Rhodri and Harley, Adam W. and Damen, Dima}, title = {PointSt3R: Point Tracking through 3D Ground Correspondence}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7430-7439} }
NoHumansRequired: Autonomous High-Quality Image Editing Triplet Mining: Maksim Kuprashevich,

Grigorii Alekseenko,

Irina Tolstykh,

Georgii Fedorov,

Bulat Suleimanov,

Vladimir Dokholyan,

Aleksandr Gordeev; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kuprashevich_2026_WACV, author = {Kuprashevich, Maksim and Alekseenko, Grigorii and Tolstykh, Irina and Fedorov, Georgii and Suleimanov, Bulat and Dokholyan, Vladimir and Gordeev, Aleksandr}, title = {NoHumansRequired: Autonomous High-Quality Image Editing Triplet Mining}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6059-6068} }
DuPLUS: Dual-Prompt Vision-Language Model for Universal Medical Image Segmentation and Prognosis: Numan Saeed,

Tausifa Jan Saleem,

Fadillah Maani,

Muhammad Ridzuan,

Hu Wang,

Mohammad Yaqub; [pdf] [supp]
[bibtex]
@InProceedings{Saeed_2026_WACV, author = {Saeed, Numan and Saleem, Tausifa Jan and Maani, Fadillah and Ridzuan, Muhammad and Wang, Hu and Yaqub, Mohammad}, title = {DuPLUS: Dual-Prompt Vision-Language Model for Universal Medical Image Segmentation and Prognosis}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8386-8395} }
Relevance-aware Multi-context Contrastive Decoding for Retrieval-augmented Visual Question Answering: Jongha Kim,

Byungoh Ko,

Jeehye Na,

Jinsung Yoon,

Hyunwoo J. Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2026_WACV, author = {Kim, Jongha and Ko, Byungoh and Na, Jeehye and Yoon, Jinsung and Kim, Hyunwoo J.}, title = {Relevance-aware Multi-context Contrastive Decoding for Retrieval-augmented Visual Question Answering}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8596-8605} }
GenHSI: Controllable Generation of Human-Scene Interaction Videos: Zekun Li,

Rui Zhou,

Rahul Sajnani,

Xiaoyan Cong,

Daniel Ritchie,

Srinath Sridhar; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2026_WACV, author = {Li, Zekun and Zhou, Rui and Sajnani, Rahul and Cong, Xiaoyan and Ritchie, Daniel and Sridhar, Srinath}, title = {GenHSI: Controllable Generation of Human-Scene Interaction Videos}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {138-149} }
Unified Video Anomaly Detection Model for Detecting Different Anomaly Types: Kijung Lee,

Youngwan Jo,

Sunghyun Ahn,

Sanghyun Park; [pdf] [supp]
[bibtex]
@InProceedings{Lee_2026_WACV, author = {Lee, Kijung and Jo, Youngwan and Ahn, Sunghyun and Park, Sanghyun}, title = {Unified Video Anomaly Detection Model for Detecting Different Anomaly Types}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {784-794} }
Image-Guided Semantic Pseudo-LiDAR Point Generation for 3D Object Detection: Minseung Lee,

Seokha Moon,

Seung Joon Lee,

Reza Mahjourian,

Jinkyu Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2026_WACV, author = {Lee, Minseung and Moon, Seokha and Lee, Seung Joon and Mahjourian, Reza and Kim, Jinkyu}, title = {Image-Guided Semantic Pseudo-LiDAR Point Generation for 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7137-7147} }
PromptGAR: Flexible Promptive Group Activity Recognition: Zhangyu Jin,

Andrew Feng,

Ankur Chemburkar,

Celso M. De Melo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jin_2026_WACV, author = {Jin, Zhangyu and Feng, Andrew and Chemburkar, Ankur and De Melo, Celso M.}, title = {PromptGAR: Flexible Promptive Group Activity Recognition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4461-4471} }
RPT-SR: Regional Prior attention Transformer for infrared image Super-Resolution: Youngwan Jin,

Incheol Park,

Yagiz Nalcakan,

Hyeongjin Ju,

Sanghyeop Yeo,

Shiho Kim; [pdf] [arXiv]
[bibtex]
@InProceedings{Jin_2026_WACV, author = {Jin, Youngwan and Park, Incheol and Nalcakan, Yagiz and Ju, Hyeongjin and Yeo, Sanghyeop and Kim, Shiho}, title = {RPT-SR: Regional Prior attention Transformer for infrared image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5184-5193} }
Intraoperative 2D/3D Registration via Spherical Similarity Learning and Differentiable Levenberg-Marquardt Optimization: Minheng Chen,

Youyong Kong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2026_WACV, author = {Chen, Minheng and Kong, Youyong}, title = {Intraoperative 2D/3D Registration via Spherical Similarity Learning and Differentiable Levenberg-Marquardt Optimization}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7239-7249} }
M-ErasureBench: A Comprehensive Multimodal Evaluation Benchmark for Concept Erasure in Diffusion Models: Ju-Hsuan Weng,

Jia-Wei Liao,

Cheng-Fu Chou,

Jun-Cheng Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Weng_2026_WACV, author = {Weng, Ju-Hsuan and Liao, Jia-Wei and Chou, Cheng-Fu and Chen, Jun-Cheng}, title = {M-ErasureBench: A Comprehensive Multimodal Evaluation Benchmark for Concept Erasure in Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {527-536} }
Bridging the Domain Gap in Small Multimodal Models: A Dual-level Alignment Perspective: Aveen Dayal,

Peketi Divya,

Nidhi Tiwari,

Linga Reddy Cenkeramaddi,

C Krishna Mohan,

Abhinav Kumar; [pdf] [supp]
[bibtex]
@InProceedings{Dayal_2026_WACV, author = {Dayal, Aveen and Divya, Peketi and Tiwari, Nidhi and Cenkeramaddi, Linga Reddy and Mohan, C Krishna and Kumar, Abhinav}, title = {Bridging the Domain Gap in Small Multimodal Models: A Dual-level Alignment Perspective}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8262-8271} }
Leveraging Pretrained Representations for Cross-Modal Point Cloud Completion: Kshitij Kale,

Hrishikesh U,

V sreenidhe,

Shylaja S S; [pdf] [supp]
[bibtex]
@InProceedings{Kale_2026_WACV, author = {Kale, Kshitij and U, Hrishikesh and sreenidhe, V and S, Shylaja S}, title = {Leveraging Pretrained Representations for Cross-Modal Point Cloud Completion}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {97-105} }
Gated Temporal Fusion Transformers for Robust Multi-Object Tracking: Jinho Kim,

Kuk-Jin Yoon; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2026_WACV, author = {Kim, Jinho and Yoon, Kuk-Jin}, title = {Gated Temporal Fusion Transformers for Robust Multi-Object Tracking}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4525-4534} }
Moire Zero: An Efficient and High-Performance Neural Architecture for Moire Removal: Seungryong Lee,

Woojeong Baek,

Younghyun Kim,

Eunwoo Kim,

Haru Moon,

Donggon Yoo,

Eunbyung Park; [pdf]
[bibtex]
@InProceedings{Lee_2026_WACV, author = {Lee, Seungryong and Baek, Woojeong and Kim, Younghyun and Kim, Eunwoo and Moon, Haru and Yoo, Donggon and Park, Eunbyung}, title = {Moire Zero: An Efficient and High-Performance Neural Architecture for Moire Removal}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2520-2530} }
DermEVAL: A Dermatologist-Reviewed Benchmark for Multimodal Large Language Models: Hongjin Zhao,

Weihao Li,

Zhenyue Qin,

Ge-Peng Ji,

Yang Liu,

Tom Gedeon,

Nick Barnes; [pdf]
[bibtex]
@InProceedings{Zhao_2026_WACV, author = {Zhao, Hongjin and Li, Weihao and Qin, Zhenyue and Ji, Ge-Peng and Liu, Yang and Gedeon, Tom and Barnes, Nick}, title = {DermEVAL: A Dermatologist-Reviewed Benchmark for Multimodal Large Language Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {927-937} }
GAITGen: Disentangled Motion-Pathology Impaired Gait Generative Model -- Bringing Motion Generation to the Clinical Domain: Vida Adeli,

Soroush Mehraban,

Majid Mirmehdi,

Alan Whone,

Benjamin Filtjens,

Amirhossein Dadashzadeh,

Alfonso Fasano,

Andrea Iaboni,

Babak Taati; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Adeli_2026_WACV, author = {Adeli, Vida and Mehraban, Soroush and Mirmehdi, Majid and Whone, Alan and Filtjens, Benjamin and Dadashzadeh, Amirhossein and Fasano, Alfonso and Iaboni, Andrea and Taati, Babak}, title = {GAITGen: Disentangled Motion-Pathology Impaired Gait Generative Model -- Bringing Motion Generation to the Clinical Domain}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3150-3161} }
Perceptually Guided 3DGS Streaming and Rendering for Mixed Reality: Yunxiang Zhang,

Sai Harsha Mupparaju,

Kenneth Chen,

Jenna Kang,

Xinyu Zhang,

Maito Omori,

Kazuyuki Arimatsu,

Qi Sun; [pdf]
[bibtex]
@InProceedings{Zhang_2026_WACV, author = {Zhang, Yunxiang and Mupparaju, Sai Harsha and Chen, Kenneth and Kang, Jenna and Zhang, Xinyu and Omori, Maito and Arimatsu, Kazuyuki and Sun, Qi}, title = {Perceptually Guided 3DGS Streaming and Rendering for Mixed Reality}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4212-4222} }
RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph: Sameer Malik,

Ayush Singh,

Moyuru Yamada,

Dishank Aggarwal; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Malik_2026_WACV, author = {Malik, Sameer and Singh, Ayush and Yamada, Moyuru and Aggarwal, Dishank}, title = {RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2869-2878} }
Style-Friendly SNR Sampler for Style-Driven Generation: Jooyoung Choi,

Chaehun Shin,

Yeongtak Oh,

Heeseung Kim,

Jungbeom Lee,

Sungroh Yoon; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Choi_2026_WACV, author = {Choi, Jooyoung and Shin, Chaehun and Oh, Yeongtak and Kim, Heeseung and Lee, Jungbeom and Yoon, Sungroh}, title = {Style-Friendly SNR Sampler for Style-Driven Generation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5703-5713} }
Low-Rank Expert Merging for Multi-Source Domain Adaptation in Person Re-Identification: Taha Mustapha Nehdi,

Nairouz Mrabah,

Atif Belal,

Marco Pedersoli,

Eric Granger; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nehdi_2026_WACV, author = {Nehdi, Taha Mustapha and Mrabah, Nairouz and Belal, Atif and Pedersoli, Marco and Granger, Eric}, title = {Low-Rank Expert Merging for Multi-Source Domain Adaptation in Person Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1809-1819} }
ChartQA-X: Generating Explanations for Visual Chart Reasoning: Shamanthak Hegde,

Pooyan Fazli,

Hasti Seifi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hegde_2026_WACV, author = {Hegde, Shamanthak and Fazli, Pooyan and Seifi, Hasti}, title = {ChartQA-X: Generating Explanations for Visual Chart Reasoning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6453-6463} }
BOP-Distrib: Revisiting 6D Pose Estimation Benchmarks for Better Evaluation under Visual Ambiguities: Boris Meden,

Asma Brazi,

Fabrice Mayran de Chamisso,

Steve Bourgeois,

Vincent Lepetit; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Meden_2026_WACV, author = {Meden, Boris and Brazi, Asma and de Chamisso, Fabrice Mayran and Bourgeois, Steve and Lepetit, Vincent}, title = {BOP-Distrib: Revisiting 6D Pose Estimation Benchmarks for Better Evaluation under Visual Ambiguities}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1575-1585} }
SPOC: Spatially-Progressing Object State Change Segmentation in Video: Priyanka Mandikal,

Tushar Nagarajan,

Alex Stoken,

Zihui Xue,

Kristen Grauman; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mandikal_2026_WACV, author = {Mandikal, Priyanka and Nagarajan, Tushar and Stoken, Alex and Xue, Zihui and Grauman, Kristen}, title = {SPOC: Spatially-Progressing Object State Change Segmentation in Video}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3504-3513} }
RealDroneVision: Dataset and Architecture Advancements for Small-Object Drone Detection: Arun Kumar Sivapuram,

Pranav R T Peddinti,

Harish Puppala,

Komuravelli Prashanth,

Jaladi Sri Harsha,

Rama Krishna Sai Gorthi; [pdf] [supp]
[bibtex]
@InProceedings{Sivapuram_2026_WACV, author = {Sivapuram, Arun Kumar and Peddinti, Pranav R T and Puppala, Harish and Prashanth, Komuravelli and Harsha, Jaladi Sri and Gorthi, Rama Krishna Sai}, title = {RealDroneVision: Dataset and Architecture Advancements for Small-Object Drone Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6687-6695} }
brat: Aligned Multi-View Embeddings for Brain MRI Analysis: Maxime Kayser,

Maksim Gridnev,

Wanting Wang,

Max Bain,

Aneesh Rangnekar,

Avijit Chatterjee,

Aleksandr Petrov,

Harini Veeraraghavan,

Nathaniel C. Swinburne; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kayser_2026_WACV, author = {Kayser, Maxime and Gridnev, Maksim and Wang, Wanting and Bain, Max and Rangnekar, Aneesh and Chatterjee, Avijit and Petrov, Aleksandr and Veeraraghavan, Harini and Swinburne, Nathaniel C.}, title = {brat: Aligned Multi-View Embeddings for Brain MRI Analysis}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5864-5874} }
TalkingPose: Efficient Face and Gesture Animation with Feedback-guided Diffusion Model: Alireza Javanmardi,

Pragati Jaiswal,

Tewodros Amberbir Habtegebrial,

Christen Millerdurai,

Shaoxiang Wang,

Alain Pagani,

Didier Stricker; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Javanmardi_2026_WACV, author = {Javanmardi, Alireza and Jaiswal, Pragati and Habtegebrial, Tewodros Amberbir and Millerdurai, Christen and Wang, Shaoxiang and Pagani, Alain and Stricker, Didier}, title = {TalkingPose: Efficient Face and Gesture Animation with Feedback-guided Diffusion Model}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3098-3108} }
Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing: Saarthak Kapse,

Robin Betz,

Srinivasan Sivanandan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kapse_2026_WACV, author = {Kapse, Saarthak and Betz, Robin and Sivanandan, Srinivasan}, title = {Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2923-2933} }
A Dataset and Framework for Learning State-invariant Object Representations: Rohan Sarkar,

Avinash Kak; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sarkar_2026_WACV, author = {Sarkar, Rohan and Kak, Avinash}, title = {A Dataset and Framework for Learning State-invariant Object Representations}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4715-4723} }
SurfDist: Interpretable Three-Dimensional Instance Segmentation Using Curved Surface Patches: Jackson Borchardt,

Saul Kato; [pdf] [arXiv]
[bibtex]
@InProceedings{Borchardt_2026_WACV, author = {Borchardt, Jackson and Kato, Saul}, title = {SurfDist: Interpretable Three-Dimensional Instance Segmentation Using Curved Surface Patches}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5541-5549} }
Histogram Assisted Quality Aware Generative Model for Resolution Invariant NIR Image Colorization: Abhinav Attri,

Rajeev Ranjan Dwivedi,

Samiran Das,

Vinod Kumar Kurmi; [pdf] [arXiv]
[bibtex]
@InProceedings{Attri_2026_WACV, author = {Attri, Abhinav and Dwivedi, Rajeev Ranjan and Das, Samiran and Kurmi, Vinod Kumar}, title = {Histogram Assisted Quality Aware Generative Model for Resolution Invariant NIR Image Colorization}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6422-6431} }
DRWKV: Focusing on Object Edges for Low-Light Image Enhancement: Xuecheng Bai,

Yuxiang Wang,

Boyu Hu,

Qinyuan Jie,

Chuanzhi Xu,

Kechen Li,

Hongru Xiao,

Vera Chung; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bai_2026_WACV, author = {Bai, Xuecheng and Wang, Yuxiang and Hu, Boyu and Jie, Qinyuan and Xu, Chuanzhi and Li, Kechen and Xiao, Hongru and Chung, Vera}, title = {DRWKV: Focusing on Object Edges for Low-Light Image Enhancement}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1554-1564} }
Fetal and Neonatal Cortical Surface Reconstruction with Anatomical Normal-guidance and Perceptual Enhancements: Jiyang Lee,

Woori Bae,

U-Geun Ji,

Hanyeol Yang,

Jong-Min Lee; [pdf]
[bibtex]
@InProceedings{Lee_2026_WACV, author = {Lee, Jiyang and Bae, Woori and Ji, U-Geun and Yang, Hanyeol and Lee, Jong-Min}, title = {Fetal and Neonatal Cortical Surface Reconstruction with Anatomical Normal-guidance and Perceptual Enhancements}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7759-7768} }
Intra-Class Probabilistic Embeddings for Uncertainty Estimation in Vision-Language Models: Zhenxiang Lin,

Maryam Haghighat,

Will Browne,

Dimity Miller; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lin_2026_WACV, author = {Lin, Zhenxiang and Haghighat, Maryam and Browne, Will and Miller, Dimity}, title = {Intra-Class Probabilistic Embeddings for Uncertainty Estimation in Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2327-2337} }
ExDDV: A New Dataset for Explainable Deepfake Detection in Video: Vlad Hondru,

Eduard Hogea,

Darian Onchis,

Radu Tudor Ionescu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hondru_2026_WACV, author = {Hondru, Vlad and Hogea, Eduard and Onchis, Darian and Ionescu, Radu Tudor}, title = {ExDDV: A New Dataset for Explainable Deepfake Detection in Video}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4273-4284} }
TriaGS: Differentiable Triangulation-Guided Geometric Consistency for 3D Gaussian Splatting: Quan Tran,

Tuan Dang; [pdf] [arXiv]
[bibtex]
@InProceedings{Tran_2026_WACV, author = {Tran, Quan and Dang, Tuan}, title = {TriaGS: Differentiable Triangulation-Guided Geometric Consistency for 3D Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8396-8405} }
ART: Actor-Related Tubelet for Detecting Complex-shaped Action Tubes: Jiaojiao Zhao; [pdf] [supp]
[bibtex]
@InProceedings{Zhao_2026_WACV, author = {Zhao, Jiaojiao}, title = {ART: Actor-Related Tubelet for Detecting Complex-shaped Action Tubes}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {308-317} }
Line Art Colorization with Offset Prior-based Diffusion Model: Xuan Zhu,

Miao Cao,

Fang-Lue Zhang,

Yu-Kun Lai,

Paul L Rosin; [pdf] [supp]
[bibtex]
@InProceedings{Zhu_2026_WACV, author = {Zhu, Xuan and Cao, Miao and Zhang, Fang-Lue and Lai, Yu-Kun and Rosin, Paul L}, title = {Line Art Colorization with Offset Prior-based Diffusion Model}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5570-5580} }
F-ViTA: Foundation Model Guided Visible to Infrared Translation: Jay Nitin Paranjape,

Celso M De Melo,

Vishal M. Patel; [pdf] [supp]
[bibtex]
@InProceedings{Paranjape_2026_WACV, author = {Paranjape, Jay Nitin and De Melo, Celso M and Patel, Vishal M.}, title = {F-ViTA: Foundation Model Guided Visible to Infrared Translation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5633-5642} }
DATTA: Domain-Adversarial Test-Time Adaptation for Cross-Domain WiFi-Based Human Activity Recognition: Julian Strohmayer,

Rafael Sterzinger,

Matthias Wödlinger,

Martin Kampel; [pdf] [supp]
[bibtex]
@InProceedings{Strohmayer_2026_WACV, author = {Strohmayer, Julian and Sterzinger, Rafael and W\"odlinger, Matthias and Kampel, Martin}, title = {DATTA: Domain-Adversarial Test-Time Adaptation for Cross-Domain WiFi-Based Human Activity Recognition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3421-3430} }
PALMS+: Modular Image-Based Floor Plan Localization Leveraging Depth Foundation Model: Yunqian Cheng,

Benjamin Princen,

Roberto Manduchi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cheng_2026_WACV, author = {Cheng, Yunqian and Princen, Benjamin and Manduchi, Roberto}, title = {PALMS+: Modular Image-Based Floor Plan Localization Leveraging Depth Foundation Model}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7084-7093} }
Ego-EXTRA: video-language Egocentric Dataset for EXpert-TRAinee assistance: Francesco Ragusa,

Michele Mazzamuto,

Rosario Forte,

Irene D'Ambra,

James Fort,

Jakob Engel,

Antonino Furnari,

Giovanni Maria Farinella; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ragusa_2026_WACV, author = {Ragusa, Francesco and Mazzamuto, Michele and Forte, Rosario and D'Ambra, Irene and Fort, James and Engel, Jakob and Furnari, Antonino and Farinella, Giovanni Maria}, title = {Ego-EXTRA: video-language Egocentric Dataset for EXpert-TRAinee assistance}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4438-4450} }
Cluster-Guided Adversarial Perturbations for Robust Contrastive Learning: Seongyun Seo,

Sungmin Han,

Jeonghyun Lee,

Sangkyun Lee; [pdf] [supp]
[bibtex]
@InProceedings{Seo_2026_WACV, author = {Seo, Seongyun and Han, Sungmin and Lee, Jeonghyun and Lee, Sangkyun}, title = {Cluster-Guided Adversarial Perturbations for Robust Contrastive Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {350-359} }
FSP-DETR: Few-Shot Prototypical Parasitic Ova Detection: Shubham Trehan,

Udhav Ramachandran,

Akash Rao,

Ruth Scimeca,

Sathyanarayanan N. Aakur; [pdf] [arXiv]
[bibtex]
@InProceedings{Trehan_2026_WACV, author = {Trehan, Shubham and Ramachandran, Udhav and Rao, Akash and Scimeca, Ruth and Aakur, Sathyanarayanan N.}, title = {FSP-DETR: Few-Shot Prototypical Parasitic Ova Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5342-5351} }
IDEAL-M3D: Instance Diversity-Enriched Active Learning for Monocular 3D Detection: Johannes Meier,

Florian Günther,

Riccardo Marin,

Oussema Dhaouadi,

Jacques Kaiser,

Daniel Cremers; [pdf] [supp]
[bibtex]
@InProceedings{Meier_2026_WACV, author = {Meier, Johannes and G\"unther, Florian and Marin, Riccardo and Dhaouadi, Oussema and Kaiser, Jacques and Cremers, Daniel}, title = {IDEAL-M3D: Instance Diversity-Enriched Active Learning for Monocular 3D Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {181-191} }
RemEdit: Efficient Diffusion Editing with Riemannian Geometry: Eashan Adhikarla,

Brian D. Davison; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Adhikarla_2026_WACV, author = {Adhikarla, Eashan and Davison, Brian D.}, title = {RemEdit: Efficient Diffusion Editing with Riemannian Geometry}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5037-5046} }
VFace: A Training-Free Approach for Diffusion-Based Video Face Swapping: Sanoojan Baliah,

Yohan Abeysinghe,

Rusiru Thushara,

Khan Muhammad,

Abhinav Dhall,

Karthik Nandakumar,

Muhammad Haris Khan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Baliah_2026_WACV, author = {Baliah, Sanoojan and Abeysinghe, Yohan and Thushara, Rusiru and Muhammad, Khan and Dhall, Abhinav and Nandakumar, Karthik and Khan, Muhammad Haris}, title = {VFace: A Training-Free Approach for Diffusion-Based Video Face Swapping}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4315-4324} }
CaRS: A Causal Intervention Segmentation Framework and Benchmark Dataset for Autonomous Driving under Transitional Weather Conditions: Kondapally Madhavi,

K Naveen Kumar,

C Krishna Mohan,

Sobhan Babu; [pdf] [supp]
[bibtex]
@InProceedings{Madhavi_2026_WACV, author = {Madhavi, Kondapally and Kumar, K Naveen and Mohan, C Krishna and Babu, Sobhan}, title = {CaRS: A Causal Intervention Segmentation Framework and Benchmark Dataset for Autonomous Driving under Transitional Weather Conditions}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4046-4056} }
FreeCond: Free Lunch in the Input Conditions of Text-Guided Inpainting: Teng-Fang Hsiao,

Bo-Kai Ruan,

Sung-Lin Tsai,

Yi-Lun Wu,

Hong-Han Shuai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hsiao_2026_WACV, author = {Hsiao, Teng-Fang and Ruan, Bo-Kai and Tsai, Sung-Lin and Wu, Yi-Lun and Shuai, Hong-Han}, title = {FreeCond: Free Lunch in the Input Conditions of Text-Guided Inpainting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5498-5508} }
Advancing Player Identification and Tracking with Global ID Fusion (GIF): Karol Wojtulewicz,

Minxing Liu,

Niklas Carlsson; [pdf] [supp]
[bibtex]
@InProceedings{Wojtulewicz_2026_WACV, author = {Wojtulewicz, Karol and Liu, Minxing and Carlsson, Niklas}, title = {Advancing Player Identification and Tracking with Global ID Fusion (GIF)}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7269-7280} }
VRAgent: Self-Refining Agent for Zero-Shot Multimodal Video Retrieval: Ketul Shah,

Pankaj Nathani,

Rama Chellappa,

Fabian Caba Heilbron; [pdf] [supp]
[bibtex]
@InProceedings{Shah_2026_WACV, author = {Shah, Ketul and Nathani, Pankaj and Chellappa, Rama and Heilbron, Fabian Caba}, title = {VRAgent: Self-Refining Agent for Zero-Shot Multimodal Video Retrieval}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8157-8167} }
TaxonRL: Reinforcement Learning with Intermediate Rewards for Interpretable Fine-Grained Visual Reasoning: Maximilian von Klinski,

Maximilian Schall; [pdf]
[bibtex]
@InProceedings{von_Klinski_2026_WACV, author = {von Klinski, Maximilian and Schall, Maximilian}, title = {TaxonRL: Reinforcement Learning with Intermediate Rewards for Interpretable Fine-Grained Visual Reasoning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2485-2498} }
Revisiting Retentive Networks for Fast Range-View 3D LiDAR Semantic Segmentation: Simone Mosco,

Daniel Fusaro,

Wanmeng Li,

Alberto Pretto; [pdf] [supp]
[bibtex]
@InProceedings{Mosco_2026_WACV, author = {Mosco, Simone and Fusaro, Daniel and Li, Wanmeng and Pretto, Alberto}, title = {Revisiting Retentive Networks for Fast Range-View 3D LiDAR Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2499-2509} }
Alignment and Distillation: A Robust Framework for Multimodal Domain Generalizable Human Action Recognition: Hyeonbin Ji,

Juyeob Lee,

Eunil Park; [pdf]
[bibtex]
@InProceedings{Ji_2026_WACV, author = {Ji, Hyeonbin and Lee, Juyeob and Park, Eunil}, title = {Alignment and Distillation: A Robust Framework for Multimodal Domain Generalizable Human Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6913-6924} }
GraspDiffusion: Synthesizing Realistic Whole-body Hand-Object Interaction: Patrick Kwon,

Chen Chen,

Hanbyul Joo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kwon_2026_WACV, author = {Kwon, Patrick and Chen, Chen and Joo, Hanbyul}, title = {GraspDiffusion: Synthesizing Realistic Whole-body Hand-Object Interaction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2392-2403} }
Understanding Human-Like Biases in VLMs via Subjective Face Analytics: Chaitanya Roygaga,

Aparna Bharati; [pdf] [supp]
[bibtex]
@InProceedings{Roygaga_2026_WACV, author = {Roygaga, Chaitanya and Bharati, Aparna}, title = {Understanding Human-Like Biases in VLMs via Subjective Face Analytics}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {514-526} }
Correcting and Quantifying Systematic Errors in 3D Box Annotations for Autonomous Driving: Alexandre Justo Miro,

Ludvig af Klinteberg,

Bogdan Timus,

Aron Asefaw,

Ajinkya Khoche,

Thomas Gustafsson,

Sina Sharif Mansouri,

Masoud Daneshtalab; [pdf] [arXiv]
[bibtex]
@InProceedings{Miro_2026_WACV, author = {Miro, Alexandre Justo and af Klinteberg, Ludvig and Timus, Bogdan and Asefaw, Aron and Khoche, Ajinkya and Gustafsson, Thomas and Mansouri, Sina Sharif and Daneshtalab, Masoud}, title = {Correcting and Quantifying Systematic Errors in 3D Box Annotations for Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6724-6732} }
CaFlow: Enhancing Long-Term Action Quality Assessment with Causal Counterfactual Flow: Ruisheng Han,

Kanglei Zhou,

Shuang Chen,

Amir Atapour-Abarghouei,

Hubert P. H. Shum; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Han_2026_WACV, author = {Han, Ruisheng and Zhou, Kanglei and Chen, Shuang and Atapour-Abarghouei, Amir and Shum, Hubert P. H.}, title = {CaFlow: Enhancing Long-Term Action Quality Assessment with Causal Counterfactual Flow}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8231-8241} }
Learning Beyond Labels: Self-Supervised Handwritten Text Recognition: Shree Mitra,

Ajoy Mondal,

C.V. Jawahar; [pdf] [supp]
[bibtex]
@InProceedings{Mitra_2026_WACV, author = {Mitra, Shree and Mondal, Ajoy and Jawahar, C.V.}, title = {Learning Beyond Labels: Self-Supervised Handwritten Text Recognition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6653-6663} }
A Woman with a Knife or A Knife with a Woman? Measuring Directional Bias Amplification in Image Captions: Rahul Nair,

Bhanu Tokas,

Hannah Kerner; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nair_2026_WACV, author = {Nair, Rahul and Tokas, Bhanu and Kerner, Hannah}, title = {A Woman with a Knife or A Knife with a Woman? Measuring Directional Bias Amplification in Image Captions}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {255-264} }
Vision-informed Semantic Text Alignment for Open-set Recognition in Remote Sensing: Siddhant Gole,

Akash Pal,

Ankit Jha,

Subhasis Chaudhuri,

Biplab Banerjee; [pdf] [supp]
[bibtex]
@InProceedings{Gole_2026_WACV, author = {Gole, Siddhant and Pal, Akash and Jha, Ankit and Chaudhuri, Subhasis and Banerjee, Biplab}, title = {Vision-informed Semantic Text Alignment for Open-set Recognition in Remote Sensing}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2828-2837} }
Guided Model Merging for Hybrid Data Learning: Leveraging Centralized Data to Refine Decentralized Models: Junyi Zhu,

Ruicong Yao,

Taha Ceritli,

Savas Ozkan,

Matthew B. Blaschko,

Eunchung Noh,

Jeongwon Min,

Cho Jung Min,

Mete Ozay; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2026_WACV, author = {Zhu, Junyi and Yao, Ruicong and Ceritli, Taha and Ozkan, Savas and Blaschko, Matthew B. and Noh, Eunchung and Min, Jeongwon and Min, Cho Jung and Ozay, Mete}, title = {Guided Model Merging for Hybrid Data Learning: Leveraging Centralized Data to Refine Decentralized Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3182-3192} }
EndoPBR: Photorealistic Synthetic Data for Surgical 3D Vision via Physically-based Rendering: John J. Han,

Jie Ying Wu; [pdf]
[bibtex]
@InProceedings{Han_2026_WACV, author = {Han, John J. and Wu, Jie Ying}, title = {EndoPBR: Photorealistic Synthetic Data for Surgical 3D Vision via Physically-based Rendering}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5601-5611} }
KMOPS: Keypoint-Driven Method for Multi-Object Pose and Metric Size Estimation from Stereo Images: Ying-Kun Wu,

Yi Shen,

Tzuhsuan Huang,

I-Sheng Fang,

Jun-Cheng Chen; [pdf] [supp]
[bibtex]
@InProceedings{Wu_2026_WACV, author = {Wu, Ying-Kun and Shen, Yi and Huang, Tzuhsuan and Fang, I-Sheng and Chen, Jun-Cheng}, title = {KMOPS: Keypoint-Driven Method for Multi-Object Pose and Metric Size Estimation from Stereo Images}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7730-7739} }
Referring Change Detection in Remote Sensing Imagery: Yilmaz Korkmaz,

Jay N. Paranjape,

Celso M. de Melo,

Vishal M. Patel; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Korkmaz_2026_WACV, author = {Korkmaz, Yilmaz and Paranjape, Jay N. and de Melo, Celso M. and Patel, Vishal M.}, title = {Referring Change Detection in Remote Sensing Imagery}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {106-116} }
Isolating the Role of Temporal Information in Video Saliency: A Controlled Experimental Analysis: Peter El-Jiz,

Matthias Kuemmerer,

Matthias Tangemann,

Matthias Bethge,

Andreas Bartels,

Michael Mario Bannert; [pdf] [supp]
[bibtex]
@InProceedings{El-Jiz_2026_WACV, author = {El-Jiz, Peter and Kuemmerer, Matthias and Tangemann, Matthias and Bethge, Matthias and Bartels, Andreas and Bannert, Michael Mario}, title = {Isolating the Role of Temporal Information in Video Saliency: A Controlled Experimental Analysis}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5909-5918} }
Data-Driven Loss Functions for Inference-Time Optimization in Text-to-Image: Sapir Esther Yiflach,

Yuval Atzmon,

Gal Chechik; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yiflach_2026_WACV, author = {Yiflach, Sapir Esther and Atzmon, Yuval and Chechik, Gal}, title = {Data-Driven Loss Functions for Inference-Time Optimization in Text-to-Image}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3525-3535} }
ScoreNet: Netting Lightweight Quality Scores for Better Visual Assessment with Large Multi-Modality Models: Bahador Rashidi,

Kiarash Aghakasiri,

Shupei Zhang,

Amirmohsen Sattarifard,

Yue Zhang,

Chao Gao; [pdf] [supp]
[bibtex]
@InProceedings{Rashidi_2026_WACV, author = {Rashidi, Bahador and Aghakasiri, Kiarash and Zhang, Shupei and Sattarifard, Amirmohsen and Zhang, Yue and Gao, Chao}, title = {ScoreNet: Netting Lightweight Quality Scores for Better Visual Assessment with Large Multi-Modality Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7008-7018} }
Digital Forensic AI You Can Explain: A Case Study on Video Source Camera Identification: Maryna Veksler,

Kemal Akkaya,

Selcuk Uluagac; [pdf]
[bibtex]
@InProceedings{Veksler_2026_WACV, author = {Veksler, Maryna and Akkaya, Kemal and Uluagac, Selcuk}, title = {Digital Forensic AI You Can Explain: A Case Study on Video Source Camera Identification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7030-7039} }
CoreCaption: Core Caption based Text-to-Video Retrieval: Junkyu Jang; [pdf] [supp]
[bibtex]
@InProceedings{Jang_2026_WACV, author = {Jang, Junkyu}, title = {CoreCaption: Core Caption based Text-to-Video Retrieval}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6600-6610} }
M4U: Evaluating Multilingual Understanding and Reasoning for Large Multimodal Models: Hongyu Wang,

Jiayu Xu,

Senwei Xie,

Ruiping Wang,

Jialin Li,

Zhaojie Xie,

Bin Zhang,

Chuyan Xiong,

Xilin Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2026_WACV, author = {Wang, Hongyu and Xu, Jiayu and Xie, Senwei and Wang, Ruiping and Li, Jialin and Xie, Zhaojie and Zhang, Bin and Xiong, Chuyan and Chen, Xilin}, title = {M4U: Evaluating Multilingual Understanding and Reasoning for Large Multimodal Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {382-392} }
Snapmoji: Instant Generation of Animatable Dual-Stylized Avatars: Eric Ming Chen,

Di Liu,

Sizhuo Ma,

Michael Vasilkovsky,

Bing Zhou,

Qiang Gao,

Wenzhou Wang,

Jiahao Luo,

Dimitris N. Metaxas,

Vincent Sitzmann,

Jian Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2026_WACV, author = {Chen, Eric Ming and Liu, Di and Ma, Sizhuo and Vasilkovsky, Michael and Zhou, Bing and Gao, Qiang and Wang, Wenzhou and Luo, Jiahao and Metaxas, Dimitris N. and Sitzmann, Vincent and Wang, Jian}, title = {Snapmoji: Instant Generation of Animatable Dual-Stylized Avatars}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1948-1958} }
BanglaProtha: Evaluating Vision Language Models in Underrepresented Long-tail Cultural Contexts: Md Fahim,

Md Sakib Ul Rahman,

Akm Moshiur Rahman,

Md Farhan Ishmam,

Md Tasmim Rahman,

Fariha Tanjim Shifat,

Fabiha Haider,

Md Farhad Alam Bhuiyan; [pdf] [supp]
[bibtex]
@InProceedings{Fahim_2026_WACV, author = {Fahim, Md and Rahman, Md Sakib Ul and Rahman, Akm Moshiur and Ishmam, Md Farhan and Rahman, Md Tasmim and Shifat, Fariha Tanjim and Haider, Fabiha and Alam Bhuiyan, Md Farhad}, title = {BanglaProtha: Evaluating Vision Language Models in Underrepresented Long-tail Cultural Contexts}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1159-1169} }
CineVerse: Consistent Keyframe Synthesis for Cinematic Scene Composition: Quynh Phung,

Long Mai,

Fabian David Caba Heilbron,

Feng Liu,

Jia-Bin Huang,

Cusuh Ham; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Phung_2026_WACV, author = {Phung, Quynh and Mai, Long and Heilbron, Fabian David Caba and Liu, Feng and Huang, Jia-Bin and Ham, Cusuh}, title = {CineVerse: Consistent Keyframe Synthesis for Cinematic Scene Composition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2626-2636} }
Language Integration in Fine-Tuning Multimodal Large Language Models for Image-Based Regression: Roy H. Jennings,

Genady Paikin,

Roy Shaul,

Evgeny Soloveichik; [pdf] [arXiv]
[bibtex]
@InProceedings{Jennings_2026_WACV, author = {Jennings, Roy H. and Paikin, Genady and Shaul, Roy and Soloveichik, Evgeny}, title = {Language Integration in Fine-Tuning Multimodal Large Language Models for Image-Based Regression}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3462-3471} }
Towards Reliable Test-Time Adaptation: Style Invariance as a Correctness Likelihood: Gilhyun Nam,

Taewon Kim,

Joonhyun Jeong,

Eunho Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nam_2026_WACV, author = {Nam, Gilhyun and Kim, Taewon and Jeong, Joonhyun and Yang, Eunho}, title = {Towards Reliable Test-Time Adaptation: Style Invariance as a Correctness Likelihood}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {3088-3097} }
MBTI: Metric-Based Textual Inversion for Fine-Grained Image Generation: Byungkwan Chae,

Youngjae Choi,

Heewon Kim; [pdf] [supp]
[bibtex]
@InProceedings{Chae_2026_WACV, author = {Chae, Byungkwan and Choi, Youngjae and Kim, Heewon}, title = {MBTI: Metric-Based Textual Inversion for Fine-Grained Image Generation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1106-1116} }
PRISM-CAFO: Prior-conditioned Remote-sensing Infrastructure Segmentation and Mapping for CAFOs: Oishee Bintey Hoque,

Nibir Chandra Mandal,

Kyle Luong,

Amanda Wilson,

Samarth Swarup,

Madhav Marathe,

Abhijin Adiga; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hoque_2026_WACV, author = {Hoque, Oishee Bintey and Mandal, Nibir Chandra and Luong, Kyle and Wilson, Amanda and Swarup, Samarth and Marathe, Madhav and Adiga, Abhijin}, title = {PRISM-CAFO: Prior-conditioned Remote-sensing Infrastructure Segmentation and Mapping for CAFOs}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {2083-2093} }
Gaussian Representations for Video: Sachin Shah,

Anustup Choudhury,

Guan-Ming Su,

Jaclyn Pytlarz,

Christopher A. Metzler,

Trisha Mittal; [pdf] [supp]
[bibtex]
@InProceedings{Shah_2026_WACV, author = {Shah, Sachin and Choudhury, Anustup and Su, Guan-Ming and Pytlarz, Jaclyn and Metzler, Christopher A. and Mittal, Trisha}, title = {Gaussian Representations for Video}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {827-837} }
Semantic Map Guided Bird's-Eye View Learning for Online HD Map Construction: Huantao Ren,

Hesham M. Eraqi,

ABM Musa,

Mohamed Moustafa; [pdf]
[bibtex]
@InProceedings{Ren_2026_WACV, author = {Ren, Huantao and Eraqi, Hesham M. and Musa, ABM and Moustafa, Mohamed}, title = {Semantic Map Guided Bird's-Eye View Learning for Online HD Map Construction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7852-7861} }
X-JEPA: A Novel Joint Learning Cross-Modal Predictive Alignment Framework for Remote Sensing Image Retrieval: Shabnam Choudhury,

Yash Salunkhe,

Vaibhav Rajan,

Subhasis Chaudhuri,

Biplab Banerjee; [pdf] [supp]
[bibtex]
@InProceedings{Choudhury_2026_WACV, author = {Choudhury, Shabnam and Salunkhe, Yash and Rajan, Vaibhav and Chaudhuri, Subhasis and Banerjee, Biplab}, title = {X-JEPA: A Novel Joint Learning Cross-Modal Predictive Alignment Framework for Remote Sensing Image Retrieval}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4355-4364} }
VLMs Guided Interpretable Decision Making in Autonomous Driving: Xin Hu,

Taotao Jing,

Renran Tian,

Zhengming Ding; [pdf] [arXiv]
[bibtex]
@InProceedings{Hu_2026_WACV, author = {Hu, Xin and Jing, Taotao and Tian, Renran and Ding, Zhengming}, title = {VLMs Guided Interpretable Decision Making in Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4494-4503} }
Confidence Through Parallel Attention for Depth and Uncertainty Estimation in Dynamic Environments: Onkar Susladkar,

Rohit Pawar,

Chirag Sehgal,

Samaksh Ujjawal,

Sparsh Mittal; [pdf] [supp]
[bibtex]
@InProceedings{Susladkar_2026_WACV, author = {Susladkar, Onkar and Pawar, Rohit and Sehgal, Chirag and Ujjawal, Samaksh and Mittal, Sparsh}, title = {Confidence Through Parallel Attention for Depth and Uncertainty Estimation in Dynamic Environments}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4396-4406} }
Enhancing Monocular 3D Hand Reconstruction with Learned Texture Priors: Giorgos Karvounas,

Nikolaos Kyriazis,

Iason Oikonomidis,

Georgios Pavlakos,

Antonis A. Argyros; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Karvounas_2026_WACV, author = {Karvounas, Giorgos and Kyriazis, Nikolaos and Oikonomidis, Iason and Pavlakos, Georgios and Argyros, Antonis A.}, title = {Enhancing Monocular 3D Hand Reconstruction with Learned Texture Priors}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7073-7083} }
ACuRE: Accurate Continuity-Regularized SpO2 Estimation Using Liquid Time-Constant Networks: Shahzad Ahmad,

Divya Mishra,

Sania Bano,

Sukalpa Chanda,

Yogesh Singh Rawat; [pdf] [supp]
[bibtex]
@InProceedings{Ahmad_2026_WACV, author = {Ahmad, Shahzad and Mishra, Divya and Bano, Sania and Chanda, Sukalpa and Rawat, Yogesh Singh}, title = {ACuRE: Accurate Continuity-Regularized SpO2 Estimation Using Liquid Time-Constant Networks}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {7250-7259} }
SceneShine: Illumination-aware Human Scene Gaussian Re-Splatting from Mobile Device Video: Xuqian Ren,

Wenjia Wang,

Mai Ngoc Nguyen,

Juho Kannala,

Esa Rahtu; [pdf] [supp]
[bibtex]
@InProceedings{Ren_2026_WACV, author = {Ren, Xuqian and Wang, Wenjia and Nguyen, Mai Ngoc and Kannala, Juho and Rahtu, Esa}, title = {SceneShine: Illumination-aware Human Scene Gaussian Re-Splatting from Mobile Device Video}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {8302-8312} }
Gene-DML: Dual-Pathway Multi-Level Discrimination for Gene Expression Prediction from Histopathology Images: Yaxuan Song,

Jianan Fan,

Hang Chang,

Weidong Cai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Song_2026_WACV, author = {Song, Yaxuan and Fan, Jianan and Chang, Hang and Cai, Weidong}, title = {Gene-DML: Dual-Pathway Multi-Level Discrimination for Gene Expression Prediction from Histopathology Images}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5090-5099} }
PatchEAD: Unifying Industrial Visual Prompting Frameworks for Patch-Exclusive Anomaly Detection: Po-Han Huang,

Jeng-Lin Li,

Po-Hsuan Huang,

Ming-Ching Chang,

Wei-Chao Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2026_WACV, author = {Huang, Po-Han and Li, Jeng-Lin and Huang, Po-Hsuan and Chang, Ming-Ching and Chen, Wei-Chao}, title = {PatchEAD: Unifying Industrial Visual Prompting Frameworks for Patch-Exclusive Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {5531-5540} }
DODA: Adapting Object Detectors to Dynamic Agricultural Environments in Real-Time with Diffusion: Shuai Xiang,

Pieter M. Blok,

James Burridge,

Haozhou Wang,

Wei Guo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xiang_2026_WACV, author = {Xiang, Shuai and Blok, Pieter M. and Burridge, James and Wang, Haozhou and Guo, Wei}, title = {DODA: Adapting Object Detectors to Dynamic Agricultural Environments in Real-Time with Diffusion}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4797-4807} }
T2VWorldBench: A Benchmark for Evaluating World Knowledge in Text-to-Video Generation: Yubin Chen,

Xuyang Guo,

Zhenmei Shi,

Zhao Song,

Jiahao Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2026_WACV, author = {Chen, Yubin and Guo, Xuyang and Shi, Zhenmei and Song, Zhao and Zhang, Jiahao}, title = {T2VWorldBench: A Benchmark for Evaluating World Knowledge in Text-to-Video Generation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {6474-6485} }
Unlocking Vision-Language Models for Video Anomaly Detection via Fine-Grained Prompting: Shu Zou,

Xinyu Tian,

Lukas Wesemann,

Fabian Waschkowski,

Zhaoyuan Yang,

Jing Zhang; [pdf] [arXiv]
[bibtex]
@InProceedings{Zou_2026_WACV, author = {Zou, Shu and Tian, Xinyu and Wesemann, Lukas and Waschkowski, Fabian and Yang, Zhaoyuan and Zhang, Jing}, title = {Unlocking Vision-Language Models for Video Anomaly Detection via Fine-Grained Prompting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {4223-4233} }
HyPCA-Net: Advancing Multimodal Fusion in Medical Image Analysis: Joy Dhar,

Manish Kumar Pandey,

Debashis Das Chakladar,

Maryam Haghighat,

Azadeh Alavi,

Sajib Mistry,

Nayyar Zaidi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dhar_2026_WACV, author = {Dhar, Joy and Pandey, Manish Kumar and Das Chakladar, Debashis and Haghighat, Maryam and Alavi, Azadeh and Mistry, Sajib and Zaidi, Nayyar}, title = {HyPCA-Net: Advancing Multimodal Fusion in Medical Image Analysis}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {1831-1840} }
No MoCap Needed: Post-Training Motion Diffusion Models with Reinforcement Learning using Only Textual Prompts: Macaluso Girolamo,

Mandelli Lorenzo,

Mirko Bicchierai,

Stefano Berretti,

Andrew D. Bagdanov; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Girolamo_2026_WACV, author = {Girolamo, Macaluso and Lorenzo, Mandelli and Bicchierai, Mirko and Berretti, Stefano and Bagdanov, Andrew D.}, title = {No MoCap Needed: Post-Training Motion Diffusion Models with Reinforcement Learning using Only Textual Prompts}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {967-976} }; Back