WACV 2026 Open Access Repository

Papers

Back
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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