WACV 2026 Open Access Repository

5th Workshop on Image/Video/Audio Quality Assessment in Computer Vision, VLM and Diffusion Model

VIBEFACE - Video and Image Biometric Dataset for Evaluation of Faces: Ewelina Bartuzi-Trokielewicz,

Michał Koźbiał,

Adam Baran,

Adrian Kordas,

Jarosław Wójtowicz,

Elżbieta Gomulska,

Michał Banach,

Alicja Martinek,

Michał Ołowski,

Joanna Gajewska; [pdf]
[bibtex]
@InProceedings{Bartuzi-Trokielewicz_2026_WACV, author = {Bartuzi-Trokielewicz, Ewelina and Ko\'zbia{\l}, Micha{\l} and Baran, Adam and Kordas, Adrian and W\'ojtowicz, Jaros{\l}aw and Gomulska, El\.zbieta and Banach, Micha{\l} and Martinek, Alicja and O{\l}owski, Micha{\l} and Gajewska, Joanna}, title = {VIBEFACE - Video and Image Biometric Dataset for Evaluation of Faces}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1028-1037} }
Subtle Motion Blur Detection and Segmentation from Static Image Artworks: Ganesh Samarth Chamarahalli Arunkumar,

Sibendu Paul,

Solale Tabarestani,

Caren Chen; [pdf]
[bibtex]
@InProceedings{Arunkumar_2026_WACV, author = {Arunkumar, Ganesh Samarth Chamarahalli and Paul, Sibendu and Tabarestani, Solale and Chen, Caren}, title = {Subtle Motion Blur Detection and Segmentation from Static Image Artworks}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1233-1242} }
STEC: A Spatio-Temporal Entropy Coverage Metric for Evaluating Sampled Video Frames: Shih-Yao Lin; [pdf]
[bibtex]
@InProceedings{Lin_2026_WACV, author = {Lin, Shih-Yao}, title = {STEC: A Spatio-Temporal Entropy Coverage Metric for Evaluating Sampled Video Frames}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1021-1027} }
Reason Then Ground: Multilingual Text/Logo Grounding on Movie Posters: Ganesh Samarth,

Yarong Feng,

Solale Tabarestani,

Caren Chen,

Xiaonan Zhao; [pdf] [supp]
[bibtex]
@InProceedings{Samarth_2026_WACV, author = {Samarth, Ganesh and Feng, Yarong and Tabarestani, Solale and Chen, Caren and Zhao, Xiaonan}, title = {Reason Then Ground: Multilingual Text/Logo Grounding on Movie Posters}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1087-1095} }
Image-Specific Adaptation of Transformer Encoders for Compute-Efficient Segmentation: Manyi Yao,

Abhishek Aich,

Yumin Suh,

Amit Roy-Chowdhury,

Christian Shelton,

Manmohan Chandraker; [pdf]
[bibtex]
@InProceedings{Yao_2026_WACV, author = {Yao, Manyi and Aich, Abhishek and Suh, Yumin and Roy-Chowdhury, Amit and Shelton, Christian and Chandraker, Manmohan}, title = {Image-Specific Adaptation of Transformer Encoders for Compute-Efficient Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1116-1125} }
From Filters to VLMs: Benchmarking Defogging Methods through Object Detection and Segmentation Performance: Ardalan Aryashad,

Parsa Razmara,

Amin Mahjoub,

Seyedarmin Azizi,

Mahdi Salmani,

Arad Firouzkouhi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Aryashad_2026_WACV, author = {Aryashad, Ardalan and Razmara, Parsa and Mahjoub, Amin and Azizi, Seyedarmin and Salmani, Mahdi and Firouzkouhi, Arad}, title = {From Filters to VLMs: Benchmarking Defogging Methods through Object Detection and Segmentation Performance}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1106-1115} }
Efficient Deep Demosaicing with Spatially Downsampled Isotropic Networks: Cory Fan,

Wenchao Zhang; [pdf] [arXiv]
[bibtex]
@InProceedings{Fan_2026_WACV, author = {Fan, Cory and Zhang, Wenchao}, title = {Efficient Deep Demosaicing with Spatially Downsampled Isotropic Networks}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1012-1020} }
ViTNT-FIQA: Training-Free Face Image Quality Assessment with Vision Transformers: Guray Ozgur,

Eduarda Caldeira,

Tahar Chettaoui,

Jan Niklas Kolf,

Marco Huber,

Naser Damer,

Fadi Boutros; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ozgur_2026_WACV, author = {Ozgur, Guray and Caldeira, Eduarda and Chettaoui, Tahar and Kolf, Jan Niklas and Huber, Marco and Damer, Naser and Boutros, Fadi}, title = {ViTNT-FIQA: Training-Free Face Image Quality Assessment with Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1203-1213} }
When Probe and Gallery are Low Quality: Decreasing Accuracy and Increasing Demographic Disparities in 1:N Identification: Gabriella Pangelinan,

Michael King,

Kevin Bowyer; [pdf]
[bibtex]
@InProceedings{Pangelinan_2026_WACV, author = {Pangelinan, Gabriella and King, Michael and Bowyer, Kevin}, title = {When Probe and Gallery are Low Quality: Decreasing Accuracy and Increasing Demographic Disparities in 1:N Identification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1174-1183} }
Vision Language Models Learn to Assess Images with Specialists: Quyet V. Do,

Seunghyun Yoon,

Ruiyi Zhang,

Thiloshon Nagarajah,

Trung Bui,

Viet Dac Lai; [pdf] [supp]
[bibtex]
@InProceedings{Do_2026_WACV, author = {Do, Quyet V. and Yoon, Seunghyun and Zhang, Ruiyi and Nagarajah, Thiloshon and Bui, Trung and Lai, Viet Dac}, title = {Vision Language Models Learn to Assess Images with Specialists}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1126-1135} }
REMinD: Balancing Robust Concept Unlearning and Image Quality in Diffusion Models: An Huang,

Junggab Son,

Zuobin Xiong; [pdf] [supp]
[bibtex]
@InProceedings{Huang_2026_WACV, author = {Huang, An and Son, Junggab and Xiong, Zuobin}, title = {REMinD: Balancing Robust Concept Unlearning and Image Quality in Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1068-1077} }
Device-Robust Spectral Grading and Origin Detection from UV-Vis-NIR Images: Towards Practical Gemstone Quality Assessment: Mahule Roy,

Srikanth Thudumu,

Jason Fisher,

Rajesh Vasa,

Kon Mouzakis; [pdf]
[bibtex]
@InProceedings{Roy_2026_WACV, author = {Roy, Mahule and Thudumu, Srikanth and Fisher, Jason and Vasa, Rajesh and Mouzakis, Kon}, title = {Device-Robust Spectral Grading and Origin Detection from UV-Vis-NIR Images: Towards Practical Gemstone Quality Assessment}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1224-1232} }
JetBench: Quality-Aware Benchmarking of Vision Models for Jet Parameter Classification in Heavy-Ion Physics: Haydar Mehryar,

Loren Schwiebert; [pdf] [supp]
[bibtex]
@InProceedings{Mehryar_2026_WACV, author = {Mehryar, Haydar and Schwiebert, Loren}, title = {JetBench: Quality-Aware Benchmarking of Vision Models for Jet Parameter Classification in Heavy-Ion Physics}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1214-1223} }
Transforming Video Subjective Testing with Training, Engagement, and Real-Time Feedback: Kumar Rahul,

Sriram Sethuraman,

Andrew Segall,

Yixu Chen; [pdf] [arXiv]
[bibtex]
@InProceedings{Rahul_2026_WACV, author = {Rahul, Kumar and Sethuraman, Sriram and Segall, Andrew and Chen, Yixu}, title = {Transforming Video Subjective Testing with Training, Engagement, and Real-Time Feedback}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {994-1002} }
Enhancement as Augmentation: Improving Detection in Highly Degraded Underwater Images Through Mixed-Domain Training: Ashraf Saleem,

Alex Hromada,

Ali Awad,

Amna Mazen,

Evan Lucas,

Timothy C. Havens; [pdf]
[bibtex]
@InProceedings{Saleem_2026_WACV, author = {Saleem, Ashraf and Hromada, Alex and Awad, Ali and Mazen, Amna and Lucas, Evan and Havens, Timothy C.}, title = {Enhancement as Augmentation: Improving Detection in Highly Degraded Underwater Images Through Mixed-Domain Training}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1096-1105} }
Cost Savings from Automatic Quality Assessment of Generated Images: Xavier Giró-i-Nieto,

Nefeli Andreou,

Anqi Liang,

Manel Baradad,

Francesc Moreno-Noguer,

Aleix M Martinez; [pdf] [supp]
[bibtex]
@InProceedings{Giro-i-Nieto_2026_WACV, author = {Gir\'o-i-Nieto, Xavier and Andreou, Nefeli and Liang, Anqi and Baradad, Manel and Moreno-Noguer, Francesc and Martinez, Aleix M}, title = {Cost Savings from Automatic Quality Assessment of Generated Images}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1048-1057} }
We Still See Broken Limbs: Towards Anatomical Realism in GenAI via Human Preference Learning: Stephanie Käs,

Erik Schönherr,

Bastian Leibe; [pdf] [supp]
[bibtex]
@InProceedings{Kas_2026_WACV, author = {K\"as, Stephanie and Sch\"onherr, Erik and Leibe, Bastian}, title = {We Still See Broken Limbs: Towards Anatomical Realism in GenAI via Human Preference Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1038-1047} }
Fast 2DGS: Efficient Image Representation with Deep Gaussian Prior: Hao Wang,

Ashish Bastola,

Chaoyi Zhou,

Wenhui Zhu,

Xiwen Chen,

Xuanzhao Dong,

Siyu Huang,

Abolfazl Razi; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2026_WACV, author = {Wang, Hao and Bastola, Ashish and Zhou, Chaoyi and Zhu, Wenhui and Chen, Xiwen and Dong, Xuanzhao and Huang, Siyu and Razi, Abolfazl}, title = {Fast 2DGS: Efficient Image Representation with Deep Gaussian Prior}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1184-1193} }
Quality-Driven and Diversity-Aware Sample Expansion for Robust Marine Obstacle Segmentation: Miaohua Zhang,

Mohammad Ali Armin,

Xuesong Li,

Sisi Liang,

Lars Petersson,

Changming Sun,

David Ahmedt-Aristizabal,

Zeeshan Hayder; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2026_WACV, author = {Zhang, Miaohua and Armin, Mohammad Ali and Li, Xuesong and Liang, Sisi and Petersson, Lars and Sun, Changming and Ahmedt-Aristizabal, David and Hayder, Zeeshan}, title = {Quality-Driven and Diversity-Aware Sample Expansion for Robust Marine Obstacle Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1136-1145} }
VideoForge: Efficient Domain Adaptation for Video Generation Through Quality-Driven Rewards and Enhanced LoRA: Xiaogang Wang,

Bill Cai,

Girish Patil,

Yash Shah; [pdf]
[bibtex]
@InProceedings{Wang_2026_WACV, author = {Wang, Xiaogang and Cai, Bill and Patil, Girish and Shah, Yash}, title = {VideoForge: Efficient Domain Adaptation for Video Generation Through Quality-Driven Rewards and Enhanced LoRA}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1194-1202} }
SPoRC-VIST: A Benchmark for Evaluating Generative Natural Narrative in Vision-Language Models: Yunlin Zeng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zeng_2026_WACV, author = {Zeng, Yunlin}, title = {SPoRC-VIST: A Benchmark for Evaluating Generative Natural Narrative in Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1078-1086} }
CARLA-Haze: A Synthetic Benchmark for Outdoor Image Dehazing: Henry O. Velesaca,

Leo Thomas Ramos,

Angel D. Sappa; [pdf]
[bibtex]
@InProceedings{Velesaca_2026_WACV, author = {Velesaca, Henry O. and Ramos, Leo Thomas and Sappa, Angel D.}, title = {CARLA-Haze: A Synthetic Benchmark for Outdoor Image Dehazing}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1164-1173} }
HandSurge: Localized Neural Surgery for Diffusion-Generated Hand Deformity Restoration: Zhiqiang Lao,

Dizhi Ma,

Heather Yu; [pdf]
[bibtex]
@InProceedings{Lao_2026_WACV, author = {Lao, Zhiqiang and Ma, Dizhi and Yu, Heather}, title = {HandSurge: Localized Neural Surgery for Diffusion-Generated Hand Deformity Restoration}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1058-1067} }
YOLO-OSA: A ShuffleAttention-Enhanced YOLO Model for FOD Detection with Comprehensive Benchmarking on MS COCO: Soumen Biswas,

Abhishek Mitra,

Ananth Ganesh,

Kingshuk Banerjee; [pdf] [supp]
[bibtex]
@InProceedings{Biswas_2026_WACV, author = {Biswas, Soumen and Mitra, Abhishek and Ganesh, Ananth and Banerjee, Kingshuk}, title = {YOLO-OSA: A ShuffleAttention-Enhanced YOLO Model for FOD Detection with Comprehensive Benchmarking on MS COCO}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1154-1163} }
HiFi-Deblur: High-Frequency Intense Image Deblurring with Frequency-Decoupled U-Net and Discrete Wavelet Transform: Jeewoo Lim,

Cheolhee Yu,

Jin Tae Kwak; [pdf]
[bibtex]
@InProceedings{Lim_2026_WACV, author = {Lim, Jeewoo and Yu, Cheolhee and Kwak, Jin Tae}, title = {HiFi-Deblur: High-Frequency Intense Image Deblurring with Frequency-Decoupled U-Net and Discrete Wavelet Transform}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {984-993} }
Diffuse4D: Completing NeRF-Stereo Depth via Diffusion-Driven Restoration in Dynamic Scenes: Yue Hu,

Daniel Wang,

Xiyun Song,

Zhiqiang Lao,

Yubin Zhou,

Meida Chen,

Andrew Feng,

Heather Yu; [pdf]
[bibtex]
@InProceedings{Hu_2026_WACV, author = {Hu, Yue and Wang, Daniel and Song, Xiyun and Lao, Zhiqiang and Zhou, Yubin and Chen, Meida and Feng, Andrew and Yu, Heather}, title = {Diffuse4D: Completing NeRF-Stereo Depth via Diffusion-Driven Restoration in Dynamic Scenes}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1003-1011} }
Seeing in the Dark: Synthesizing Underexposure for More Robust Underwater Image Augmentation: Ali Awad,

Evan Lucas,

Ashraf Saleem,

Shadi Moradi,

Anthony Geglio,

Angus Galloway,

Timothy Havens,

Peter Esselman; [pdf]
[bibtex]
@InProceedings{Awad_2026_WACV, author = {Awad, Ali and Lucas, Evan and Saleem, Ashraf and Moradi, Shadi and Geglio, Anthony and Galloway, Angus and Havens, Timothy and Esselman, Peter}, title = {Seeing in the Dark: Synthesizing Underexposure for More Robust Underwater Image Augmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1146-1153} }
Can You Find the Difference? Visually Identical Image Detection: Haiyun Jin,

Yarong Feng,

Jiaojiao Zhao,

Minmin Shen,

Caren Chen; [pdf]
[bibtex]
@InProceedings{Jin_2026_WACV, author = {Jin, Haiyun and Feng, Yarong and Zhao, Jiaojiao and Shen, Minmin and Chen, Caren}, title = {Can You Find the Difference? Visually Identical Image Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1243-1249} }