CVPR 2026 Open Access Repository

The 5th DataCV Workshop and Challenge

BlendFusion - Scalable Synthetic Data Generation for Diffusion Model Training: Thejas Venkatesh,

Suguna Varshini Velury; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Venkatesh_2026_CVPR, author = {Venkatesh, Thejas and Velury, Suguna Varshini}, title = {BlendFusion - Scalable Synthetic Data Generation for Diffusion Model Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3012-3021} }
OASIS: Generating Synthetic Skin Artifacts: Elena Sizikova,

Niloufar Saharkhiz,

Jana G Delfino,

Aldo Badano; [pdf] [supp]
[bibtex]
@InProceedings{Sizikova_2026_CVPR, author = {Sizikova, Elena and Saharkhiz, Niloufar and Delfino, Jana G and Badano, Aldo}, title = {OASIS: Generating Synthetic Skin Artifacts}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {2993-3002} }
Edit, Crop, and Prompt: Training-Free Visual Question Answering via Preprocessing Pipelines for Real-World Visual Illusions: Jingwei Bao,

Yunhui Deng; [pdf]
[bibtex]
@InProceedings{Bao_2026_CVPR, author = {Bao, Jingwei and Deng, Yunhui}, title = {Edit, Crop, and Prompt: Training-Free Visual Question Answering via Preprocessing Pipelines for Real-World Visual Illusions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {2880-2885} }
4KLSDB: A Large-Scale Dataset for 4K Image Restoration and Text-to-Image Generation: Zihao Zhu,

Kuan-Ru Huang,

ZhaoMing Xu,

Renjie Li,

Bo Wu,

Ruizheng Bai,

Mingyang Wu,

Sayak Paul,

Zhengzhong Tu; [pdf]
[bibtex]
@InProceedings{Zhu_2026_CVPR, author = {Zhu, Zihao and Huang, Kuan-Ru and Xu, ZhaoMing and Li, Renjie and Wu, Bo and Bai, Ruizheng and Wu, Mingyang and Paul, Sayak and Tu, Zhengzhong}, title = {4KLSDB: A Large-Scale Dataset for 4K Image Restoration and Text-to-Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3052-3061} }
Which Frames Matter? Frame Selection for Training Object Detectors on Driving Videos: Vinicius Avena,

João Victor D Sobrinho,

Douglas Castilho,

Rodrigo S. Couto,

Miguel E M Campista,

Luis H M. K. Costa,

Andre C P L F Carvalho; [pdf]
[bibtex]
@InProceedings{Avena_2026_CVPR, author = {Avena, Vinicius and Sobrinho, Jo\~ao Victor D and Castilho, Douglas and Couto, Rodrigo S. and E M Campista, Miguel and Costa, Luis H M. K. and Carvalho, Andre C P L F}, title = {Which Frames Matter? Frame Selection for Training Object Detectors on Driving Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {2870-2879} }
An Approach to Enriching Surgical Video Datasets for Fine-Grained Spatial-Temporal Understanding of Vision-Language Models: Lennart Maack,

Alexander Schlaefer; [pdf] [arXiv]
[bibtex]
@InProceedings{Maack_2026_CVPR, author = {Maack, Lennart and Schlaefer, Alexander}, title = {An Approach to Enriching Surgical Video Datasets for Fine-Grained Spatial-Temporal Understanding of Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {2945-2954} }
Illusion-Aware Visual Preprocessing and Anti-Illusion Prompting for Classic Illusion Understanding in Vision-Language Models: Junli Zha,

Jiahui Wang,

Xinkai Lu,

Jinbo Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Zha_2026_CVPR, author = {Zha, Junli and Wang, Jiahui and Lu, Xinkai and Wang, Jinbo}, title = {Illusion-Aware Visual Preprocessing and Anti-Illusion Prompting for Classic Illusion Understanding in Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3034-3042} }
Real-Wild-VLM: Prompting Large Vision-Language Models for Wildlife Recognition in Camera-Trap Videos: Yutong Deng,

Qi Song,

Lei Bao,

Jianping Ge; [pdf]
[bibtex]
@InProceedings{Deng_2026_CVPR, author = {Deng, Yutong and Song, Qi and Bao, Lei and Ge, Jianping}, title = {Real-Wild-VLM: Prompting Large Vision-Language Models for Wildlife Recognition in Camera-Trap Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {2897-2902} }
FG-PersonX: A Scalable Synthetic Dataset for Fine-Grained Person Re-Identification: Ruotian Zhang,

Xiangteng He; [pdf]
[bibtex]
@InProceedings{Zhang_2026_CVPR, author = {Zhang, Ruotian and He, Xiangteng}, title = {FG-PersonX: A Scalable Synthetic Dataset for Fine-Grained Person Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3047-3051} }
When Every Label Counts: Wasserstein-Optimal Dataset Representation for Coreset Selection in Annotation-Scarce AI-Generated Image Quality Assessment: Tushar Shinde,

Sreejita Roy; [pdf]
[bibtex]
@InProceedings{Shinde_2026_CVPR, author = {Shinde, Tushar and Roy, Sreejita}, title = {When Every Label Counts: Wasserstein-Optimal Dataset Representation for Coreset Selection in Annotation-Scarce AI-Generated Image Quality Assessment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {2974-2982} }
Enhancing Coreset Selection Via Teacher-Guided Soft Labels: Saumyaranjan Mohanty,

Konda Reddy Mopuri; [pdf]
[bibtex]
@InProceedings{Mohanty_2026_CVPR, author = {Mohanty, Saumyaranjan and Mopuri, Konda Reddy}, title = {Enhancing Coreset Selection Via Teacher-Guided Soft Labels}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {2955-2963} }
VGGHeads: 3D Multi Head Alignment with a Large-Scale Synthetic Dataset: Orest Kupyn,

Eugene Khvedchenya,

Christian Rupprecht; [pdf] [supp]
[bibtex]
@InProceedings{Kupyn_2026_CVPR, author = {Kupyn, Orest and Khvedchenya, Eugene and Rupprecht, Christian}, title = {VGGHeads: 3D Multi Head Alignment with a Large-Scale Synthetic Dataset}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {2923-2933} }
A Two-Stage ICL Pipeline for Robust Visual Illusion Understanding: Yiming Zhang,

Xiongkuo Min,

Guangtao Zhai; [pdf]
[bibtex]
@InProceedings{Zhang_2026_CVPR, author = {Zhang, Yiming and Min, Xiongkuo and Zhai, Guangtao}, title = {A Two-Stage ICL Pipeline for Robust Visual Illusion Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3043-3046} }
Gen-SIS: Generative Self-augmentation Improves Self-supervised Learning: Varun Belagali,

Srikar Yellapragada,

Alexandros Graikos,

Saarthak Kapse,

Zilinghan Li,

Tarak Nath Nandi,

Ravi K Madduri,

Prateek Prasanna,

Joel Saltz,

Dimitris Samaras; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Belagali_2026_CVPR, author = {Belagali, Varun and Yellapragada, Srikar and Graikos, Alexandros and Kapse, Saarthak and Li, Zilinghan and Nandi, Tarak Nath and Madduri, Ravi K and Prasanna, Prateek and Saltz, Joel and Samaras, Dimitris}, title = {Gen-SIS: Generative Self-augmentation Improves Self-supervised Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {2886-2896} }
Beyond Data Augmentation: Energy-Based Kuramoto Neurons for Semi-Supervised Learning: Yundi Hong,

Ao Li,

Xinyuan Song,

Yan Zhong,

Hongyang He,

Victor Sanchez; [pdf]
[bibtex]
@InProceedings{Hong_2026_CVPR, author = {Hong, Yundi and Li, Ao and Song, Xinyuan and Zhong, Yan and He, Hongyang and Sanchez, Victor}, title = {Beyond Data Augmentation: Energy-Based Kuramoto Neurons for Semi-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {2913-2922} }
Schema Affects Evaluation Conclusions: Metadata Context in Medical VLM Benchmarks: Daniel Vela Jarquin; [pdf]
[bibtex]
@InProceedings{Jarquin_2026_CVPR, author = {Jarquin, Daniel Vela}, title = {Schema Affects Evaluation Conclusions: Metadata Context in Medical VLM Benchmarks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3003-3011} }
Less Detail, Better Answers: Degradation-Driven Prompting for VQA: Haoxuan Han,

Weijie wang,

Zeyu Zhang,

Yefei He,

Bohan Zhuang; [pdf] [arXiv]
[bibtex]
@InProceedings{Han_2026_CVPR, author = {Han, Haoxuan and wang, Weijie and Zhang, Zeyu and He, Yefei and Zhuang, Bohan}, title = {Less Detail, Better Answers: Degradation-Driven Prompting for VQA}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {2903-2912} }
Analyzing Training-Free Corruption Detection for Object Detection Datasets: Christian Sieberichs,

Simon Geerkens,

Thomas Waschulzik,

Ramesh Visvanathan,

Alexander Braun; [pdf]
[bibtex]
@InProceedings{Sieberichs_2026_CVPR, author = {Sieberichs, Christian and Geerkens, Simon and Waschulzik, Thomas and Visvanathan, Ramesh and Braun, Alexander}, title = {Analyzing Training-Free Corruption Detection for Object Detection Datasets}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {2983-2992} }
PIVOT: Prior-Interrupting Visual Option Testing for Counterintuitive Image Understanding with Frozen VLMs: Hang Yu,

Hong Sun,

Xiaochen Liu,

Jiahao Wen,

Ruihan Wang,

Shilv Cai,

Haoning Alice Xi,

Zhenbo Li; [pdf]
[bibtex]
@InProceedings{Yu_2026_CVPR, author = {Yu, Hang and Sun, Hong and Liu, Xiaochen and Wen, Jiahao and Wang, Ruihan and Cai, Shilv and Xi, Haoning Alice and Li, Zhenbo}, title = {PIVOT: Prior-Interrupting Visual Option Testing for Counterintuitive Image Understanding with Frozen VLMs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3027-3033} }
IndoorCrowd: A Multi-Scene Dataset for Human Detection, Segmentation, and Tracking with an Automated Annotation Pipeline: Sebastian-Ion Nae,

Radu Moldoveanu,

Alexandra Ștefania Ghiță,

Adina Magda Florea; [pdf] [supp]
[bibtex]
@InProceedings{Nae_2026_CVPR, author = {Nae, Sebastian-Ion and Moldoveanu, Radu and Ghiț\u{a}, Alexandra Ștefania and Florea, Adina Magda}, title = {IndoorCrowd: A Multi-Scene Dataset for Human Detection, Segmentation, and Tracking with an Automated Annotation Pipeline}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {2964-2973} }
Unleashing the Potential of Generative Data Augmentation for Semantic Segmentation via Intrinsic Mask Distribution Modeling: Yuqi Lin,

Wenqi Shao,

Shiqu Liu,

Zhihong Gu,

Wenxiao Wang,

Xiaofei He,

Kaipeng Zhang; [pdf]
[bibtex]
@InProceedings{Lin_2026_CVPR, author = {Lin, Yuqi and Shao, Wenqi and Liu, Shiqu and Gu, Zhihong and Wang, Wenxiao and He, Xiaofei and Zhang, Kaipeng}, title = {Unleashing the Potential of Generative Data Augmentation for Semantic Segmentation via Intrinsic Mask Distribution Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {2934-2944} }
Seeing the Evidence, Missing the Answer: Tool-Guided Vision-Language Models on Visual Illusions: Xuesong Wang,

Harry Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2026_CVPR, author = {Wang, Xuesong and Wang, Harry}, title = {Seeing the Evidence, Missing the Answer: Tool-Guided Vision-Language Models on Visual Illusions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3022-3026} }