Video Generative Models: Benchmarks and Evaluation

Tempered Self-Similarity Alignment for Physically Plausible Video Generation

Manjin Kim,

Suha Kwak,

Minsu Cho

[pdf] [supp]

[bibtex]

@InProceedings{Kim_2026_CVPR, author = {Kim, Manjin and Kwak, Suha and Cho, Minsu}, title = {Tempered Self-Similarity Alignment for Physically Plausible Video Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5148-5158} }

Risk-Controllable Multi-View Diffusion for Driving Scenario Generation

Hongyi Lin,

Wenxiu Shi,

Heye Huang,

Dingyi Zhuang,

Song Zhang,

Yang Liu,

Xiaobo Qu,

Jinhua Zhao

[pdf] [arXiv]

[bibtex]

@InProceedings{Lin_2026_CVPR, author = {Lin, Hongyi and Shi, Wenxiu and Huang, Heye and Zhuang, Dingyi and Zhang, Song and Liu, Yang and Qu, Xiaobo and Zhao, Jinhua}, title = {Risk-Controllable Multi-View Diffusion for Driving Scenario Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5169-5178} }

Generative AI Video Evaluation: Survey of Metrics, Benchmarks, and Trustworthiness

Kaveh Safavigerdini,

Bijaya Kumar Hatuwal,

Amirreza Daghighi,

Kannappan Palaniappan

[pdf]

[bibtex]

@InProceedings{Safavigerdini_2026_CVPR, author = {Safavigerdini, Kaveh and Hatuwal, Bijaya Kumar and Daghighi, Amirreza and Palaniappan, Kannappan}, title = {Generative AI Video Evaluation: Survey of Metrics, Benchmarks, and Trustworthiness}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5189-5200} }

Physics-Aware Video Instance Removal Benchmark

Zirui Li,

Xinghao Chen,

Lingyu Jiang,

Dengzhe Hou,

Fangzhou Lin,

Kazunori Yamada,

Xiangbo Gao,

Zhengzhong Tu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2026_CVPR, author = {Li, Zirui and Chen, Xinghao and Jiang, Lingyu and Hou, Dengzhe and Lin, Fangzhou and Yamada, Kazunori and Gao, Xiangbo and Tu, Zhengzhong}, title = {Physics-Aware Video Instance Removal Benchmark}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5159-5168} }

Inferring Dynamic Physical Properties from Video Foundation Models

Guanqi Zhan,

Xianzheng Ma,

Weidi Xie,

Andrew Zisserman

[pdf] [arXiv]

[bibtex]

@InProceedings{Zhan_2026_CVPR, author = {Zhan, Guanqi and Ma, Xianzheng and Xie, Weidi and Zisserman, Andrew}, title = {Inferring Dynamic Physical Properties from Video Foundation Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5214-5224} }

VGBE 2026 Challenge on Image-to-Video Consistent Generation: Methods and Results

Mingyang Wu,

Siyuan Yang,

Shuo Xing,

Ashirbad Mishra,

Soumik Dey,

Xiangbo Gao,

Jinyu Zhao,

Jiongze Yu,

Fangzhou Lin,

Zhengzhong Tu,

Yu Lei,

Zelin Feng,

Xiaopeng Zhou,

Yujie Guo,

Fang Liu,

Lingling Li,

Hongyang Du,

Junjie Ye,

Xiaoyan Cong,

Runhao Li,

Jingcheng Ni,

Aman Agarwal,

Zeqi Zhou,

Zekun Li,

Randall Balestriero,

Yue Wang,

Debajyoti Dasgupta,

Parth Mishra,

Gaurang Garg,

Pranshu Goel,

Sukh Manpreet Kaur,

Siwei Meng,

Pu Luo,

Cong Xu,

Yumei Li,

Licheng Jiao,

Xu Liu,

Wenping Ma

[pdf]

[bibtex]

@InProceedings{Wu_2026_CVPR, author = {Wu, Mingyang and Yang, Siyuan and Xing, Shuo and Mishra, Ashirbad and Dey, Soumik and Gao, Xiangbo and Zhao, Jinyu and Yu, Jiongze and Lin, Fangzhou and Tu, Zhengzhong and Lei, Yu and Feng, Zelin and Zhou, Xiaopeng and Guo, Yujie and Liu, Fang and Li, Lingling and Du, Hongyang and Ye, Junjie and Cong, Xiaoyan and Li, Runhao and Ni, Jingcheng and Agarwal, Aman and Zhou, Zeqi and Li, Zekun and Balestriero, Randall and Wang, Yue and Dasgupta, Debajyoti and Mishra, Parth and Garg, Gaurang and Goel, Pranshu and Kaur, Sukh Manpreet and Meng, Siwei and Luo, Pu and Xu, Cong and Li, Yumei and Jiao, Licheng and Liu, Xu and Ma, Wenping}, title = {VGBE 2026 Challenge on Image-to-Video Consistent Generation: Methods and Results}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5201-5213} }

AIGVE-MACS: Unified Multi-Aspect Commenting and Scoring Model for AI-Generated Video Evaluation

Xiao Liu,

Jiawei Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2026_CVPR, author = {Liu, Xiao and Zhang, Jiawei}, title = {AIGVE-MACS: Unified Multi-Aspect Commenting and Scoring Model for AI-Generated Video Evaluation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {5179-5188} }