Workshop on Agentic AI for Visual Media
Test-time Conditional Text-to-Image Synthesis Using Diffusion Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Shukla_2026_CVPR, author = {Shukla, Tripti and Karanam, Srikrishna and Srinivasan, Balaji Vasan}, title = {Test-time Conditional Text-to-Image Synthesis Using Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {4559-4568} }
TeDiO: Temporal Diagonal Optimization for Training-Free Coherent Video Diffusion-
[pdf]
[arXiv]
[bibtex]@InProceedings{Tursynbek_2026_CVPR, author = {Tursynbek, Nurislam and Lao, Zhiqiang and Yu, Heather and Bertasius, Gedas and Niethammer, Marc}, title = {TeDiO: Temporal Diagonal Optimization for Training-Free Coherent Video Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {4602-4612} }
Can Nano Banana 2 Replace Traditional Image Restoration Models? An Evaluation of Its Performance on Image Restoration Tasks-
[pdf]
[arXiv]
[bibtex]@InProceedings{Sun_2026_CVPR, author = {Sun, Weixiong and Yin, Xiang and Dong, Chao}, title = {Can Nano Banana 2 Replace Traditional Image Restoration Models? An Evaluation of Its Performance on Image Restoration Tasks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {4581-4590} }
From Task-Specific Models to Agentic Systems: Progress and Challenges of Agents in Image Restoration-
[pdf]
[bibtex]@InProceedings{Sun_2026_CVPR, author = {Sun, Weixiong and Yin, Xiang and Dong, Chao}, title = {From Task-Specific Models to Agentic Systems: Progress and Challenges of Agents in Image Restoration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {4569-4580} }
Consensus Matrix: A Role-Specialized Multi-Agent Framework for Structured Collaborative Decision-Making in Agentic Visual Media Workflows-
[pdf]
[bibtex]@InProceedings{Zhang_2026_CVPR, author = {Zhang, Bingli and Wang, Xinyu and Kao, Hsiang and Zhang, Guozhong and Gao, Chenkai and Wang, Yifan and Da, Zhengda and Tian, Zhen and Lyu, Ning and Chen, Kaijie}, title = {Consensus Matrix: A Role-Specialized Multi-Agent Framework for Structured Collaborative Decision-Making in Agentic Visual Media Workflows}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {4613-4622} }
SciTextures: Collecting and Connecting Visual Patterns, Models, and Code Across Science and Art-
[pdf]
[arXiv]
[bibtex]@InProceedings{Eppel_2026_CVPR, author = {Eppel, Sagi and Strugatski, Alona}, title = {SciTextures: Collecting and Connecting Visual Patterns, Models, and Code Across Science and Art}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {4530-4539} }
MAP-VD: Cross Match-Guided Video Diffusion for AM Anomaly Detection-
[pdf]
[bibtex]@InProceedings{Paul_2026_CVPR, author = {Paul, Sosmita and Roy, Krishna}, title = {MAP-VD: Cross Match-Guided Video Diffusion for AM Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {4549-4558} }
Banana100: Breaking NR-IQA Metrics by 100 Iterative Image Replications with Nano Banana Pro-
[pdf]
[arXiv]
[bibtex]@InProceedings{Tang_2026_CVPR, author = {Tang, Kenan and Arunshankar, Praveen and Hua, Andong and Yang, Anthony and Qin, Yao}, title = {Banana100: Breaking NR-IQA Metrics by 100 Iterative Image Replications with Nano Banana Pro}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {4591-4601} }
StoryNodes: Human-AI Co-Creation for Multimodal Media Generation Using an Agentic Node-Based Interface-
[pdf]
[supp]
[bibtex]@InProceedings{Kyaw_2026_CVPR, author = {Kyaw, Alexander Htet and Sivalingam, Lenin Ravindranath}, title = {StoryNodes: Human-AI Co-Creation for Multimodal Media Generation Using an Agentic Node-Based Interface}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {4540-4548} }

