ICCV 2025 Open Access Repository

The 1st International Workshop and Challenge on Disentangled Representation Learning for Controllable Generation

DiViD: Disentangled Video Diffusion for Static-Dynamic Factorization: Marzieh Gheisari,

Auguste Genovesio; [pdf] [arXiv]
[bibtex]
@InProceedings{Gheisari_2025_ICCV, author = {Gheisari, Marzieh and Genovesio, Auguste}, title = {DiViD: Disentangled Video Diffusion for Static-Dynamic Factorization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {341-350} }
Textual Semantics Matters: Unsupervised Representation Disentanglement in Realistic Scenarios with Language Inductive Bias: Junhao Geng,

Lexiang Lv,

Jianxin Lin; [pdf] [supp]
[bibtex]
@InProceedings{Geng_2025_ICCV, author = {Geng, Junhao and Lv, Lexiang and Lin, Jianxin}, title = {Textual Semantics Matters: Unsupervised Representation Disentanglement in Realistic Scenarios with Language Inductive Bias}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {361-370} }
Why Compress What You Can Generate? When GPT-4o Generation Ushers in Image Compression Fields: Yixin Gao,

Xiaohan Pan,

Xin Li,

Zhibo Chen; [pdf] [arXiv]
[bibtex]
@InProceedings{Gao_2025_ICCV, author = {Gao, Yixin and Pan, Xiaohan and Li, Xin and Chen, Zhibo}, title = {Why Compress What You Can Generate? When GPT-4o Generation Ushers in Image Compression Fields}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {371-381} }
Controllable Generation with Disentangled Representative Learning of Multiple Perspectives in Autonomous Driving: Haoran Jin; [pdf]
[bibtex]
@InProceedings{Jin_2025_ICCV, author = {Jin, Haoran}, title = {Controllable Generation with Disentangled Representative Learning of Multiple Perspectives in Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {388-395} }
A Guided Fine-tuning Framework for Diffusion Models with Disentangled Semantic Priors for Multi-Factor Image Editing: Baorui Peng,

Zhongming Chen; [pdf]
[bibtex]
@InProceedings{Peng_2025_ICCV, author = {Peng, Baorui and Chen, Zhongming}, title = {A Guided Fine-tuning Framework for Diffusion Models with Disentangled Semantic Priors for Multi-Factor Image Editing}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {382-387} }
FusionGen: Feature Fusion-Based Few-Shot EEG Data Generation: Yuheng Chen,

Dingkun Liu,

Xinyao Yang,

Xinping Xu,

Baicheng Chen,

Dongrui Wu; [pdf] [arXiv]
[bibtex]
@InProceedings{Chen_2025_ICCV, author = {Chen, Yuheng and Liu, Dingkun and Yang, Xinyao and Xu, Xinping and Chen, Baicheng and Wu, Dongrui}, title = {FusionGen: Feature Fusion-Based Few-Shot EEG Data Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {351-360} }