Publications

Note: # = Equal Contribution, * = Corresponding Author.

• CVPR26W CVEU

  DRA-MTransfer: Physically Realistic Video Motion Transfer with Dual-Grained Re-Adaptation

  Guoli Jia, Zhiyuan Ma, Junyao Hu, Xinwei Long, Kai Tian, Kaikai Zhao, Zhaoxiang Liu, Kai Wang, Shiguo Lian, Bowen Zhou*

  TL;DR:DRA-MTransfer leverages dual-grained re-adaptation to unlock motion priors in video diffusion models, enhancing physical realism in motion transfer while maintaining fidelity and coherence.

  

• CVPR26

  Garments2Look: A Multi-Reference Dataset for High-Fidelity Outfit-Level Virtual Try-On with Clothing and Accessories

  Junyao Hu, Zhongwei Cheng, Waikeung Wong, Xingxing Zou*

  TL;DR:Garments2Look, the first outfit-level VTON dataset with 80K pairs, 40 categories, rich annotations, tests SOTA models and reveals their limitations in layering/styling.

  

• TAFFC26

  Emotion-Director: From Emotion-Aware Image Generation to Art Design

  Guoli Jia#, Junyao Hu#, Xinwei Long, Kai Tian, Kaikai Zhao, Zhaoxiang Liu, Kai Wang, Shiguo Lian, Kaiyan Zhang, Ning Ding, Bowen Zhou*

  TL;DR:Emotion-Director combines multimodal diffusion, negative-emotion preference optimization, and collaborative prompt rewriting for emotion-aware image generation and art design.

  

• CVPR24

  ExtDM: Distribution Extrapolation Diffusion Model for Video Prediction

  Zhicheng Zhang#, Junyao Hu#, Wentao Cheng*, Danda Paudel, Jufeng Yang

  TL;DR:We present ExtDM, a new diffusion model that extrapolates video content from current frames by accurately modeling distribution shifts towards future frames.