Yixuan Zhu
I am a second-year Ph.D. student at Tsinghua University, advised by Prof. Jie Zhou , Prof. Jiwen Lu and Prof. Yansong Tang. Prior to my doctoral journey, I received my B.S. degree in Electronic Engineering with honours from Tsinghua University in 2022. My academic pursuits revolve around the dynamic intersection of visual generation and human digitization. This compelling research area fuels my passion for exploring innovative solutions and contributing to the cutting-edge advancements in the field.
Email / Github
|
|
News
2025-02: A papers on multimodal video editing, accepted by CVPR 2025. Papers and codes coming soon!
2025-01: A papers on AIGC image enhancement, accepted by ICLR 2025. Papers and codes coming soon!
2024-04: We are happy that our work, FlowIE, has been nominated as an oral in CVPR 2024!
2024-02: Two papers on AIGC image enhancement and 3D human recovery, accepted by CVPR 2024. Papers and codes coming soon!
2024-02: A paper on face swapping, accepted by IEEE Transactions on Multimedia.
|
Recent Selected Publications [ Full List ]
(*Equal Contribution, #Corresponding Author)
|
|
FADE: Frequency-Aware Diffusion Model Factorization for Video Editing
Yixuan Zhu, Haolin Wang, Shilin Ma, Wenliang Zhao, Yansong Tang, Lei Chen#, Jie Zhou
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
[Coming soon]
We introduce FADE—a training-free yet highly effective video editing approach that fully leverages the inherent priors from pre-trained video diffusion models via frequency-aware factorization.
|
|
InstaRevive: One-Step Image Enhancement via Dynamic Score Matching
Yixuan Zhu*, Haolin Wang*, Ao Li, Wenliang Zhao, Yansong Tang, Jingxuan Niu, Lei Chen#, Jie Zhou, Jiwen Lu
The Thirteenth International Conference on Learning Representations (ICLR), 2025
[Coming soon]
We propose InstaRevive, a straightforward yet powerful image enhancement framework that employs score-based diffusion distillation to harness potent generative capability and minimize the sampling steps.
|
|
FlowIE: Efficient Image Enhancement via Rectified Flow
Yixuan Zhu*, Wenliang Zhao*, Ao Li, Yansong Tang#, Jie Zhou, Jiwen Lu
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR Oral), 2024
[Paper]
[Code]
We proposed a unified framework for various efficient image enhancement tasks with generative diffusion priors.
|
|
DPMesh: Exploiting Diffusion Prior for Occluded Human Mesh Recovery
Yixuan Zhu*, Ao Li*, Yansong Tang#, Wenliang Zhao, Jie Zhou, Jiwen Lu
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
[Paper]
[Code]
[Project Page]
We propose a new method to exploit diffusion priors for human mesh recovery (HMR) in occlusion and crowded scenarios.
|
|