Zongsheng Yue

Zongsheng Yue (岳宗胜)

Full Professor

School of Mathematics and Statistics, Xi'an Jiaotong University, Xi'an, China

Email: zsyzam@gmail.com; zsyue@xjtu.edu.cn

[Google Scholar] [Github] [ResearchGate]

2025年学硕名额还有1个，2026年学硕、博士名额均有2个，欢迎数学基础好、编程能力强的同学加入我们组，请提前发邮件联系。

Biography

I am currently a full professor at School of Mathematics and Statistics, Xi'an Jiaotong University. Previously, I was a postdoctoral researcher at MMLab@NTU of Nanyang Technological University and The University of Hong Kong, working with Prof. Chen Change Loy and Prof. Kenneth K.Y. Wong. I received my Ph.D. degree from Xi'an Jiaotong University under the supervision of Prof. Deyu Meng in 2021.

Research Interest

My work focus on the noise modeling method in machine learning and the image restoration problem in low-level computer vision. Specifically, I mainly investigate how to design more efficient and interpretable image restoration models by incorporating the more robust noise modeling technologies and the classical Bayesian methods. Recently, I focus on the following research topics:

Diffusion model and its application
Noise modeling
Blind image restoration
Bayesian methods in image processing

News

2025.05.16: Our work MOWA has been accepted by TPAMI 2025.
2025.02.27: Our work InvSR has been accepted by CVPR 2025.
2025.02.05: Our work Noise-DA has been accepted by ICLR 2025.
2024.12.31: We have released a new image super-resolution work InvSR.
2024.9.13: The exteneded journal version of ResShift has been accepted by TPAMI.
2024.7.19: DifFace has been accepted by TPAMI.
2024.6.29: StableSR has been accepted by IJCV.
2024.6.02: Our recent work MOWA, a general image warping framework, is available on arXiv.
2024.6.02: We have exteneded ResShift to a journal paper, capable of handling general restoration tasks. Welcome to follow.
2024.2.05: Our work VIRNet for blind imaage restoration has been accepted by TPAMI 2024.

Research Experiences

	MMLab@NTU, Nanyang Technological University, Singapore Research Fellow, Apr. 2022 ~ present Supervisor: Prof. Chen Change Loy
	Computer Vision Group, The University of Hong Kong, Hong Kong Postdoctoral Researcher, Sep. 2021 ~ Mar. 2022 Supervisor: Assoc Prof. Kenneth K.Y. Wong
	DAMO Academy, Alibaba Group, Shenzhen, China Research Intern, Mar. 2021 ~ Sep. 2021 Supervisor: Prof. Lei Zhang
	Department of Computing, The Hong Kong Polytechnic University, Hong Kong Research Assistant, Oct. 2018 ~ Jun. 2019 Supervisor: Prof. Lei Zhang
	Institute of Future Cities, The Chinese University of Hong Kong, Hong Kong Research Assistant, Feb. 2017 ~ Sep. 2017 Supervisor: Prof. Leung Yee

Preprint

Degradation-Guided One-Step Image Super-Resolution with Diffusion Priors

Aiping Zhang, Zongsheng Yue, Renjing Pei, Weiqi Ren, Xiaochun Cao
arXiv:2409.17058, 2024
[Paper] [Code]

Selected Publications [Full List]

	MOWA: Multiple-in-One Image Warping Model Kang Liao, Zongsheng Yue, Zhonghua Wu, Chen Change Loy IEEE Transactions on Pattern Analysis and Machine Intelligence(TPAMI), 2025. [Paper] [Code] [Project]
	Arbitrary-steps Image Super-resolution via Diffusion Inversion Zongsheng Yue, Kang Liao, Chen Change Loy IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2025. [Paper] [Code] [Hugging Face Demo] [Replicate Demo]
	Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restoration Kang Liao, Zongsheng Yue, Zhouxia Wang, Chen Change Loy International Conference on Learning Representations(ICLR), 2025. [Paper] [Code] [Project]
	Efficient Diffusion Model for Image Restoration by Residual Shifting Zongsheng Yue, Jianyi Wang, Chen Change Loy IEEE Transactions on Pattern Analysis and Machine Intelligence(TPAMI), 2025. [Paper] [Code] [Project]
	Blind Image Deconvolution by Generative-based Kernel Prior and Initializer via Latent Encoding Jiangtao Zhang, Zongsheng Yue, Hui Wang, Qian Zhao, Deyu Meng European Conference on Computer Vision (ECCV), 2024. [Paper] [Code]
	DifFace: Blind Face Restoration via Diffused Error Contraction Zongsheng Yue, Chen Change Loy IEEE Transactions on Pattern Analysis and Machine Intelligence(TPAMI), 2024. [Paper] [Code] [Demo]
	Exploiting Diffusion Prior for Real-World Image Super-resolution Jianyi Wang, Zongsheng Yue, Shangchen Zhou, Kelvin C.K. Chan, Chen Change Loy International Journal of Computer Vision(IJCV), 2024. [Paper] [Code] [Project]
	Variational Image Restoration Network Zongsheng Yue, Hongwei Yong, Qian Zhao, Lei Zhang, Deyu Meng, Kwan-Yee K. Wong IEEE Transactions on Pattern Analysis and Machine Intelligence(TPAMI), 2024. [Paper] [Code]
	ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting Zongsheng Yue, Jianyi Wang, Chen Change Loy Neural Information Processing Systems(NeurIPS), *Spotlight*, 2023. [Paper] [Code] [Project]
	Blind Image Super-resolution with Elaborate Degradation Modeling on Noise and Kernel Zongsheng Yue, Qian Zhao, Jianwen Xie, Lei Zhang, Deyu Meng, K.-Y. K. Wong IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2022. [Paper] [Code]
	Semi-Supervised Video Deraining with Dynamical Rain Generator Zongsheng Yue, Jianwen Xie, Qian Zhao, Deyu Meng IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2021. [Paper] [Code] [Supp]
	From Rain Generation to Rain Removal Hong Wang, Zongsheng Yue, Qi Xie, Qian Zhao, Yefeng Zheng, Deyu Meng (Equal Contribution) IEEE International Conference on Computer Vision and Pattern Recognition (CVPR*), 2021. [Paper] [Code]
	Dual Adversarial Network: Toward Real-World Noise Removal and Noise Generation Zongsheng Yue, Qian Zhao, Lei Zhang, Deyu Meng European Conference on Computer Vision (ECCV), 2020. [Paper] [Code] [Supp]
	Variational Denoising Network: Toward Blind Noise Modeling and Removal Zongsheng Yue, Hongwei Yong, Qian Zhao, Lei Zhang, Deyu Meng Neural Information Processing Systems(NeurIPS), 2019. [Paper] [Code] [Supp]
	Robust Multiview Subspace Learning With Nonindependently and Nonidentically Distributed Complex Noise Zongsheng Yue, Hongwei Yong, Deyu Meng, Qian Zhao, Yee Leung, Lei Zhang IEEE International Conference on Neural Networks and Learning Systems (TNNLS), 2019. [Paper] [Code] [Supp]