Xin Li

Postdoc Research Fellow
University of Science and Technology of China
Email: xin.li@ustc.edu.cn

Currently, I work in USTC as a Postdoc Research Fellow and work with Zhibo Chen. I have obtained my Ph.D. in MOE-Microsoft Key Laboratory of Multimedia Computing and Communication, University of Science and Technology of China (USTC), supervised by Zhibo Chen. Prior to that, I obtained my B.S. degree in Department of Electronic Engineering and Information Science from the University of Science and Technology of China (USTC). From Apr. 2021 to Apr. 2022, I was a research intern at Intelligence Media Group of MSRA under the supervision of Cuiling Lan and Wenjun Zeng. I have been a visiting Ph.D. of Learning and Vision (LV) Lab at the National University of Singapore under the supervision of Xinchao Wang. My research interests mainly focus on image/video processing, transfer learning of foundational models, generation, and agent.

[Workshop/Tutorial/Competitions]
The Application of Generative AI and Intelligent Agents in Low-level Vision @ AAAI 2026

Short-form UGC Image Super-resolution (4x) @ CVPR 2025 NTIRE Workshop

Efficient Short-form UGC Video Quality Assessment @ CVPR 2025 NTIRE Workshop

The First Challenge on Day and Night Raindrop Removal for Dual-Focused Images @ CVPR 2025 NTIRE Workshop

Visual Quality Assessment Workshop and Competition (VQualA) @ ICCV 2025

[Welcome to join us] We are seeking self-motivated students to join our USTC Intelligent Media Computing Lab for internships, masters, and in-school Ph.D. transfers. We warmly welcome like-minded talents to join us in pioneering the frontiers of intelligent media computing. Our lab is devoted to Generative AI, Visual Compression, Quality Assessment, AI Agents, AI for Science, and Embodied AI. If you are interested, please send email to xin.li@ustc.edu.cn and cc chenzhibo@ustc.edu.cn

News

[11/2025]	Three papers are accepted by AAAI2026.
[09/2025]	I will host a tutorial on AAAI2026: "The application of generative AI and intelligent agents in low-level vision", and one paper is accepted by NeurIPS2025.
[08/2025]	Awarded by Outstanding Doctoral Dissertation of the Chinese Academy of Sciences (中国科学院优秀博士学位论文).
[08/2025]	One paper was accepted by IJCV.
[05/2025]	Invited as the Area Chairs for BMVC 2025.
[05/2025]	I will organize a tutorial related to low-level image processing in IEEE VCIP2025.
[5/2025]	One paper was accepted by ICML 2025.
[4/2025]	Invited as the Area Chairs for NeurIPS 2025.
[4/2025]	Selected for Mozi Distinguished Young Scholar Special Allowance Program (First-Class)
[3/2025]	Invited as the Area Chairs for ACM MultiMedia 2025.
[2/2025]	Four papers were accepted by CVPR2025(1), IEEE ISCAS (2), and JUSTC(1) totally.
[2/2025]	I am organizing The First Challenge on Day and Night Raindrop Removal for Dual-Focused Images in the 10th NTIRE Workshop at CVPR 2025.
[1/2025]	I am organizing the Short-form UGC Video Quality Assessment and Enhancement Challenge (Two Tracks: VQA and Image SR) (Offical Repo) in the 10th NTIRE Workshop at CVPR 2025.
[12/2024]	One paper accepted by AAAI 2025.
[08/2024]	One paper accepted by IEEE TMM and invited as the reviewer for ICLR2025.
[07/2024]	One paper accepted by IEEE TIP.
[07/2024]	Three papers accepted by ECCV 2024.
[06/2024]	Invited as the reviewer for AAAI2024.
[06/2024]	One tutorial "Low-level Image Processing with Diffusion Models" is accepted and will be hosted in IEEE VCIP2024.
[05/2024]	Invited as the reviewer for NeurIPS2024.
[04/2024]	Won the Basic Research Project for Young Students of National Natural Science Foundation of China (Doctoral candidate), PI (首届国家自然科学基金青年学生基础研究项目-博士研究生)
[03/2024]	Won two first prize in CVPR NTIRE2024 Blind Compressed Image Enhancement Challenge and CVPR NTIRE2024 Quality Assessment for AI-Generated Content (AIGC) Challenge.
[03/2024]	Won first prize in the 6th CLIC2022 (Video Perceptual Track) of DCC.
[02/2024]	Three papers accepted in CVPR2024.
[02/2024]	I am organizing the Short-form UGC Video Quality Assessment Challenge jointly with co-organizing the 9th NTIRE Workshop at CVPR 2024.
[01/2024]	Invited as the reviewer for ECCV2024.
[12/2023]	Invited as the reviewer for ICML2024.
[12/2023]	Awarded IEEE VCIP Best Paper Award.
[09/2023]	One paper accepted by IEEE TMM.
[09/2023]	One paper accepted by NeurIPS2023.
[02/2023]	One paper accepted by CVPR2023.
[11/2022]	One paper accepted by AAAI2023 (Oral).
[10/2022]	Awarded ByteDance Scholarship 2022 (Ten Students in China).
[08/2022]	One paper accepted by ECCV Workshop 2022.
[07/2022]	Awarded China Scholarship Council (CSC) scholarship.
[06/2022]	One paper accepted by IEEE TMM.
[06/2022]	One paper accepted by MICCAI 2022.
[04/2022]	First prize in 5th CVPR CLIC 2022 in Perceptual Metric Track.
[11/2021]	One paper accepted by IEEE TIP 2021.
[10/2021]	Awarded China National Scholarship.
[09/2021]	One paper accepted by IEEE TCSVT 2021.
[06/2021]	One paper accepted by IEEE TIP 2021.
[11/2020]	One papers accepted by AAAI 2021.
[08/2020]	One paper accepted by ECCV Workshop 2020.
[06/2020]	Two papers accepted by ECCV 2020.
[03/2020]	One paper accepted by CVPR Workshop 2020.
[01/2020]	The third prize in the 2019 4K+HDR National Artificial Intelligence Competition. (3/1000+).

Selected Publications

(^† Equal Contribution, ^✉ Corresponding Author)

IJCV’25

Diffusion Models for Image Restoration and Enhancement: A Comprehensive Survey

Xin Li , Yulin Ren, Xin Jin, Cuiling Lan, Xingrui Wang, Wenjun Zeng, Xinchao Wang and Zhibo Chen

IJCV , 2025

PDF Code
IEEE TIP’24

Semantic-aware Message Broadcasting for Efficient Unsupervised Domain Adaptation

Xin Li , Cuiling Lan, Guoqiang Wei, and Zhibo Chen

IEEE Transactions on Image Processing (TIP) , 2024

arXiv Code
IEEE TMM’24

StyleAM: Perception-Oriented Unsupervised Domain Adaption for No-reference Image Quality Assessment

Yiting Lu, Xin Li^✉, Jianzhao Liu, and Zhibo Chen^✉

IEEE Transactions on MultiMedia (TMM) , 2024

arXiv Code
IEEE TMM’23

FreqAlign: Excavating Perception-oriented Transferability for Blind Image Quality Assessment from A Frequency Perspective

Xin Li , Yiting Lu and Zhibo Chen

IEEE Transactions on MultiMedia (TMM) , 2023

PDF
IEEE TIP’21

Task-driven Semantic Coding via Reinforcement Learning

Xin Li , Jun Shi and Zhibo Chen

IEEE Transactions on Image Processing (TIP) , 2021

PDF Code
JUSTC’25

A Close Look at Few-shot Real Image Super-resolution from the Distortion Relation Perspective

Xin Li^✉, Xin Jin, Jun Fu, Xiaoyuan Yu, Bei Tong, Zhibo Chen

JUSTC, 2025 (Cover Paper)

PDF arXiv
AAAI’26

Test-Time Preference Optimization for Image Restoration

Bingchen Li, Xin Li^✉, Jiaqi Xu, Jiaming Guo, Wenbo Li, Renjing Pei, Zhibo Chen

AAAI Conference on Artificial Intelligence, 2026

PDF Code
AAAI’26

Sonic4D: Spatial Audio Generation for Immersive 4D Scene Exploration

Siyi Xie, Hanxin Zhu, Tianyu He, Xin Li^✉, Zhibo Chen^✉

AAAI Conference on Artificial Intelligence, 2026

PDF Project
NeurIPS’25

Diff-ICMH: Harmonizing Machine and Human Vision in Image Compression with Generative Prior

Ruoyu Feng, Yunpeng Qi, Jinming Liu, Yixin Gao, Xin Li^✉, Xin Jin, Zhibo Chen

Advances in Neural Information Processing Systems (NeurIPS), 2025

PDF Code
CVPR’25

RaSS: Improving Denoising Diffusion Samplers with Reinforced Active Sampling Scheduler

Xin Ding, Lei Yu, Xin Li^✉, Zhijun Tu, Hanting Chen, Jie Hu, Zhibo Chen

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

PDF Code
CVPRW’25

NTIRE 2025 challenge on day and night raindrop removal for dual-focused images: Methods and results

Xin Li, Yeying Jin, Xin Jin, Zongwei Wu, Bingchen Li, Yufei Wang, Wenhan Yang, Yu Li, Zhibo Chen, Bihan Wen, Robby T. Tan, Radu Timofte, et al.

CVPR Workshops (NTIRE), 2025

PDF Project
CVPRW’25

NTIRE 2025 challenge on short-form ugc video quality assessment and enhancement: Methods and results

Xin Li, Kun Yuan, Bingchen Li, Fengbin Guan, Yizhen Shao, Zihao Yu, Xijun Wang, Yiting Lu, Wei Luo, Suhang Yao, Ming Sun, Chao Zhou, Zhibo Chen, Radu Timofte, et al.

CVPR Workshops (NTIRE), 2025

PDF Code
CVPRW’25

NTIRE 2025 challenge on short-form ugc video quality assessment and enhancement: Kwaisr dataset and study

Xin Li^✉, Xijun Wang, Bingchen Li, Kun Yuan, Yizhen Shao, Suhang Yao, Ming Sun, Chao Zhou, Radu Timofte, Zhibo Chen

CVPR Workshops (NTIRE), 2025

PDF Dataset
ICML’25

QMamba: On First Exploration of Vision Mamba for Image Quality Assessment

Fengbin Guan, Xin Li^✉, Zihao Yu, Yiting Lu, and Zhibo Chen

ICML , 2025

arXiv
AAAI’25

TIV-Diffusion: Towards Object-Centric Movement for Text-driven Image to Video Generation

Xingrui Wang, Xin Li^✉, Yaosi Hu, Hanxin Zhu, Chen Hou, Cuiling Lan and Zhibo Chen^✉

AAAI , 2025

arXiv
ECCV’24

UCIP: A Universal Framework for Compressed Image Super-Resolution using Dynamic Prompt

Xin Li , Bingchen Li, Yeying Jin, Cuiling Lan, Hanxin Zhu, Yulin Ren and Zhibo Chen

ECCV , 2024

PDF Project Code
ECCV’24

MoE-DiffIR: Task-customized Diffusion Priors for Universal Compressed Image Restoration

Yulin Ren , Xin Li^✉, Bingchen Li, Xingrui Wang, Mengxi Guo, Shijie Zhao, Li Zhang and Zhibo Chen^✉

ECCV , 2024

PDF Project Code
CVPR’24

SeD: Semantic-Aware Discriminator for Image Super-Resolution

Bingchen Li^† , Xin Li^†(Equal Contribution), Hanxin Zhu, Yeying Jin, Ruoyu Feng, Zhizheng Zhang and Zhibo Chen

CVPR , 2024

PDF Code
CVPR’24

KVQ: Kwai Video Quality Assessment for Short-form Videos

Yiting Lu^† , Xin Li^†, Yajing Pei^†, Kun Yuan, Qizhi Xie, Yunpeng Qu, Ming Sun, Chao Zhou and Zhibo Chen

CVPR , 2024

PDF PROJECT Code
NTIRE’24

NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Results

Xin Li , Kun Yuan, Yajing Pei, Yiting Lu, Ming Sun, Chao Zhou, Zhibo Chen and Radu Timofte

CVPR Workshop, Challenge Report for KVQ , 2024

PDF Project Code
ECCV’24

MoE-DiffIR: Task-customized Diffusion Priors for Universal Compressed Image Restoration

Yulin Ren , Xin Li^✉, Bingchen Li, Xingrui Wang, Mengxi Guo, Shijie Zhao, Li Zhang and Zhibo Chen^✉

ECCV , 2024

PDF Project Code
NeurIPS’23

GraphAdapter: Tuning Vision-Language Models With Dual Knowledge Graph

Xin Li , Dongze Lian, Zhihe Lu, Jiawang Bai, Zhibo Chen and Xinchao Wang

NeurIPS , 2023

PDF Code
CVPR’23

Learning Distortion Invariant Representation for Image Restoration from A Causality Perspective

Xin Li , Bingchen Li, Xin Jin, Cuiling Lan, and Zhibo Chen

CVPR , 2023

PDF Code
AAAI’21

Learning Omni-Frequency Region-adaptive Representations for Real Image Super-Resolution

Xin Li , Xin Jin, Tao Yu, Simeng Sun, Yingxue Pang, Zhizheng Zhang, and Zhibo Chen

AAAI , 2021

PDF
ECCV’20

Learning disentangled feature representation for hybrid-distorted image restoration

Xin Li , Xin Jin, Jianxin Lin, Sen Liu, Yaojun Wu, Tao Yu, Wei Zhou and Zhibo Chen

ECCV , 2020

PDF
CVPRW’20

Multi-scale grouped dense network for VVC intra coding

Xin Li , Simeng Sun, Zhizheng Zhang and Zhibo Chen

CVPR Workshop , 2020

PDF