Publications

Research in AIGC and Image Restoration

My research focuses on AIGC and image restoration:

(1) Advancing AIGC (AI-Generated Content) technology through various generative paradigms (e.g., Diffusion Models, Auto-Regressive Models, VAR) for intelligent image generation;

(2) Developing robust and generalizable solutions for real-world image restoration, particularly in adverse conditions;

(3) Exploring multimodal large language models (MLLM) for intelligent visual application.

Diffusion Models AIGC MLLM Image Generation Real-world Image Restoration

🏆

CVPR/ICCV/ECCV/NeurIPS

📚

AAAI/IJCAI/ACM MM/MICCAI

🔬

Other Conferences

📄 Selected Papers

* - Equal Contribution ^♤ - Project Lead ^✉️ - Corresponding Author

2025

🔥🔥🔥 PosterCraft: Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework

Unified Framework Aesthetic Poster Generation

Sixiang Chen*, Jianyu Lai*, Jialin Gao*, Tian Ye, Haoyu Chen, Hengyu Shi, Shitong Shao, Yunlong Lin, Song Fei, Zhaohu Xing, Yeying Jin, Junfeng Luo, Xiaoming Wei, Lei Zhu^✉️.

arXiv, 2025

Paper GitHub Project Website HF Demo HF Paper Video Presentation Paper Interpretation

Watch Demo Video

GenHaze: Pioneering Controllable One-Step Realistic Haze Generation for Real-World Dehazing

Generative Model for Image Restoration Real-world Generalization, Plug and Play

Sixiang Chen*, Tian Ye, Yunlong Lin, Yeying Jin, Yijun Yang, Haoyu Chen, Jianyu Lai, Song Fei, Zhaohu Xing, Fugee Tsung, Lei Zhu^✉️.

International Conference on Computer Vision (ICCV), 2025

Paper GitHub

An Empirical Study of GPT-4o Image Generation Capabilities

Empirical Evaluation for GPT-4o Comprehensive Analysis

Sixiang Chen*, Jinbin Bai*, Zhuoran Zhao*, Tian Ye*, Qingyu Shi, Donghao Zhou, Wenhao Chai, Xin Lin, Jianzong Wu, Chao Tang, Shilin Xu, Tao Zhang, Haobo Yuan, Yikang Zhou, Wei Chow, Linfeng Li, Xiangtai Li^✉️, Lei Zhu^✉️, Lu Qi^✉️.

arXiv, 2025

Paper Code

SnowMaster: Comprehensive Real-world Image Desnowing via MLLM with Multi-Model Feedback Optimization

MLLM for Image Restoration Multi-Model Feedback Optimization

Jianyu Lai*, Sixiang Chen*^♤, Yunlong Lin, Tian Ye, Yun Liu, Song Fei, Zhaohu Xing, Hongtao Wu, Weiming Wang, and Lei Zhu^✉️.

Computer Vision and Pattern Recognition (CVPR), 2025

Paper Code Project

JarvisIR: Elevating Autonomous Driving Perception with Intelligent Image Restoration

MLLM for Image Restoration Intelligent Agent, RL

Yunlong Lin*, Zixu Lin*, Haoyu Chen*, Panwang Pan*, Chenxin Li, Sixiang Chen, Kairun Wen, Yeying Jin, Wenbo Li, Xinghao Ding^✉️.

Computer Vision and Pattern Recognition (CVPR), 2025

Paper Code Project

Detect Any Mirrors: Boosting Learning Reliability on Large-Scale Unlabeled Data with an Iterative Data Engine

MLLM for Mirror Detection Iterative Data Engine

Zhaohu Xing, Lihao Liu, Yijun Yang, Hongqiu Wang, Tian Ye, Sixiang Chen, Wenxue Li, Guang Liu, and Lei Zhu^✉️.

Computer Vision and Pattern Recognition (CVPR), 2025

Paper Code Project

PromptHaze: Prompting Real-world Dehazing via Depth Anything Model

Prompt Learning for Image Restoration Real-world Generalization

Tian Ye, Sixiang Chen, Haoyu Chen, Wenhao Chai, Jingjing Ren, Zhaohu Xing, Wenxue Li, Lei Zhu^✉️.

Conference on Artificial Intelligence (AAAI), 2025

Paper Code Project

AGLLDiff: Guiding Diffusion Models Towards Unsupervised Training-free Real-world Low-light Image Enhancement

Generative Model for Image Restoration Unsupervised Training-free

Yunlong Lin*, Tian Ye*, Sixiang Chen*, Zhenqi Fu, Yingying Wang, Wenhao Chai, Zhaohu Xing, Lei Zhu, Xinghao Ding^✉️.

Conference on Artificial Intelligence (AAAI), 2025

Paper Code Project

2024

RestoreAgent: Autonomous Image Restoration Agent via Multimodal Large Language Models

MLLM for Image Restoration Intelligent Agent

Haoyu Chen, Wenbo Li, Jinjin Gu, Jingjing Ren, Sixiang Chen, Tian Ye, Renjing Pei, Kaiwen Zhou, Fenglong Song, Lei Zhu^✉️.

Neural Information Processing Systems (NeurIPS), 2024

Paper Code Project

Teaching Tailored to Talent: Adverse Weather Restoration via Prompt Pool and Depth-Anything Constraint

Generative Model for Image Restoration Real-world Generalization, Prompt Learning

Sixiang Chen, Tian Ye, Kai Zhang, Zhaohu Xing, Yunlong Lin, Lei Zhu^✉️.

European Conference on Computer Vision (ECCV), 2024

Paper Code Project

Semi-Supervised Video Desnowing Network via Temporal Decoupling Experts and Distribution-Driven Contrastive Regularization

MoE for Video Restoration Semi-Supervised Learning, New Benchmark

Hongtao Wu, Yijun Yang, Angelica Aviles-Rivero, Jingjing Ren, Sixiang Chen, Haoyu Chen, Lei Zhu^✉️.

European Conference on Computer Vision (ECCV), 2024

Paper Code

Cross-conditioned Diffusion Model for medical image-to-image translation

Generative Model for Medical Image Translation Conditional Generation

Zhaohu Xing, Sicheng Yang, Sixiang Chen, Tian Ye, Lei Zhu^✉️.

Medical Image Computing and Computer Assisted Intervention (MICCAI), 2024

Paper Code

Learning Diffusion Texture Priors for Image Restoration

Generative Model for Image Restoration Diffusion Model for Textural Learning

Tian Ye, Sixiang Chen, Wenhao Chai, Zhaohu Xing, Jing Qin, Ge Lin, Lei Zhu^✉️.

Computer Vision and Pattern Recognition (CVPR Highlight), 2024

Paper Code

2023

Sparse Sampling Transformer with Uncertainty-Driven Ranking for Unified Removal of Raindrops and Rain Streaks

Uncertainty for Image Restoration Uncertainty-Driven Consideration, Sparse Sampling

Sixiang Chen*, Tian Ye*, Jinbin Bai, Jun Shi, Erkang Chen, Lei Zhu^✉️.

International Conference on Computer Vision (ICCV), 2023

Paper Code Project

Adverse Weather Removal with Codebook Priors

Tian Ye*, Sixiang Chen*, Jinbin Bai, Jun Shi, Chenghao Xue, Jingjia Jiang, Junjie Yin, Erkang Chen, Yun Liu^✉️.

International Conference on Computer Vision (ICCV), 2023

Paper Code

Uncertainty-Driven Dynamic Degradation Perceiving and Background Modeling for Efficient Single Image Desnowing

Uncertainty for Image Restoration Novel Perspective for Desnowing

Sixiang Chen*, Tian Ye*, Chenghao Xue*, Haoyu Chen, Yun Liu, Erkang Chen, Lei Zhu^✉️.

ACM Multimedia (ACM MM), 2023

Paper Code

CPLFormer: Cross-scale Prototype Learning Transformer for Image Snow Removal

Prototype Learning for Image Restoration Cross-scale Prototype

Sixiang Chen*, Tian Ye*, Yun Liu, Jinbin Bai, Haoyu Chen, Yunlong Lin, Jun Shi, Erkang Chen^✉️.

ACM Multimedia (ACM MM), 2023

Paper Code

Sequential Affinity Learning for Video Restoration

Sequential Affinity for Video Restoration Sequential Affinity Learning

Tian Ye*, Sixiang Chen*, Yun Liu^✉️, Wenhao Chai, Jinbin Bai, Wenbin Zou, Yunchen Zhang, jiang mingchao, Erkang Chen, Chenghao Xue.

ACM Multimedia (ACM MM), 2023

Paper Code

NightHazeFormer: Single Nighttime Haze Removal Using Prior Query Transformer

Prior Query Transformer for Image Restoration New Benchmark

Yun Liu, Zhongsheng Yan, Sixiang Chen^✉️, Tian Ye^✉️, Wenqi Ren, Erkang Chen.

ACM Multimedia (ACM MM), 2023

Paper Code

Five A+ Network: You Only Need 9K Parameters for Underwater Image Enhancement

Efficient Image Restoration Only 9K Parameters

Jingxia Jiang*, Tian Ye*, Jinbin Bai*, Sixiang Chen, Wenhao Chai, Jun Shi, Yun Liu, Erkang Chen^✉️.

British Machine Vision Conference (BMVC), 2023

Paper Code

DEHRFormer: Real-time Transformer for Depth Estimation and Haze Removal from Varicolored Haze Scenes

Vision Transformer for Image Restoration Real-time, New Benchmark for Vari-color Haze

Sixiang Chen*, Tian Ye*, Jun Shi, Yun Liu, JingXia Jiang, Erkang Chen, Peng Chen^✉️.

International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023

Paper Code

MSP-Former: Multi-Scale Projection Transformer for Single Image Desnowing

Vision Transformer for Image Restoration Multi-Scale Projection, First Vision Transformer for Desnowing

Sixiang Chen*, Tian Ye*, Yun Liu, Taodong Liao, Jingxia Jiang, Erkang Chen, Peng Chen^✉️.

International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023

Paper Code

2022

SnowFormer: Context Interaction Transformer with Scale-awareness for Single Image Desnowing

Vision Transformer for Image Restoration SOTA Desnowing, Significant Performance Improvement

Sixiang Chen*, Tian Ye*, Yun Liu, Erkang Chen^✉️.

Arxiv (Under review), 2022

Paper Code

Towards Real-time High-Definition Image Snow Removal: Efficient Pyramid Network with Asymmetrical Encoder-decoder Architecture

Efficient Image Restoration Real-time, High-Definition

Tian Ye*, Sixiang Chen*, Yun Liu, Yi Ye, Erkang Chen^✉️.

Asian Conference on Computer Vision (ACCV), 2022

Paper Code

Dual-former: Hybrid Self-attention Transformer for Efficient Image Restoration

Vision Transformer for Image Restoration Latent-based Self-attention

Sixiang Chen, Tian Ye, Yun Liu, Erkang Chen^✉️.

Digital Signal Processing, 2024

Paper Code

Perceiving and Modeling Density for Image Dehazing

Novel Attention for Image Restoration New Perspective for Image Dehazing

Tian Ye*, Mingchao Jiang*, Yunchen Zhang*, Liang Chen, Yun Liu, Sixiang Chen, Erkang Chen^✉️.

European Conference on Computer Vision (ECCV Oral), 2022

Paper Code

Underwater Light Field Retention: Neural Rendering for Underwater Imaging

Neural Rendering for Image Generation Light Field Retention, New Benchmark

Tian Ye*, Sixiang Chen*, Yun Liu, Yi Ye, Erkang Chen^✉️, Yuche Li.

Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), 2022

Paper Code