Visual-Information Intelligent Learning LAB
Welcome to VILLA, the research group lead by Prof. Jian Zhang, affiliated to the School of Electronic and Computer Engineering, Peking University. We research on intelligent visual representation, reconstruction, and learning.

Previous Next

Current Team Members

Professor

Avatar

Jian Zhang (张健)

Associate Professor, Ph. D. Supervisor

AI-based low-level vision and computational imaging, AI-generated content (AIGC) and security

Postdoc

Avatar

Qiankun Gao (高乾坤)

3D Vision, AIGC, Continual Learning

Phd Students

Avatar

Shuzhou Yang (杨树州)

3D Reconstruction, Image Restoration, Image Enhancement

Avatar

Bin Chen (陈斌)

Image Reconstruction, Compressed Sensing, Inverse Imaging Problems

Avatar

Xuanyu Zhang (张轩宇)

Multimodal Large Language Model, AIGC Security

Avatar

Weiqi Li (李玮琦)

AIGC, 360 Image Processing, Compressed Sensing

Avatar

Qian Wang (王茜)

Image Restoration, Compressive Sensing, Computer Vision

Avatar

Yule Duan (段宇乐)

Low-Level Vision, Image Generation

Master Students

Avatar

Runyi Li (李润一)

Computer Vision, Compressed Sensing, Image Restoration

Avatar

Xuhan Sheng (盛栩涵)

Omnidirectional Image Problem, SNN

Avatar

Haijie Li (李海杰)

3D Vision-and-Language

Avatar

Guanhua Zhao (赵灌华)

Computer Vision, Deep Learning, Multimedia Coding

Avatar

Chengxiang Wen (温程翔)

Computer Vision, Deep Learning

Avatar

Yu Wang (汪玉)

Computer Vision, Deep Learning

Avatar

Zhipei Xu (徐志沛)

Image Forgery Detection and Localization

Avatar

Gehui Li (李戈辉)

Computational Photography, Image Reconstruction

Avatar

Chuhan Tong (佟楚涵)

Computer Vision, Image Restoration

Avatar

Zecheng Tang (汤泽城)

Computer Vision, Deep Learning

Avatar

Jiexuan Zhang (张杰宣)

Computer Vision, AIGC

Avatar

Jieye Fu (付迦叶)

Neural data compression & generation

Avatar

Shuyu Wang (王姝谕)

AIGC

Avatar

Xu Jiang (蒋旭)

Computer Vision, Facial Expression Recognition

Avatar

Jiayang Li (李佳阳)

Computer Vision, Image Fusion, MLLM

Avatar

Zhizhen Zhang (张志臻)

Computer Vision, Deep Learning, Image Generation

Avatar

Haokun Gong(巩昊坤)

Computer Vision, Super-Resolution, AIGC

Avatar

Yuhao Liang (梁宇昊)

Computer Vision

Avatar

Hongxiu Chen (陈虹秀)

AIGC

Avatar

Zhile Guan (关志乐)

AIGC

Alumni

2022

Jianhui Chang (常建慧)

Master 2019-2022, To Ph.D study at Peking University

Mengxi Jia (贾梦溪)

Master 2019-2022, To Ph.D study at Peking University

Zhuoyuan Wu (武卓远)

Master 2019-2022, To work at Mei Tuan

Zihong Huang (黄姿鸿)

Master 2019-2022, To work at Alibaba

Di You (由迪)

Master 2019-2022, To Ph.D study at Imperial College London

2023

Jingfen Xie (谢静芬)

Master 2020-2023, To work at ByteDance

Youmin Xu (许佑民, 转博)

Master 2020-2023, To Ph.D study at Peking University

Chong Mou (牟冲, 转博)

Master 2020-2023, To Ph.D study at Peking University

Qiankun Gao (高乾坤, 转博)

Master 2020-2023, To Ph.D study at Peking University

2024

Jiechong Song (宋皆充)

Ph.D 2019-2024, To work at China Mobile Research Institute

Zhenyu Zhang (张振宇)

Master 2019-2024, To Ph.D study at Arizona State University

Xinhua Cheng (程鑫华)

Master 2021-2024, To Ph.D study at Peking University

Jiwen Yu (余济闻)

Master 2021-2024, To Ph.D study at The University of Hong Kong

Bin Chen (陈斌, 转博)

Master 2021-2024, To Ph.D study at Peking University

Yinhuai Wang (王荫槐)

Master 2021-2024, To Ph.D study at Hong Kong University of Science and Technology

2025

Qiankun Gao (高乾坤)

Ph.D 2020-2025, To conduct postdoctoral research at Peking University

Yujie Hu (胡妤婕)

Ph.D 2020-2025, To work at Migu Shenzhen Research Institute

Yanmin Wu (吴艳敏)

Ph.D 2021-2025, To work at XPeng Inc

Youmin Xu (许佑民)

Ph.D 2020-2025, To work at Tencent

Chong Mou (牟冲)

Ph.D 2020-2025, To work at ByteDance

Weiqi Li (李玮琦, 转博)

Master 2022-2025, To Ph.D study at Peking University

Xuanyu Zhang (张轩宇, 转博)

Master 2022-2025, To Ph.D study at Peking University

Qian Wang (王茜, 转博)

Master 2022-2025, To Ph.D study at Peking University

Yu Gu (古雨)

Master 2022-2025, To work at Mei Tuan

Recent News

  • 2025/05 - 1 paper accepted to TPAMI!
  • 2025/02 - 6 papers accepted to CVPR 2025!
  • 2025/01 - 1 paper accepted to TPAMI!
  • 2025/01 - 2 papers accepted to ICLR 2025!
  • 2024/11 - 1 paper accepted to TPAMI!
  • 2024/10 - 1 paper accepted to IJCV!
  • 2024/09 - 4 papers accepted to NeurIPS 2024!
  • 2024/07 - 1 paper accepted to IJCV!
  • 2024/07 - 2 papers accepted to ACM MM 2024!
  • 2024/07 - 1 paper accepted to ECCV 2024!
  • 2024/06 - 1 paper accepted to Commun Eng!
  • 2024/05 - 2 papers accepted to TCSVT!
  • 2024/04 - 1 paper accepted to TPAMI!
  • 2024/02 - 6 papers accepted to CVPR 2024!
  • 2024/01 - 2 papers accepted to ICLR 2024!
  • 2023/12 - 3 papers accepted to AAAI 2024!
  • 2023/11 - 1 paper accepted to TPAMI!
  • 2023/10 - 1 paper accepted to TMM!
  • 2023/09 - 1 paper accepted to NeurIPS 2023!
  • 2023/08 - 1 paper accepted to TIM!
  • 2023/07 - 3 papers accepted to ICCV 2023!

Papers 2025

Yahao Shi, Yanmin Wu, Chenming Wu, Xing Liu, Chen Zhao, Haocheng Feng, Jian Zhang, Bin Zhou, Errui Ding, Jingdong Wang (2025). GIR: 3D Gaussian Inverse Rendering for Relightable Scene Factorization. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).

PDF Code Project

Lanjiong Li, Guanhua Zhao (赵灌华), Lingting Zhu, Zeyu Cai, Lequan Yu, Jian Zhang (张健), Zeyu Wang (2025). AssetDropper: Asset Extraction via Diffusion Models with Reward-Driven Optimization. Special Interest Group for Computer GRAPHICS and Interactive Techniques (SIGGRAPH).

Guanhua Zhao (赵灌华), Yu Gu (古雨), Xuhan Sheng (盛栩涵), Yujie Hu (胡妤婕), Jian Zhang (张健) (2025). Label-guided Facial Retouching Reversion. IEEE International Conference on Multimedia and Expo(ICME).

Oral

Gehui Li (李戈辉), Bin Chen (陈斌), Chen Zhao, Lei Zhang, Jian Zhang (张健) (2025). OSMamba: Omnidirectional Spectral Mamba with Dual-Domain Prior Generator for Exposure Correction![alt new](/images/new.gif). IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

Haijie Li (李海杰), Yanmin Wu (吴艳敏), Jiarui Meng (孟佳锐), Qiankun Gao (高乾坤), Zhiyao Zhang, Ronggang Wang, Jian Zhang (张健) (2025). InstanceGaussian: Appearance-Semantic Joint Gaussian Representation for 3D Instance-Level Perception. IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

See All

Papers 2024

Bin Chen (陈斌), Jian Zhang (张健) (2024). Practical Compact Deep Compressed Sensing. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).

PDF Code Project

Shuzhou Yang (杨树州), Xuanyu Zhang (张轩宇), Yinhuai Wang (王荫槐), Jiwen Yu (余济闻), Yuhan Wang, Jian Zhang (张健) (2024). DiffLLE: Diffusion-guided Domain Calibration for Unsupervised Low-light Image Enhancement. International Journal of Computer Vision (IJCV).

PDF

Chong Mou (牟冲), Mingdeng Cao, Xintao Wang, Zhaoyang Zhang, Ying Shan, Jian Zhang (张健) (2024). ReVideo: Remake a Video with Motion and Content Control. Advances in Neural Information Processing Systems (NeurIPS).

PDF Code Project

Xuanyu Zhang (张轩宇), Jiarui Meng (孟佳锐), Runyi Li (李润一), Zhipei Xu (徐志沛), Yongbing Zhang, Jian Zhang (张健) (2024). GS-Hider: Hiding Messages into 3D Gaussian Splatting. Advances in Neural Information Processing Systems (NeurIPS).

PDF Project

Qiankun Gao (高乾坤), Jiarui Meng (孟佳锐), Chengxiang Wen (温程翔), Jie Chen, Jian Zhang (张健) (2024). HiCoM: Hierarchical Coherent Motion for Dynamic Streamable Scenes with 3D Gaussian Splatting. Advances in Neural Information Processing Systems (NeurIPS).

See All

Papers 2023

Wenxue Cui, Xiaopeng Fan, Jian Zhang (张健), Debin Zhao (2023). Deep Unfolding Network for Image Compressed Sensing by Content-adaptive Gradient Updating and Deformation-invariant Non-local Modeling. IEEE Transactions on Multimedia (TMM).

PDF

Jiwen Yu (余济闻), Xuanyu Zhang (张轩宇), Youmin Xu (许佑民), Jian Zhang (张健) (2023). CRoSS: Diffusion Model Makes Controllable, Robust and Secure Image Steganography. Advances in Neural Information Processing Systems (NeurIPS).

PDF Code

Jiechong Song (宋皆充), Jian Zhang (张健) (2023). SODAS-Net: Side-Information-Aided Deep Adaptive Shrinkage Network for Compressive Sensing. IEEE Transactions on Instrumentation and Measurement (TIM).

PDF Code

Qiankun Gao (高乾坤), Chen Zhao, Yifan Sun, Teng Xi, Gang Zhang, Bernard Ghanem, Jian Zhang (张健) (2023). A Unified Continual Learning Framework with General Parameter-Efficient Tuning. International Conference on Computer Vision (ICCV).

PDF Code

Jiwen Yu (余济闻), Yinhuai Wang (王荫槐), Chen Zhao, Bernard Ghanem, Jian Zhang (张健) (2023). Freedom: Training-free energy-guided conditional diffusion model. International Conference on Computer Vision (ICCV).

PDF Code

See All

Papers Before 2023

Chong Mou (牟冲), Yanze Wu, Xintao Wang, Chao Dong, Jian Zhang (张健), Ying Shan (2022). Metric Learning based Interactive Modulation for Real-World Super-Resolution. European Conference on Computer Vision (ECCV).

PDF Code

Qiankun Gao (高乾坤), Chen Zhao, Bernard Ghanem, Jian Zhang (张健) (2022). R-DFCIL: Relation-Guided Representation Learning for Data-Free Class Incremental Learning. European Conference on Computer Vision (ECCV).

PDF Code

Jianhui Chang (常建慧), Jian Zhang (张健), Youmin Xu (许佑民), Jiguo Li, Siwei Ma, Wen Gao (2022). Consistency-Contrast Learning for Conceptual Coding. ACM International Conference on Multimedia (ACM MM).

PDF

Xinhua Cheng (程鑫华), Mengxi Jia (贾梦溪), Qian Wang (王茜), Jian Zhang (张健) (2022). More is better: Multi-source Dynamic Parsing Attention for Occluded Person Re-identification. ACM International Conference on Multimedia (ACM MM).

PDF

Hao Bian, Zhuchen Shao, Yang Chen, Yifeng Wang, Haoqian Wang, Jian Zhang (张健), Yongbing Zhang (2022). Multiple Instance Learning with Mixed Supervision in Gleason Grading. International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI).

PDF Code

See All

Openings

Postdoctoral Fellows

The VILLA group at PKU is looking for a top postdoctoral researcher with expertise in computer vision, computational photography, and deep learning. The researcher for this opening will work at PKU to investigate and develop principled computational methods for highly effective, scalable, and robust visual-information intelligent learning (e.g. person re-identification, tracking, segmentation, compression, reconstruction). Please send a full CV with a complete list of your publications and projects to Prof. Jian Zhang.

Students

The VILLA group at PKU is looking for motivated MS and Ph.D. students in computer vision and signal processing. Please send a full CV with a complete list of your publications and projects, as well as, an unofficial academic transcript to Prof. Jian Zhang.
国内学生请认真阅读【2026招收硕士/博士研究生及访问学生申请须知】。

Contact