MMLab MMLab
Chen Change Loy

Brief

Biography

Chen Change (Cavan) Loy is a President’s Chair Professor at the College of Computing and Data Science, Nanyang Technological University (NTU), Singapore. He is the Director of MMLab@NTU and Co-Associate Director of S-Lab. He received his PhD in Computer Science from the Queen Mary University of London in 2010. Prior to joining NTU in 2018, he was a Research Assistant Professor at the Multimedia Laboratory (MMLab) at The Chinese University of Hong Kong from 2013 to 2018. Earlier, he worked as a postdoctoral researcher at Queen Mary University of London between 2010 and 2013.

His research interests include large multimodal models, generative AI, spatial intelligence and representation learning. His work has significantly advanced image and video super-resolution and face restoration. Notable contributions include pioneering deep-learning approaches such as SRCNN, ESRGAN, GLEAN, CodeFormer, and the BasicVSR series. His publications have received over 120,000 citations with an h-index of 141, and many of his methods are widely adopted in both academia and industry.

Cavan is recognized among the 100 Most Influential Scholars in Computer Vision by AMiner from 2020 to 2025. His awards include the NRF Investigatorship, the IIT Bombay International Award, the Nanyang Research Award, and the CCF-CV Test of Time Award.

He has served as Associate Editor for leading journals including IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), International Journal of Computer Vision (IJCV), and Computer Vision and Image Understanding (CVIU). He has also served as Area Chair or Senior Area Chair for major conferences such as CVPR, ICCV, ECCV, ICLR, and NeurIPS, and has co-organized multiple workshops and challenges at top computer vision conferences. He currently serves as Program Co-Chair of CVPR 2026 and will serve as General Co-Chair of ACCV 2028.

吕健勤（Chen Change (Cavan) Loy），新加坡南洋理工大学 计算与数据科学学院 校长讲席教授。2010年获得英国 伦敦大学玛丽王后学院 计算机科学博士学位。2013年至2018年在香港中文大学多媒体实验室（MMLab）担任研究助理教授。2010年至2013年期间在英国伦敦大学玛丽王后学院从事博士后研究工作。

他的研究方向包括大规模多模态模型、生成式人工智能、空间智能以及表示学习等领域。在图像与视频超分辨率、人脸修复和生成式视觉建模等方面取得了一系列具有影响力的成果。其代表性工作包括 SRCNN、ESRGAN、GLEAN、CodeFormer 以及 BasicVSR 系列等深度学习方法，这些方法推动了相关研究的发展并在工业界得到广泛应用。截至目前，其学术论文被引用超过120,000次，H-index 为141（Google Scholar）。

吕健勤教授在2020至2025年连续入选 AMiner 发布的 全球计算机视觉领域最具影响力学者前100名。曾获得 NRF Investigatorship、IIT Bombay International Award、南洋研究奖 以及中国计算机学会计算机视觉专委会（CCF-CV）颁发的持久影响力论文奖等多项荣誉。

他曾担任国际顶级期刊 IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)、International Journal of Computer Vision (IJCV) 和 Computer Vision and Image Understanding (CVIU) 的副主编，并多次担任 CVPR、ICCV、ECCV、ICLR 和 NeurIPS 等国际顶级会议的领域主席或高级领域主席。他目前担任 CVPR 2026 大会程序主席，并将担任 ACCV 2028 大会主席。

Education

  1. Ph.D. Computer Science, Queen Mary University of London, 2010
    Thesis: Activity Understanding and Unusual Event Detection in Surveillance Videos
    Advisors: Tao Xiang and Shaogang Gong
    Thesis committee: Tim Ellis and Gabriel Brostow
  2. B.Eng. Electronic Engineering (1st class honours), University of Science Malaysia, 2005
    Thesis: A Pressure-based Typing Biometrics System for User Authentication
    Advisor: Chee Peng Lim

Professional Experience

  1. Nanyang Technological University, Singapore
    • President's Chair Professor, Apr 2024-Present
    • Professor, Sep 2023-Present
    • Nanyang Associate Professor, Apr 2019-Aug 2023
    • Associate Professor, Aug 2018-Mar 2019
  2. The Chinese University of Hong Kong
    • Adjunct Associate Professor, Aug 2018-Present
    • Research Assistant Professor, Mar 2013-Jul 2018
  3. Vision Semantics Limited, United Kingdom
    • Postdoctoral Researcher, Jan 2012-Feb 2013
      Projects: GETAWAY
  4. Queen Mary University of London, United Kingdom
    • Postdoctoral Researcher, Dec 2010-Dec 2011
      Projects: SAMURAI
  5. MIMOS Berhad, Malaysia
    • Researcher, Jul 2007-Aug 2007
    • Associate Researcher, May 2005-Jul 2007
    • Research Assistant, Mar 2004-May 2004

Services and Activities

Teaching

  • NTU: AI6126 MSAI Advanced Computer Vision: 2020-2024 (with Ziwei Liu)
  • NTU: CE7491 Advanced Digital Image Processing: 2019-2025 (with Tat-Jen Cham)
  • NTU: SC4001 Neural Networks and Deep Learning: 2019-2025 (with Jagath C Rajapakse and Alvin Chan)
  • CUHK: IERG6210 Advanced Topics in Information Processing: 2018
  • CUHK: IERG4160 Image and Video Processing: 2014-2017

Honours and Awards

Academic and other Recognition
  • NRF Investigatorship, 2026
  • IIT Bombay International Award, 2025
  • WAIC Youth Outstanding Paper Award Honorable Mention, 2025
  • Springer Nature Editorial Contribution Award, 2025
  • Nanyang Research Award, 2024
  • Singapore Open Research Award, 2024
  • Test of Time Award, CCF-CV, 2024
  • President's Chair Professorship, 2024
  • Computational Visual Media Journal, Best Paper Honorable Mention. 2024
  • WAIC Youth Outstanding Paper Award Honorable Mention, 2023
  • Honorable Mention, AI 2000 Computer Vision Most Influential Scholar Award, AMiner, 2020, 2021, 2022, 2023, 2024, 2025
  • Nanyang Associate Professorship (Career Award), 2019
  • Best Application Paper Honorable Mention, Asian Conference on Computer Vision, 2016
  • Best Student Invention Award, Silver Award (as supervisor), Hong Kong ICT Awards, 2016
  • Outstanding Reviewer, CVPR 2017, BMVC 2017, ACCV 2014
  • Gold Medal Award, The 34th International Exhibition of Inventions, New Techniques and Products of Geneva, 2006
  • Gold Medal Award, Malaysia Public Institutions of Higher Learning R&D Expo, 2005
  • Special Award for ICT Cluster, Malaysia Public Institutions of Higher Learning R&D Expo, 2005
  • Hall of Fame Award, Product Research Category, University of Science Malaysia, 2005-2006
Competitions and Challenges
  • Three Champions, NTIRE 2021 Challenge on Video Restoration and Enhancement, 2021
  • Best Neural Planning Metric (PKL), second runner-up, nuScenes Detection Challenge of 5th AI Driving Olympics, NeurIPS 2020
  • Champion, COCO 2019 Object Detection Challenge (Without External Data), 2019
  • Champions of all four tracks, Facebook AI Self-Supervision Challenge, 2019
  • Champion, Open Images Challenge (Object Detection), 2019
  • Champions of all four tracks, NTIRE 2019 Challenge on Video Restoration and Enhancement, 2019
  • Champion, COCO Object Detection Challenge, 2018
  • Champion, PIRM Challenge on Perceptual Super-Resolution (Third Region), 2018
  • First Runner-up, DAVIS Challenge on Video Object Segmentation, 2018 [Technical Report]
  • First Runner-up, NTIRE 2018 Challenge on Single Image Super-Resolution, 2018
  • Champion, DAVIS Challenge on Video Object Segmentation, 2017 [PDF]
  • First Runner-up, NTIRE 2017 Challenge on Single Image Super-Resolution, 2017 [PDF]
  • Second Runner-up in ImageNet Large Scale Visual Recognition Challenge (ILSVRC) object classification task, 2016
  • Champion in ICDAR 2015 Competition on Text Image Super-Resolution, 2015
  • Runner-up in ImageNet Large Scale Visual Recognition Challenge (ILSVRC) object detection task, 2014
  • Honorary Mention, National Instruments ASEAN Virtual Instrumentation Applications Contest, 2005 [PDF]

Selected Talks

  • From Segment Anything Efficiently to Matting Anyone Precisely
    Invited Talk, Nanjing University, June 2025
    Invited Talk, CVPR 2025 Workshop on Efficient Large Vision Models, June 2025
  • Improving Generalization in Image Restoration via ‘Unconventional' Losses
    Invited Talk, ACCV 2024 Workshop on Rich Media with Generative AI, December 2024
    Invited Talk, Xi'an Jiaotong University, June 2024
  • Harnessing Diffusion Prior for Content Enhancement and Creation
    Invited Talk, University of Tokyo, April 2024
    Invited Talk, Annual ShanghaiTech Symposium on Information Science and Technology, Shanghai, China, September 2023
  • Harnessing Generative Priors for Visual Content Restoration
    Lecture, IAPR/IEEE Winter School on Biometrics, Shenzhen, China, January 2024
  • Image and Video Restoration
    Lecture, DeepLearn 2023 Summer, 10th International Gran Canaria School on Deep Learning, Las Palmas de Gran Canaria, Spain, July 2023
  • Harnessing Generative Priors for Image Super-Resolution
    Invited Talk, 18th IEEE Computer Society Workshop on Biometrics 2023, Vancouver, Canada, June 2023
  • Generative Reconstruction Models for Low-Quality Face Images
    Lecture, IAPR/IEEE Winter School on Biometrics, Shenzhen, China, January 2023
  • Joint Low-light Enhancement and Deblurring in the Dark
    Invited Talk, Google Computational Imaging Workshop, Virtual, August 2022
  • Improving Video Super-Resolution with Enhanced Propagation and Alignment
    Invited Talk, CVPR Tutorial on OpenMMLab, New Orleans, USA, June 2022
  • Training Generative Adversarial Networks with Limited Data
    Keynote, The Third Workshop on Fair, Data-Efficient and Trusted Computer Vision (TCV 2022), New Orleans, USA, June 2022
  • Deep Learning Is Shaping the Future of Content Creation
    Invited Talk, SupercomputingAsia 2022 (SCA22), Singapore, March 2022
  • Generative Latent Bank for Large-Factor Image Super-Resolution
    Invited Talk, CVPR Tutorial on OpenMMLab, June 2021
    [Slides]
  • Deep Generative Prior
    Invited Talk, AI Technology Summer School, August 2021
    Invited Talk, Baidu Research, February 2021
    Invited Talk, CCV-CV 底层视觉的前沿进展与未来趋势, January 2021
    Keynote, The International Conference on Digital Image Computing: Techniques and Applications (DICTA), December 2020
    [Slides]
  • Deep Learning in Computer Vision
    Invited Talk, TF–NTU AI Asia, December 2020
  • Deep Learning in Computer Vision
    Invited Talk, The Institution of Engineers Malaysia, December 2020
  • An Introduction to Deepfakes
    Invited Talk, Interpol Virtual Discussion Room, Audio and Video Forensic in the Era of Artificial Intelligence, November 2020
  • Blurring The Line between Real and the Fake
    Invited Talk, VALSE, August 2020
    [Slides]
  • Content-Aware Reassembly of Features
    Invited Talk, CVPR Workshop on Large-Scale Video Object Segmentation Challenge, Seoul, Korea, October 2019
    [Slides]
  • Blurring The Line between Real and the Fake
    Invited Talk, APAC HPC-AI Competition, Singapore, August 2019
  • Towards Versatile Image Restoration
    Invited Talk, CVPR NTIRE 2019, Long Beach, CA, USA, June 2019
    [Slides]
  • AI & Deep Learning Workshop, 人工智慧深度学习工作坊
    Lecture, National Taiwan University of Science and Technology, Taipei, December 2018
  • Deep Learning for Face Recognition
    Invited Talk, Foxlink, Taipei, December 2018
  • Deep Image Super-Resolution
    Invited Talk, National Tsing Hua University, Taiwan, December 2018
  • AI is Powering the Future
    Keynote, 人工智慧与智慧制造论坛, National Taiwan University of Science and Technology, Taipei, December 2018
  • Creating a Network of Smart Cities as a Booster of Growth and Technology Innovation
    Panel, FutureChina Global Forum, Singapore, August 2018
  • Large-Scale Deep Learning for Face Recognition
    Invited Talk, APAC HPC-AI Competition, Singapore, August 2018
  • Face Recognition by Deep Learning - The Imbalance Problem
    Invited Talk, CVPR Workshop on Biometrics 2018, Salt Lake City, Utah, USA, June 2018
    [Slides]
  • From Image Super-Resolution to Face Hallucination
    Guest Lecture, The Hong Kong University of Science and Technology, Hong Kong, April 2018
  • The Path Toward Tomorrow's AI
    Keynote, SupercomputingAsia 2018 (SCA18), Singapore, March 2018
  • Deep Learning in Face Analysis
    Lecture, IAPR/IEEE Winter School on Biometrics, Shenzhen, China, February 2018
    [Slides]
  • Pedestrian Color Naming and Attribute Recognition
    Keynote, ICME Workshop on Human Identification in Multimedia, Hong Kong, July 2017
  • Deep Learning - Current and Future Research Challenges
    IEEE CIS Invited Lecture Program (ILP), Malaysia, June 2017
  • 图像超分辨率的最新进展
    Invited Talk, Fudan University, China, May 2017
  • Deep Learning in Face Analysis
    Lecture, IAPR/IEEE Winter School on Biometrics, Hong Kong Baptist University, Hong Kong, January 2017
    [Slides]
  • 深度学习下的超分辨率图像重建和人脸幻构
    Seminar, Tsinghua University, Beijing, China, November 2016
  • From Facial Expression Recognition to Interpersonal Relation Prediction
    Keynote, ACCV Workshop on Computer Vision for Affective Computing, Taipei, Taiwan, November 2016
  • Deep Learning in Face Analysis: Face Hallucination
    Keynote, ACCV Workshop on Facial Informatics, Taipei, Taiwan, November 2016
  • Learning Deep Representation for Imbalanced Classification
    Keynote, ACCV Workshop on Human Identification for Surveillance, Taipei, Taiwan, November 2016
  • Deep Learning in Computer Vision
    Invited Talk, University of Nottingham, Malaysia, Septemper 2016
  • Learning Deep Representation for Imbalanced Classification
    Invited Talk, Sun Yat-sen University, China, May 2016