Chongyi Li



đź“Ť ABN-02b-11, NTU, SG
📧lichongyi25 at gmail.com
📧chongyi.li at ntu.edu.sg

[GitHub] [DBLP]
[Google Scholar]


Homepage

Publications

Datasets

Welcome to Chongyi Li (李重仪)'s Homepage


2021/10 - , I am a Research Assistant Professor with the School of Computer Science and Engineering, Nanyang Technological University (NTU), Singapore.

2020/01 - 2021/10, I was a research fellow at the MMLab@NTU and worked with Dr. Chen Change Loy, School of Computer Science and Engineering, Nanyang Technological University (NTU), Singapore.

2018/10 - 2020/01, I was a postdoctoral fellow and worked with Chair Prof. Sam Kwong (IEEE Fellow), Department of Computer Science, City University of Hong Kong (CityU), Kowloon, Hong Kong.

2016/12 - 2017/12, I was a joint Ph.D. student at Research School of Engineering, Australian National University (ANU), Canberra, Australia, under the supervision of Prof. Fatih Porikli (IEEE Fellow).

2014/09 - 2018/07, I was a Ph.D. student at School of Electrical and Information Engineering, Tianjin University (TJU), Tianjin, China, under the supervision of Prof. Jichang Guo.

Hiring:


We are looking for Research Fellow, Research Assistant, and Project Officer who want to conduct research and develop advanced deep learning algorithms for image and video enhancement and restoration, computational imaging, and image signal processor. [Join Us]



Research Interests:

    My primary reseach interests include artificial intelligence, machine learning, computer vision, and image processing, particularly in the domains of

  • Image and Video Restoration and Enhancement

    • The purpose is to develop algorithms to process an image or video so that result is more suitable than original image or video for specific application. The specific research topics are
    1. restoring and enhancing the images and videos captured in adverse weather (hazy, foggy, sandy, dusty, rainy, snowy day)
    2. restoring and enhancing the images and videos captured in special circumstances or devices (underwater, weak illumination, dark, under-display devices)
    3. general photo enhancement, auto image retouching
    4. image/depth super-resolution, image deblurring, image denosing
  • Multi-Modality Scene Understanding

    • The purpose is to design AI models to perceive and understand scenes. The specific research topics are
    1. RGB-D salient object detection
    2. co-salient object detection
    3. remote sensing image salient object detection

Recent News:

  • 2022/06 --One paper has been accepted by TIP
  • 2022/05 --One paper has been recognized as ESI Hot Paper
  • 2022/05 --One paper has been accepted by TIP
  • 2022/05 --I am nominated with honor to serve as an Associate Editor of IEEE Journal of Oceanic Engineering (IF: 3.554).
  • 2022/04 --Our team Feedforward won the second runner-up (3/317) in MegCup Efficient Model for Blind Denoising. Congrats to Xin Jin, Ruiqi Wu, and Zhen Li. The code is publicly available here.
  • 2022/04 --One paper has been accepted by TCYB
  • 2022/03 --Our ECCV 2022 Workshop coupled with challenges: Mobile Intelligent Photography & Imaging has been accepted. (http://mipi-challenge.org/)
  • 2022/03 --One paper has been accepted by TCSVT
  • 2022/03 --One paper has been accepted by CVPR 2022
  • 2022/02 --I am homored to be recognised as the Outstanding Reviewer of the IEEE Journal of Oceanic Engineering.
  • 2022/01 --One paper has been recognized as ESI Hot Paper
  • 2022/01 --One paper has been recognized as ESI Highly Cited Paper
  • 2022/01 --One papers is recognized as Popular Documents (the 50 most frequently accessed documents) in IEEE Transactions on Cybernetics
  • 2022/01 --I am nominated with honor to serve as an Associate Editor of Neurocomputing (IF: 5.719).
  • 2022/01 --Two papers are recognized as Popular Documents (the 50 most frequently accessed documents) in IEEE Transactions on Image Processing
  • 2022/01 --I am homored to be recognised as the World’s Top 2% Scientists (2020). It is compiled by Stanford University based on the standardized citation indicators (Table_1_Authors_singleyr_2020_wopp_extracted_202108), which is avaiable online at Mendeley Database

Projects:


CuDi: Curve Distillation for Efficient and Controllable Exposure Adjustment
2022
Chongyi Li, Chunle Guo, Ruicheng Feng, Shangchen Zhou, and Chen Change Loy.
PDF| Project Page| Code





BeautyREC: Robust, Efficient, and Content-preserving Makeup Transfer
2022
Qixin Yan, Chunle Guo, Chen Change Loy, and Chongyi Li.
PDF| Project Page| Code





Revisiting RAW Data for Seeing in the Dark
2022
Linghao Han, Xin Jin, Zhen Li, Chunle Guo, Zhi Chai, and Chongyi Li.
PDF| Project Page| Code





LEDNet: Joint Low-light Enhancement and Deblurring in the Dark
2022
Shangchen Zhou, Chongyi Li, Chen Change Loy.
PDF| Project Page| Code| Dataset





Flare7K: A Phenomenological Nighttime Flare Removal Dataset
2022
Yuekun Dai, Chongyi Li, Shangchen Zhou, Ruicheng Feng, and Chen Change Loy.
PDF| Project Page| Dataset Video






Towards Robust Blind Face Restoration with Codebook Lookup TransFormer
2022
Shangchen Zhou, Kelvin C. K. Chan, Chongyi Li, and Chen Change Loy.
PDF| Project Page| Code| Video






Low-Light Image Enhancement Online Platform Different algorithms demand various configurations, GPU versions, and hardware specifications that are prohibitive to beginners who are new to this area and may not even have GPU resources. We contribute an online plateform.
Website






Mobile Intelligent Photography & Imaging
1st MIPI workshop @ ECCV 2022
Chongyi Li, Shangchen Zhou, Ruicheng Feng, Jun Jiang, Wenxiu Sun, Qingyu Yang, Qingpeng Zhu, Chen Change Loy, and Jinwei Gu.
Website





Image Dehazing Transformer with Transmission-Aware 3D Position Embedding
CVPR, 2022
Chunle Guo, Qixin Yan, Saeed Anwar, Runmin Cong, Wenqi Ren, and Chongyi Li+.
PDF| Project Page| Code





Underwater Image Enhancement via Minimal Color Loss and Locally Adaptive Contrast Enhancement
TIP, 2022
Weidong Zhang, Peixian Zhuang, Haihan Sun, Guohou Li, Sam Kwong, and Chongyi Li+.
PDF| Project Page| Code





Global-and-Local Collaborative Learning for Co-Salient Object Detection
TCYB, 2022
Runmin Cong, Ning Yang, and Chongyi Li+, Huazhu Fu, Yao Zhao, Qingming Huang, and Sam Kwong.
PDF| Project Page| Code





Underwater Image Enhancement Quality Evaluation: Benchmark Dataset and Objective Metric
TCSVT, 2022
Qiuping Jiang, Yuses Gu, Chongyi Li, Runmin Cong, and Feng Shao.
PDF| Code| Dataset





Under-Display Camera Image Enhancement via Cascaded Curve Estimationc
TIP, 2022
Jun Luo, Wenqi Ren, Tao Wang, Chongyi Li, and Xiaochun Cao.
PDF





Low-Light Image and Video Enhancement Using Deep Learning: A Survey
TPAMI, 2021
Chongyi Li, Chunle Guo, Linghao Han, Jun Jiang, Ming-Ming Cheng, Jinwei Gu, Chen Change Loy.
PDF| Project Page| Collection| Dataset





Removing Diffraction Image Artifacts in Under-Display Camera via Dynamic Skip Connection Network
CVPR, 2021
Ruicheng Feng, Chongyi Li, Huaijin Chen, Shuai Li, Chen Change Loy, Jinwei Gu.
PDF| Project Page| Code





Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation
TPAMI, 2021
Chongyi Li, Chunle Guo, Chen Change Loy.
PDF| Project Page| Code





Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding
TIP, 2021
Chongyi Li, Saeed Anwar, Junhui Hou, Runmin Cong, Chunle Guo, Wenqi Ren.
PDF| Project Page| Code





Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement
CVPR, 2020
Chunle Guo, Chongyi Li, Jichang Guo, Chen Change Loy, Junhui Hou, Sam Kwong, Runmin Cong.
PDF| Project Page| Code





RGB-D Salient Object Detection with Cross-Modality Modulation and Selection
ECCV, 2020
Chongyi Li, Runmin Cong, Yongri Piao, Qianqian Xu, Chen Change Loy.
PDF| Project Page| Code





NuI-Go: Recursive Non-Local Encoder-Decoder Network for Retinal Image Non-Uniform Illumination Removal
ACM MM, 2020
Chongyi Li, Huazhu Fu, Runmin Cong, Zechao Li, Qianqian Xu.
PDF| Project Page| Code





An Underwater Image Enhancement Benchmark Dataset and Beyond
TIP, 2020
Chongyi Li, Chunle Guo, Wenqi Ren, Runmin Cong, Junhui Hou, Sam Kwong, Dacheng Tao.
PDF| Project Page| Benchmark| Code





Nested Network With Two-Stream Pyramid for Salient Object Detection in Optical Remote Sensing Images
TGRS, 2020
Chongyi Li, Runmin Cong, Junhui Hou, Sanyi Zhang, Yue Qian, Sam Kwong.
PDF| Project Page| Benchmark| Results





Underwater Scene Prior Inspired Deep Underwater Image and Video Enhancement
PR, 2020
Chongyi Li, Saeed Anwar, Fatih Porikli.
PDF| Project Page| Code





ASIF-Net: Attention Steered Interweave Fusion Network for RGB-D Salient Object Detection
TCYB, 2020
Chongyi Li, Runmin Cong, Sam Kwong, Junhui Hou, Huazhu Fu, Guopu Zhu, Dingwen Zhang, Qiangming Huang.
PDF| Code and Results





CoADNet: Collaborative Aggregation-and-Distribution Networks for Co-Salient Object Detection
NeurIPS, 2020
Qijian Zhang, Runmin Cong, Junhui Hou, Chongyi Li, and Yao Zhao.
PDF| Project Page| Code





Dense attention fluid network for salient object detection in optical remote sensing images
TIP, 2020
Qijian Zhang, Runmin Cong, Chongyi Li, Ming-Ming Cheng, Yuming Fang, Xiaochun Cao, Yao Zhao, and Sam Kwong.
PDF| Project Page| Benchmark| Code





Hierarchical Features Driven Residual Learning for Depth Map Super-Resolution
TIP, 2019
Chunle Guo, Chongyi Li+, Jichang Guo, Runmin Cong, Huazhu Fu, Ping Han.
PDF| Project Page| Code





PDR-Net: Perception-Inspired Single Image Dehazing Network With Refinement
TMM, 2019
Chongyi Li, Chunle Guo, Jichang Guo, Ping Han, Huazhu Fu, Runmin Cong.
PDF| Project Page| Code





Underwater Image Enhancement by Dehazing with Minimum Information Loss and Histogram Distribution Prior
TIP, 2016
Chongyi Li, Jichang Guo, Runmin Cong, Yanwei Pang, Bo Wang.
PDF| Project Page| Code




Events:

  • [Workshop] ECCV 2022 Workshop on Mobile Intelligent Photography and Imaging (MIPI)
  • [Special Session] IEEE MMSP 2022 Special Session on Underwater Multimedia Processing
  • [Special Issue] IEEE Journal of Oceanic Engineering Special Issue on Advanced Machine Learning Methodologies for Underwater Image and Video Processing and Analysis (2021-2022)
  • [Special Issue] Multimedia Tools and Applications Special Issue on Depth-Related Processing and Applications in Visual Systems (2020-2021)
  • [Special Issue] Signal Processing : Image Communication Special Issue on Visual Information Processing for Underwater Images and Videos: Theories, Algorithms, and Applications (2019-2020)
  • [Special Session] APSIPA ASC 2019 Special Session on Multi-source Data Processing and Analysis: Models, Methods and Applications (2019-2020)

Honors & Awards:

  • 2022/04 --Our team Feedforward won the second runner-up (3/317) in MegCup Efficient Model for Blind Denoising. Congrats to Xin Jin, Ruiqi Wu, and Zhen Li. The code is publicly available here.
  • IEEE Journal of Oceanic Engineering (Outstanding Reviewer in 2021)News
  • One paper has been recognized as ESI Hot Paper.
  • I am homored to be recognised as the World’s Top 2% Scientists (2020). It is compiled by Stanford University based on the standardized citation indicators (Table_1_Authors_singleyr_2020_wopp_extracted_202108), which is avaiable online at Mendeley Database.
  • Two papers are recognized as Popular Documents (the 50 most frequently accessed documents) in IEEE Transactions on Image Processing.
  • One paper is recognized as Popular Documents (the 50 most frequently accessed documents) in IEEE Transactions on Cybernetics.
  • 2021 Innovation in Information Technology Application and Artificial Intelligent Academic Forum for Post-doctoral Talents, Tianjin, China. Runners-up Award. PDF
  • Seven papers have been recognized as ESI Highly Cited Paper. PDF
  • ICCV (Outstanding Reviewer in 2021). PDF
  • CVPR (Outstanding Reviewer in 2021). PDF
  • 6th, NTIRE 2021 Challenge on Non-Homogeneous Image Dehazing, 2021. PDF
  • 2020 National Postdoctoral Forum on the Development and Application of Artificial Intelligence, Tianjin, China. Excellence Award. PDF
  • Distinguished Dissertation Award of Beijing Society of Image and Graphics, 2018.Media
  • "Outstanding Graduate Student" in Tianjin University, 2018.

Professional Service:


    Associate Editor
    2022/05- : IEEE Journal of Oceanic Engineering (IF: 3.554)
    2022/01- : Neurocomputing (IF: 5.719)
    2021/01- : Springer Journal of Signal, Image and Video Processing (IF: 1.794)

    Guest Editor
    IEEE Journal of Oceanic Engineering (Lead Guest Editor) (IF: 3.554)
    Signal Processing: Image Communication (Management Guest Editor) (IF：2.779)
    Multimedia Tools and Applications (IF: 2.313)
    Session Chair
    IEEE Workshop on Multimedia Signal Processing (MMSP) 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) 2019
    Senior Program Committee (Meta-Reviewers)
    AAAI 2022

Supervision and Teaching:

  • Co-Supervisor, M.E.: Zhexin Liang (Zhejiang University), AI Major Project: Image and Video Enhancement, NTU, 01/2022-present
  • Co-Supervisor, M.E.: Yuekun Dai (Peking University), AI Major Project: Video Depth Estimation, NTU, 08/2021-present
  • Co-Supervisor, M.E.: Xingshu Wang (Beijing University of Posts and Telecommunications), Project: Reference-Based Image Super-Resolution, ANU
  • Teaching Assistant, NTU CE6126: MSAI Advanced Computer Vision, NTU, Fall 2020

Alumni:

  • Co-Supervised with Cavan, Zurang Liu (Beijing University of Posts and Telecommunications), Project: Deep Image Harmonization, AI Master@NTU, 01/2021-04/2022, Now: Engineer@ByteDance, SG
  • Co-Supervisor with Cavan, Sihao Chen, Project: Learning to See in the Dark [Final Report--Video (A+)], FYP of Computer Science@NTU, 06/2020-06/2021, Now: Engineer@Shopee, SG. Sihao's project is awarded the 2021 Global Undergraduate Awards for his entry 'Learning to See in the Dark - Low Light Image Enhancement'. [The Global Undergraduate Awards][NTU News]
  • Co-Superviso with Cavan, Qiming Ai (University of Science and Technology of China), Project: Deep Photo Enhancement, AI Master@NTU, 01/2020-12/2020, Now:

Miscellaneous: