PeopleofSuperintelligence

Researcher

Chongyi Li

Also known as Chong-Yi Li, Li Chong-yi

Chongyi Li is a computer-vision researcher and professor in Nankai University's College of Computer Science and at Shenzhen Loop Area Institute whose deep-learning work restores underwater and low-light images. After earning a PhD at Tianjin University in 2018 under Jichang Guo, he worked as a research fellow at City University of Hong Kong and Nanyang Technological University from 2018 to 2021 and as a research assistant professor at NTU from 2021 to 2023. In 2019, he coauthored the UWCNN underwater enhancement network and the UIEB benchmark paper with its Water-Net baseline, followed by Zero-Reference Deep Curve Estimation (Zero-DCE) at CVPR 2020 and a 2021 low-light enhancement survey and mobile-phone dataset. He shared the 2025 IEEE Signal Processing Society Best Paper Award for the UIEB benchmark paper and leads the π Research Group at Nankai University, working on computational imaging, generative vision and multimodal models.

Now at
Nankai University, Shenzhen Loop Area Institute and Nanyang Technological University
Works
191
Citations
21,347
h-index
59

Publication numbers from OpenAlex, as of 22 October 2026.

Timeline

  1. 2018

    A PhD at Tianjin University

    Chongyi Li earns a PhD at Tianjin University in 2018 under the supervision of Jichang Guo.

  2. 2018–2021

    Research fellow at CityU and NTU

    From 2018 to 2021, he works as a research fellow at City University of Hong Kong under Sam Kwong and at Nanyang Technological University under Chen Change Loy.

  3. 2019

    UWCNN and the UIEB benchmark

    In 2019, he coauthors UWCNN, an underwater image enhancement convolutional neural network built on an underwater scene prior. His 2019 UIEB paper introduces an underwater image enhancement benchmark dataset and proposes Water-Net as a trained CNN baseline.

  4. 2020

    Zero-DCE for low-light images

    At CVPR 2020, he coauthors Zero-Reference Deep Curve Estimation (Zero-DCE), a low-light enhancer that formulates light enhancement as image-specific curve estimation with a deep network and requires no paired or unpaired training data.

  5. 2021

    Low-light enhancement survey and dataset

    He coauthors a 2021 survey of deep-learning methods for low-light image and video enhancement that proposes a dataset of images and videos captured by different mobile-phone cameras under diverse illumination conditions.

  6. 2021–2023

    Research assistant professor at NTU

    From 2021 to 2023, Li serves as a research assistant professor in the School of Computer Science and Engineering at Nanyang Technological University in Singapore.

  7. 2025

    IEEE SPS Best Paper Award

    With Chunle Guo, Runmin Cong, Junhui Hou and Sam Kwong, he shares the 2025 IEEE Signal Processing Society Best Paper Award for their 2019 IEEE Transactions on Image Processing paper on the UIEB benchmark.

  8. As of October 2026

    Professor at Nankai and SLAI

    As of October 2026, he is a professor in Nankai University's College of Computer Science, where he leads the π Research Group, and serves concurrently as a professor at Shenzhen Loop Area Institute. His research covers computational imaging, image enhancement and restoration, generative vision, multimodal models and visual intelligence.

Career

  1. Since 2023Nankai UniversityProfessor
  2. NowShenzhen Loop Area InstituteProfessor
  3. 2020–2022Tongji University
  4. 2018–2021City University of Hong KongResearch fellow
  5. 2018–2023Nanyang Technological UniversityResearch fellow, Research assistant professor

Education

  1. 2018Tianjin UniversityPhD

From the biography and OpenAlex affiliations (the years of papers that list the organization), so some years are approximate.

  1. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes Chongyi Li. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other university. We compare doctorate and 5+ year employment links, career timing and current workplaces for 187 major-prize and 1,111 best-paper winners.
  2. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes Nanyang Technological University. We estimate where the people shaping AI studied and where their careers led. Massachusetts Institute of Technology leads with 467 former students, including 291 recorded doctorates.
  3. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Nanyang Technological University. We estimate where the people shaping AI worked when their most-cited papers appeared: the company share was 31% in 2020–2024 and 8% in 1970–1974, and Google led all organizations in 2020–2024.
  4. Google has the highest combined h-index among AI organizationsIncludes Nanyang Technological University. We estimate that Google holds the highest combined h-index at 8,016, while universities account for 73% of the deduplicated total across AI organizations.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Chongyi Li yet. Send us a free-licensed photo.

  1. People | Photography & Imaging (π) Research Group pi-lab.xyz. Checked 22 October 2026.
  2. Underwater Scene Prior Inspired Deep Underwater Image and Video Enhancement li-chongyi.github.io. Checked 22 October 2026.
  3. An Underwater Image Enhancement Benchmark Dataset and Beyond arxiv.org. Checked 22 October 2026.
  4. Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement openaccess.thecvf.com. Checked 22 October 2026.
  5. Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation arxiv.org. Checked 22 October 2026.
  6. Low-Light Image and Video Enhancement Using Deep Learning: A Survey arxiv.org. Checked 22 October 2026.
  7. Staff Achievements | Department of Computer Science cs.cityu.edu.hk. Checked 22 October 2026.
  8. Chongyi Li — Academic Homepage li-chongyi.github.io. Checked 22 October 2026.