PeopleofSuperintelligence

Researcher

Kuk-Jin Yoon

Also known as Kukjin Yoon

Kuk-Jin Yoon is a KAIST computer-vision researcher whose work spans stereo matching, event-camera imaging, and video editing. He earned three degrees at KAIST, completed postdoctoral work at KAIST and INRIA, and held faculty posts at GIST before joining KAIST's Department of Mechanical Engineering. His work includes adaptive stereo correspondence, EventSR for event-camera images, and Video-3DGS for temporally consistent video editing. As of October 2026, he is Dean of KAIST's College of AI and a professor in its Department of Mechanical Engineering.

Now at
KAIST

Timeline

  1. 1998–2006

    Three degrees at KAIST

    He earns a B.S. in electrical engineering at KAIST in 1998, an M.S. in electrical engineering and computer science in 2000, and a Ph.D. in the same field in 2006.

  2. March 2006–May 2006

    Postdoctoral researcher at KAIST

    In March 2006, he works as a postdoctoral researcher in KAIST's RCV Lab through May 2006.

  3. April 2006

    Adaptive support-weight stereo

    With In So Kweon, he publishes “Adaptive Support-Weight Approach for Correspondence Search” in April 2006. The method adjusts pixel support weights using color similarity and geometric proximity to reduce ambiguity in stereo correspondence.

  4. August 2006–August 2008

    Postdoctoral fellow at INRIA

    In August 2006, he joins INRIA's PERCEPTION team in France as a postdoctoral fellow and works there through August 2008.

  5. 2008–2018

    Faculty at GIST

    At GIST, he serves as an assistant professor from 2008 to 2014 and an associate professor from 2014 to 2018.

  6. 2018–2024

    KAIST faculty and EventSR

    He joins KAIST's Department of Mechanical Engineering as an associate professor in 2018. With Lin Wang and Tae-Kyun Kim, he presents EventSR in an arXiv preprint in 2020, an end-to-end pipeline that reconstructs low-resolution images from event streams, enhances their quality, and upsamples the results. He becomes a professor at KAIST in 2024.

  7. 2025

    Video-3DGS at TMLR

    In 2025, he coauthors Video-3DGS in Transactions on Machine Learning Research, a 3D Gaussian Splatting video refiner designed to improve temporal consistency in zero-shot video editing.

  8. As of October 2026

    Dean and professor at KAIST

    As of October 2026, he is Dean of KAIST's College of AI and a professor in its Department of Mechanical Engineering. KAIST's Visual Intelligence Lab researches computer vision, robotics, and machine learning.

Career

  1. Since 2006KAISTPostdoctoral researcher, Associate professor
  2. 2008–2018Gwangju Institute of Science and TechnologyAssistant professor, Associate professor
  3. 2006–2008InriaPostdoctoral fellow

Education

  1. 2006KAISTPh.D. in electrical engineering and computer science
  2. 2000KAISTM.S. in electrical engineering and computer science
  3. 1998KAISTB.S. in electrical engineering

From the biography.

  1. The United States employs an estimated 48% of people shaping AIIncludes KAIST. We estimate where the people shaping AI work today, how universities, companies and research institutes split across countries, and how country shares have changed since the 1960s.
  2. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes KAIST. 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 KAIST. 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. 44% of AI career moves go from one university to anotherIncludes KAIST. We estimate how 26,439 AI career moves link universities, companies, labs, nonprofits and government research centers, with decade counts, net flows and the top paths.

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 Kuk-Jin Yoon yet. Send us a free-licensed photo.

  1. KUK-JIN YOON sites.google.com. Checked 21 October 2026.
  2. Adaptive support-weight approach for correspondence search | Korea Advanced Institute of Science and Technology pure.kaist.ac.kr. Checked 21 October 2026.
  3. Kuk-Jin Yoon - Korea Advanced Institute of Science and Technology pure.kaist.ac.kr. Checked 21 October 2026.
  4. [2003.07640] EventSR: From Asynchronous Events to Image Reconstruction, Restoration, and Super-Resolution via End-to-End Adversarial Learning arxiv.org. Checked 21 October 2026.
  5. Enhancing Temporal Consistency in Video Editing by Reconstructing Videos with 3D Gaussian Splatting - Korea Advanced Institute of Science and Technology pure.kaist.ac.kr. Checked 21 October 2026.
  6. Dean's Message | KAIST AI 대학 aicollege.kaist.ac.kr. Checked 21 October 2026.
  7. KAIST Visual Intelligence Lab | VILab vi.kaist.ac.kr. Checked 21 October 2026.