Hello, I'm Donghwan Kim

I am a Ph.D. student in Computer Vision and Learning Lab at KAIST advised by Prof. Tae-Kyun Kim.

My dream is making people (also including me) happy. I feel happy in tackling challenging problems and exploring innovative ways to solve them. To make people happy, I am interested in research topics that enhance entertainment experiences particularly in fields such as AR/VR, telepresence, and creative content generation. Recently, my research has focused on 3D human reconstruction and human mesh recovery/generation.


Education

    KAIST
    Ph.D. student in Computer Science, advised by Prof. Tae-Kyun (T-K) Kim.
    Spring 2025 - Current
    KAIST
    M.S. in Computer Science, advised by Prof. Tae-Kyun (T-K) Kim.
    Spring 2023 - Spring 2025
    KAIST
    B.S. in Computer Science.
    Spring 2018 - Fall 2022

News

  • Oct. 2024: MHCDIFF has been accepted to NeurIPS 2024.
  • Jul. 2023: HOGraspNet has been accepted to ECCV 2024.
  • Sep. 2023: FourierHandFlow has been accepted to NeurIPS 2023.

Publications

Employment

    PLUME.D
    • Part time Researcher at PLUME.D.
    • Improved generalization of 2D-to-3D pose uplifting with training on synthetic random camera projection.
    • Implemented video-based SMPL-X estimation pipeline with diffusion models.
    Feb. 2023 - Dec. 2024
    Seoul, Korea
    PLUME.D
    • Unity Developer at PLUME.D.
    • Implemented avatar rendering service from 2.5D human body joints with single web cam in real-time.
    • 1st place (of 876 teams), 11th Chung Ju-Young Startup Competition (the largest private startup contest in Korea).
    • 2nd place (of 5,420 teams), K-Startup Grand Challenge 2022 (the largest government startup contest in Korea).
    Jan. 2022 - Feb. 2023
    Seoul, Korea
    NCSOFT
    • Research Intern in the Human pose team of Vision AI Lab.
    • Implemented GUI tool for multi-view camera calibration and multi-view camera capture.
    Mar. 2021 - Aug. 2021
    Seongnam, Korea