Chunghyun Park

Ph.D. student in the Computer Vision Lab at POSTECH.

chunghyun.png

I am a Ph.D. student in Graduate School of Artificial Intelligence at POSTECH, working as a member of the Computer Vision Lab, advised by Prof. Jaesik Park. Previously, I completed my M.S. in Artificial Intelligence and B.S. in Mechanical Engineering at POSTECH.

My research lies in machine learning and computer vision including, but not limited to, 3D scene understanding and reconstruction. I am particularly interested in 3D perception on point clouds for applications in autonomous vehicles and robotics.

If you are interested in my research projects, please feel free to contact me.

News

Nov 7, 2022 :trophy: Our paper, Fast Point Transformer, won the Qualcomm Innovation Fellowship 2022.
Oct 22, 2022 :pencil: One workshop paper about equivariant learning is accepted to NeurIPS 2022 Workshop - NeurReps.
Oct 19, 2022 :mega: Open3D 0.16 is released with my contribution to the NearestNeighborSearch module.
Oct 4, 2022 :trophy: Two papers got included in the 42 finalists at the Qualcomm Innovation Fellowship 2022.
Jul 4, 2022 :pencil: One paper about 3D point cloud processing is accepted to ECCV 2022.
Mar 3, 2022 :pencil: One paper about large-scale 3D scene understanding is accepted to CVPR 2022.
Feb 16, 2022 :trophy: I won the silver prize at the 28th HumanTech Paper Award from Samsung Electronics Co., Ltd..

Education

Mar, 2022 - Present Pohang University of Science and Technology (POSTECH), Pohang, South Korea
Ph.D. in Artificial Intelligence
Advisor: Prof. Jaesik Park
Mar, 2020 - Feb, 2022 Pohang University of Science and Technology (POSTECH), Pohang, South Korea
M.S. in Artificial Intelligence
Advisor: Prof. Jaesik Park
Mar, 2014 - Feb, 2019 Pohang University of Science and Technology (POSTECH), Pohang, South Korea
B.S. in Mechanical Engineering

Selected Publications

  1. SeLCA: Self-Supervised Learning of Canonical Axis
    Seungwook Kim*, Yoonwoo Jeong*,  Chunghyun Park*, Jaesik Park, and Minsu Cho (*equal contribution)
    Conference on Neural Information Processing Systems Workshop (NeurIPSW) - Symmetry and Geometry in Neural Representations (NeurReps), 2022
  2. PointMixer: MLP-Mixer for Point Cloud Understanding
    Jaesung Choe*,  Chunghyun Park*, Francois Rameau, Jaesik Park, and In So Kweon (*equal contribution)
    European Conference on Computer Vision (ECCV), 2022
    Qualcomm Innovation Fellowship 2022 Finalist
  3. Fast Point Transformer
    Chunghyun Park, Yoonwoo Jeong, Minsu Cho, and Jaesik Park
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
    Silver Prize @ the 28th HumanTech Paper Award
    Qualcomm Innovation Fellowship 2022 Winner

Professional Services

Collaborator Reviewer
  • IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022-2023
  • International Conference on 3D Vision (3DV), 2022
  • European Conference on Computer Vision (ECCV), 2022

Honors and Awards

Qualcomm Innovation Fellowship South Korea (2022)
  • Winner ($4,000): Fast Point Transformer (CVPR 2022)
  • Finalist: PointMixer (ECCV 2022)
The 28th HumanTech Paper Award, Samsung Electronics Co., Ltd. (2022)
  • Silver Prize ($7,000) in Signal Processing