Hoon-Gyu Chung
Hoon-Gyu Chung
Embedded Files
I'm a Ph.D student of Baek's Group at Computer Graphics Lab @ POSTECH, advised by Prof. Seung-Hwan Baek. My research interests are inverse rendering and computational imaging. I work as a visiting researcher at University of Toronto, advised by Prof. David B. Lindell.
I'm a Ph.D student of Baek's Group at Computer Graphics Lab @ POSTECH, advised by Prof. Seung-Hwan Baek. My research interests are inverse rendering and computational imaging. I work as a visiting researcher at University of Toronto, advised by Prof. David B. Lindell.
Email: hgchung@postech.ac.kr
Github: [link]
News
News
MAR 2026
One paper is accepted to SIGGRAPH 2026
DEC 2025 ~ FEB 2026
Visiting researcher at Toronto Computation Imaging Group
Jun 2025
One paper is accepted to ICCV 2025
Feb 2025
One paper is accepted to CVPR 2025
Feb 2024
One paper is accepted to CVPR 2024
Publications
Publications
Ambient-robust Inverse Rendering using Active RGB-NIR Imaging
Ambient-robust Inverse Rendering using Active RGB-NIR Imaging
Hoon-Gyu Chung, Jiinyeong Kim, Hyunwoo Kang, Seung-Hwan Baek
SIGGRAPH 2026
[PDF] [arXiv] [Project] [Code] [Video]
We introduce an ambient-robust inverse rendering method using an active imaging system comprised of an RGB-NIR camera and NIR flash mounted on a robotic arm attached to a mobile base.
A Real-world Display Inverse Rendering Dataset
A Real-world Display Inverse Rendering Dataset
Seokjun Choi, Hoon-Gyu Chung, Yujin Jeon, Giljoo Nam, Seung-Hwan Baek
ICCV 2025
[PDF] [arXiv] [Project] [Code] [Video]
We present the first real-world dataset for display-based inverse rendering, captured using a calibrated LCD display and stereo polarization cameras under OLAT patterns.
Differentiable Inverse rendering with Interpretable Basis BRDFs
Differentiable Inverse rendering with Interpretable Basis BRDFs
Hoon-Gyu Chung, Seokjun Choi, Seung-Hwan Baek
CVPR 2025
[PDF] [arXiv] [Project] [Code] [Video]
We introduce a differentiable inverse rendering method that produces interpretable basis BRDFs . It supports physically-based novel-view relighting and intuitive scene editing.
Differentiable Point-based Inverse Rendering
Differentiable Point-based Inverse Rendering
Hoon-Gyu Chung, Seokjun Choi, Seung-Hwan Baek
CVPR 2024
[PDF] [arXiv] [Project] [Code] [Video]
We present differentiable point-based inverse rendering, DPIR, an analysis-by-synthesis method that processes images captured under diverse illuminations to estimate shape and spatially-varing BRDF.
Education
Education
POSTECH, Feb.2024 - Present
M.S-Ph.d in Department of Computer Science and Engineering
Korea University, Mar.2018 - Feb.2024
B.S in Department of Electrical Engineering
Reviewer
Reviewer
ICCV, NeurIPS, BMCV, TPAMI, TVCG
Page updated
Google Sites
Report abuse