I am a Ph.D. student at KAIST AMILab, advised by Tae-Hyun Oh. I received my M.S. and B.S., both in Electrical Engineering, from POSTECH. I work on computer vision, generative models, and image processing — most of my research is about inferring the physical world (shape, motion, color, light) from ordinary images, so that scenes can be relit, re-rendered, and animated rather than merely replayed.
Selected research
Education
Advisor: Tae-Hyun Oh
Advisor: Tae-Hyun Oh
Thesis: High Dynamic Range Space-Time View Synthesis of Dynamic Scenes
Undergraduate thesis advisor: Chulhong Kim
Publications
Conference
-
Reflection-aware Generative Novel View Synthesis ECCV 2026 · project page · paper · code
-
HDR-NSFF: High Dynamic Range Neural Scene Flow Fields ICLR 2026 · project page · paper · code
Under review
-
A training-free, image-level defense against typographic attacks on vision-language models -
Animatable Gaussian head avatars synthesized from a single motion-blurred portrait image
Workshop
- Dynamic HDR Radiance Fields via Neural Scene Flow ICCV Workshop on Wild3D, 2025
- HDR-NSFF: High Dynamic Range Neural Scene Flow Fields 37th Workshop on Image Processing and Image Understanding (IPIU), 2025 · Outstanding Poster Award
Awards & honors
- Outstanding Poster Award, IPIU2025
Service
Experience
Robust optical flow estimation under exposure change. Advisor: Tae-Hyun Oh
Smartwatch-based hand gesture recognition. Advisor: Yongsang Cho
Performance and quality assessment methodology for SSD and HDD