|
Seunguk Do I am a Ph.D. candidate in Artificial Intelligence at Seoul National University, advised by Professor Jaesik Park. Previously, I received my M.S. degree in Computer Science and Engineering at Computer Vision Lab, POSTECH where I was advised by Jaesik Park. My research interests lie in computer vision and graphics, with a focus on 3D human reconstruction and diffusion models. |
|
Research |
|
StudioRecon: 4D Human-Scene Reconstruction from Low-Overlap Captures
Minhyuk Hwang*, Sangmin Kim*, Seunguk Do, Daneul Kim, Jaesik Park SIGGRAPH, 2026 A diffusion-guided 4D reconstruction pipeline that recovers humans and scenes from sparse, low-overlap multi-view captures of studio environments. |
|
Direct Reward Fine-tuning on Poses for Single Image to 3D Human in the
wild
Seunguk Do, Minwoo Huh, Joonghyuk Shin, Jaesik Park ICLR, 2026 paper / code A method to post-train a image-to-multi-view diffusion model for enhanced 3D human reconstruction from single-view images across diverse human poses. |
|
ShowMak3r: Compositional TV Show Reconstruction
Sangmin Kim, Seunguk Do, Jaesik Park CVPR, 2025 paper / code A comprehensive pipeline that reconstructs the dynamic radiance field from TV shows, enabling viewpoint editing like how the video clip is made in a production control room. |
Education |
| Seoul National University, Ph.D. in Artificial Intelligence, 2023 - Present |
| POSTECH, M.S. in Computer Science and Engineering, 2022 - 2023 |
| POSTECH, B.S. in Computer Science and Engineering, 2018 - 2022 |
|
Website's source code is referenced from Jon Barron's. |