|
My research focuses on 3D computer vision, particularly depth estimation, 3D reconstruction, and neural rendering. I am open to collaborations and discussions. Please feel free to reach out. :) Email / CV / Google Scholar / Github / Linkedin |
|
|
[June. 2026] One papers got accepted at CVPR 2026! |
|
My first-author papers are highlighted with a yellow background. |
|
|
Wonjoon Lee, Sungmin Woo, Donghyeong Kim, Jungho Lee, Sangheon Park, Sangyoun Lee IEEE/CVF Computer Vision and Pattern Recognition (CVPR), 2026 project page / arXiv We propose MoRGS, an efficient online per-Gaussian motion reasoning framework that explicitly models per-Gaussian motion to improve 4D reconstruction quality. |
|
Jungho Lee, Donghyeong Kim, Wonjoon Lee, Taeoh Kim, Dongyoon Wee, Sangyoun Lee IEEE/CVF International Conference on Computer Vision (ICCV), 2025 project page / arXiv We propose continous motion-aware blur kernel on 3D gaussian splatting utilizing 3D rigid transformation and neural ordinary differential function to reconstruct accurate 3D scene from blurry images with real-time rendering speed. |
|
|
Sungmin Woo*, Wonjoon Lee*, Woo Jin Kim, Dogyoon Lee, Sangyoun Lee IEEE/CVF European Conference on Computer Vision (ECCV), 2024 project page / arXiv We propose probabilistic framework for self-supervised multi-frame monocular depth estimation that mitigates dynamic scene inconsistencies by inferring motion-induced uncertainty and adaptively modulating the cost volume. |
|
Wonjoon Lee, Sungmin Woo, Donghyeong Kim, Sangyoun Lee IEEE International Conference on Image Processing (ICCV), 2023 project page / arXiv We propose two-stage 3D object detection framework that captures multiscale voxel relationships by constructing and aggregating graph features across different voxel resolutions for enhanced geometric reasoning. |
|
This website's source code is borrowed from Jon Barron's website template. Last updated February 2026. |