LEE Gim Hee

COM2-03-54

651 62214

www.comp.nus.edu.sg/~leegh

Associate Professor

Dr.sc. (Computer Science, ETH Zurich)
M.Eng. (Mechanical Engineering, National University of Singapore)
B.Eng. (Mechanical Engineering, 1st Class Honors, National University of Singapore)

Hi there! I am working at the intersection of 3D Computer Vision, Robotics, and Machine Learning. My research focuses on spatial and physical intelligence: enabling machines to perceive, understand, and interact with the 3D world. We study problems in 3D scene understanding, neural 3D modeling, multiview geometry, robot perception, and embodied AI, with the goal of building intelligent agents that can reason and act robustly in complex real-world environments. I am always looking for motivated and talented students. If you are equally excited about the future of 3D vision, robotics, and embodied intelligence, please feel free to reach out!

RESEARCH AREAS

Media

Artificial Intelligence

RESEARCH INTERESTS

Computer Vision
Robotic Perception
Machine Learning

RESEARCH PROJECTS

Acquiring High Quality Datasets for Dynamic Scene Reconstruction and Event Cameras in Motions

The project addresses limitations in reconstructing dynamic 3D scenes and static scenes from event cameras. It aims to acquire datasets for indoor scenes with moving objects and high-speed rendering, advancing neural scene representation in these scenarios through public release.

Media

RESEARCH GROUPS

TEACHING INNOVATIONS

SELECTED PUBLICATIONS

Yunsong Wang, Gim Hee Lee, Flow4DGS-SLAM: Optical Flow-Guided 4D Gaussian Splatting SLAM, In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2026
Haoran Zhou, Gim Hee Lee, MotionScale: Reconstructing Appearance, Geometry, and Motion of Dynamic Scenes with Scalable 4D Gaussian Splatting , In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2026.
Suyi Jiang, Gim Hee Lee, PhysHO: Physics-Based Dynamic 3D Gaussian Human and Object from Monocular Video , In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2026.
Zihan Wang, Seungjun Lee, Guangzhao Dai, Gim Hee Lee, D3D-VLP: Dynamic 3D Vision-Language-Planning Model for Embodied Grounding and Navigation , In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2026.
Stefan Lionar, Gim Hee Lee, TeamHOI: Learning a Unified Policy for Cooperative Human-Object Interactions with Any Team Size, In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2026.