SCOPE: Scale-Consistent One-Pass Estimation of 3D Geometry
SIGGRAPH Conference Papers, 2026
Scale-consistent 3D geometry from long monocular videos in a single pass.
I am a PhD student in Computer Science at The University of Hong Kong, advised by Prof. Hengshuang Zhao.
My research focuses on 3D computer vision, video geometry, and self-supervised visual representation learning. I am interested in learning the structure of the 3D world from images and videos.
I have been a research intern at Ant Research, Alibaba DAMO Academy, and Shanghai AI Laboratory. I received my bachelor's degree in Automation from Harbin Institute of Technology in 2023.
I am looking for research positions in industry starting in 2027.
SIGGRAPH Conference Papers, 2026
Scale-consistent 3D geometry from long monocular videos in a single pass.
ICCV 2025 Highlight
Scene-consistent depth from individual frames, with reduced flicker across a video.
ECCV 2024
Pixel-aware density control improves Gaussian-splat reconstructions in sparsely initialized regions.