Chenyang Lei

Hong Kong University of Science and Technology

Papers

Total Citations

H-Index

About

Chenyang Lei is a researcher at the forefront of 3D computer vision and scene understanding, with a focus on enabling machines to perceive depth and color from minimal visual data. His major contributions lie in monocular video depth estimation and point cloud colorization. In his highly cited 2020 work, "Video Depth Estimation by Fusing Flow-to-Depth Proposals" (21 citations), Lei introduced a novel model that leverages optical flow and camera pose refinement to extract dense depth from single-camera video, a breakthrough that could empower billions of devices and robots with 3D vision using only a standard camera. More recently, in his 2023 paper "Scene-level Point Cloud Colorization with Semantics-and-geometry-aware Networks" (2 citations), he tackles the challenge of adding realistic color to uncolored 3D point clouds—a common problem in robotics and visualization. By integrating semantic and geometric cues, his approach produces vivid, context-aware colorizations that enhance both human interpretation and downstream tasks. Lei’s work bridges the gap between raw sensor data and rich, human-interpretable 3D scenes, making him a rising voice in practical, deployable computer vision.