Zhuwen Li

Papers

Total Citations

H-Index

About

Zhuwen Li is a leading researcher in computer vision, with a primary focus on 3D scene understanding, depth estimation, and geometric deep learning. His most impactful work tackles the fundamental challenge of inferring dense 3D structure from monocular video—a capability that could enable billions of single-camera devices and robots to perceive the world in three dimensions. In his highly cited 2020 paper, "Video Depth Estimation by Fusing Flow-to-Depth Proposals," Li introduced a novel model that integrates a flow-to-depth layer, a camera pose refinement module, and a depth fusion network. This work, which has garnered 21 citations, demonstrates how optical flow can be leveraged to generate robust depth proposals from video, significantly advancing the state of the art in dynamic scene reconstruction. Li’s contributions are particularly notable for their practical impact on autonomous systems, augmented reality, and robotics, where accurate depth from affordable hardware is critical. His research continues to push the boundaries of how machines learn to see and navigate the world in 3D.