Enze Xie

Papers

Total Citations

H-Index

About

Enze Xie is a prominent researcher working at the intersection of computer vision, robotics, and deep learning, with a particular focus on visual perception and scene understanding. His work spans monocular depth estimation, visual odometry, and autonomous navigation — areas that are critical for enabling machines to interpret and interact with the three-dimensional world using minimal sensor input. One of Xie's most recognized contributions is his 2022 framework for improving monocular visual odometry through learned depth estimation, a technically demanding problem given that monocular systems must infer 3D structure from a single camera without stereo or LiDAR support. By leveraging deep learning-based depth cues, his approach advances the accuracy and robustness of visual odometry systems across diverse real-world scenarios — a longstanding challenge in the robotics and computer vision communities. This work has already attracted 37 citations, reflecting its relevance and uptake among researchers tackling autonomous systems and mobile robotics. Xie's research addresses some of the most practically significant bottlenecks in making autonomous agents perceive their environments reliably, making his contributions valuable to students and professionals working in robotics, self-driving vehicles, and embodied AI applications.