Papers
1
Total Citations
6
H-Index
1
About
Hao Qu is a researcher advancing the frontiers of self-supervised learning for autonomous systems, with a focus on egomotion estimation and depth perception. His most cited work, "SelfOdom: Self-Supervised Egomotion and Depth Learning via Bi-Directional Coarse-to-Fine Scale Recovery" (2023), tackles a critical challenge in autonomous driving and mobile robotics: accurately perceiving location and scene geometry from monocular images without expensive ground-truth labels. By introducing a bi-directional coarse-to-fine scale recovery mechanism, Qu’s method significantly improves the robustness and accuracy of self-supervised depth and motion estimation, addressing inherent scale ambiguity issues that have long plagued the field. This contribution has garnered 6 citations in a short time, reflecting its timely impact. Qu’s research sits at the intersection of computer vision, robotics, and deep learning, offering practical solutions for real-world deployment where labeled data is scarce. His work not only advances theoretical understanding but also holds promise for safer, more autonomous navigation in dynamic environments.
Research Focus
Key Achievements
Top Papers
- 1