Nan Zou
Papers
2
Total Citations
30
H-Index
2
About
Nan Zou is a researcher advancing the frontier of scene understanding, with key contributions in computer vision, 3D reconstruction, and autonomous perception. Her work bridges semantic and geometric reasoning, most notably through her highly cited 2020 paper on simultaneous semantic segmentation and depth completion, which enforces boundary constraints to improve accuracy in tasks critical for robot navigation, AR/VR, and autonomous driving. This work has garnered 20 citations, reflecting its impact on integrating two core scene-parsing tasks. In earlier research, Zou tackled 3D reconstruction using a single-camera multi-mirror catadioptric system, achieving multi-stereo depth estimation from a single shot—a cost-effective solution for robotics and surveillance. Her 2019 paper on this system has earned 10 citations, demonstrating its value for large field-of-view applications. By combining semantic and geometric cues, Zou’s work enables more robust environmental perception, directly supporting real-world systems that must understand both what and where objects are. Her research is particularly notable for its practical focus on boundary-aware learning and efficient sensor design, making her a rising voice in the intersection of computer vision and autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2