Kunhong Li
Papers
1
Total Citations
15
H-Index
1
About
Kunhong Li is a researcher at the forefront of robotic perception and autonomous driving, specializing in sensor fusion and depth estimation. His major contributions center on developing efficient deep learning architectures that integrate complementary sensing modalities—particularly stereo cameras and LiDAR—to overcome the limitations of each individual sensor. His most notable work, "SLFNet: A Stereo and LiDAR Fusion Network for Depth Completion" (2022, 15 citations), introduces a novel fusion network that combines the dense texture information from stereo images with the sparse but precise depth measurements from LiDAR point clouds. This approach enables real-time prediction of dense, high-fidelity depth maps, a critical capability for safe navigation in autonomous vehicles and robust robotic manipulation. By addressing the challenge of acquiring accurate depth information under dynamic conditions, Li’s research directly impacts the reliability and efficiency of perception systems. His work is recognized for its practical engineering focus, bridging the gap between algorithmic innovation and real-world deployment in time-sensitive applications.
Research Focus
Key Achievements
Top Papers
- 1SLFNet: A Stereo and LiDAR Fusion Network for Depth Completion15 citations · 2022