Anning Hu
Papers
1
Total Citations
7
H-Index
1
About
Anning Hu is a leading researcher in autonomous driving perception, with a focus on advancing sensor fusion and depth estimation technologies. Their work bridges the gap between stereo cameras and LiDAR systems, addressing critical challenges in robotic and vehicular perception. Hu’s most-cited paper, “Stereo-LiDAR Depth Estimation with Deformable Propagation and Learned Disparity-Depth Conversion” (2024, 7 citations), introduces a novel framework that overcomes limitations of sparse LiDAR point clouds in stereo matching. By proposing deformable propagation for cost aggregation and a learned disparity-depth conversion module, Hu’s method achieves accurate, dense depth maps—a breakthrough for real-world applications like autonomous navigation. This work tackles the fundamental issue of non-uniform LiDAR data distribution, enhancing reliability in dynamic environments. Hu’s contributions are pivotal for the next generation of perception systems, where robust depth estimation is critical. Their research continues to influence both academic studies and industry implementations, marking them as a rising innovator in computer vision and robotics.
Research Focus
Key Achievements
Top Papers
- 1