Kangkang Hu
Papers
1
Total Citations
16
H-Index
1
About
Kangkang Hu is a leading researcher in robotic perception and 3D reconstruction, with a focus on leveraging polarization imaging to enhance dense mapping for autonomous systems. His most cited work, "Polarimetric Monocular Dense Mapping Using Relative Deep Depth Prior" (2021, 16 citations), introduces a novel approach that fuses polarimetric cues—specifically surface normal information derived from azimuth and zenith angles—with deep learning-based relative depth priors. This method enables a monocular camera to reconstruct dense, high-fidelity 3D maps, overcoming traditional limitations in textureless or low-light environments. Hu's contributions bridge the gap between physics-based vision and modern deep learning, offering a robust solution for real-time robotic navigation and scene understanding. His work has been recognized for its practical impact in autonomous driving and augmented reality, where accurate depth estimation is critical. By demonstrating how polarization data can complement conventional RGB inputs, Hu has opened new pathways for cost-effective, sensor-rich mapping systems. His research continues to inspire advances in polarimetric computer vision, making him a notable figure in the field.
Research Focus
Key Achievements
Top Papers
- 1Polarimetric Monocular Dense Mapping Using Relative Deep Depth Prior16 citations · 2021