Mid Range LiDAR
Mid-range LiDAR research focuses on improving the accuracy, efficiency, and robustness of light detection and ranging (LiDAR) systems for applications like autonomous navigation and 3D mapping. Current research emphasizes integrating LiDAR data with other sensor modalities (e.g., radar, cameras, IMUs) using techniques like sensor fusion and knowledge distillation, often within frameworks employing Gaussian splatting or Kalman filtering for improved performance. These advancements are significant for enhancing the reliability and capabilities of autonomous systems operating in complex and dynamic environments, particularly in challenging weather conditions or when dealing with non-line-of-sight scenarios.
Papers
LiHi-GS: LiDAR-Supervised Gaussian Splatting for Highway Driving Scene Reconstruction
Pou-Chun Kung, Xianling Zhang, Katherine A. Skinner, Nikita Jaipuria
PC-BEV: An Efficient Polar-Cartesian BEV Fusion Framework for LiDAR Semantic Segmentation
Shoumeng Qiu, Xinrun Li, XiangYang Xue, Jian Pu
SCKD: Semi-Supervised Cross-Modality Knowledge Distillation for 4D Radar Object Detection
Ruoyu Xu, Zhiyu Xiang, Chenwei Zhang, Hanzhi Zhong, Xijun Zhao, Ruina Dang, Peng Xu, Tianyu Pu, Eryun Liu