Lidar Based 3D Object Detection
Lidar-based 3D object detection aims to accurately identify and locate objects in three-dimensional space using lidar sensor data, crucial for applications like autonomous driving and robotics. Current research emphasizes improving the robustness and efficiency of detection models, focusing on techniques like point-voxel fusion, transformer networks, and various domain adaptation strategies to handle variations in lidar data across different environments and weather conditions. These advancements are driving significant improvements in the accuracy and speed of 3D object detection, leading to safer and more reliable autonomous systems.
Papers
Cost-Aware Evaluation and Model Scaling for LiDAR-Based 3D Object Detection
Xiaofang Wang, Kris M. Kitani
3D Object Detection with a Self-supervised Lidar Scene Flow Backbone
Ekim Yurtsever, Emeç Erçelik, Mingyu Liu, Zhijie Yang, Hanzhen Zhang, Pınar Topçam, Maximilian Listl, Yılmaz Kaan Çaylı, Alois Knoll