This project implements state-of-the-art 3D object detection models for LiDAR point cloud data, including PointPillars, SECOND, and CenterPoint architectures. It provides a complete pipeline from data ...

Custom/: Primary entrance for users. Contains training, evaluation, configuration, and model definitions.

Robots and autonomous vehicles can use 3D point clouds from LiDAR sensors and camera images to perform 3D object detection. However, current techniques that combine both types of data struggle to ...

Abstract: Compared to monocular 3D object detection, stereo-based 3D methods offer significantly higher accuracy but still suffer from high computational overhead and latency. The state-of-the-art ...