Understanding the Robustness of 3D Object Detection with Bird'View Representations in Autonomous Driving

3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird's-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with camera inputs on popular benchmarks. However, there still lacks a * Equal Contribution. Corresponding authors. This work was done when Zijian Zhu and Hai Chen were visiting Tsinghua University.