Please explain Bird's eye view in the KITTI test set performance evaluation table in the VoxelNet paper

Question

I read this paper VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection (https://arxiv.org/abs/1711.06396) and I don't know what BEV means in the table. enter image description here

I also asked ChatGPT, but I don't quite understand what he's saying. enter image description here

I'd appreciate it if you could let me know. thank you