This technical report summarizes the winning solution for the 3D Occupancy Prediction Challenge, which is held in conjunction with the CVPR 2023 Workshop on End-to-End Autonomous Driving and CVPR 23 Workshop on Vision-Centric Autonomous Driving Workshop. Our proposed solution FB-OCC builds upon FB-BEV, a cutting-edge camera-based bird's-eye view perception design using forward-backward projection. On top of FB-BEV, we further study novel designs and optimization tailored to the 3D occupancy prediction task, including joint depth-semantic pre-training, joint voxel-BEV representation, model scaling up, and effective post-processing strategies. These designs and optimization result in a state-of-the-art mIoU score of 54.19% on the nuScenes dataset, ranking the 1st place in the challenge track. Code and models will be released at: https://github.com/NVlabs/FB-BEV.
@article{arxiv.2307.01492,
title = {FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformation},
author = {Zhiqi Li and Zhiding Yu and David Austin and Mingsheng Fang and Shiyi Lan and Jan Kautz and Jose M. Alvarez},
journal= {arXiv preprint arXiv:2307.01492},
year = {2023}
}
Comments
Outstanding Champion and Innovation Award in the 3D Occupancy Prediction Challenge (CVPR23)