Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformation

About

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.

Zhiqi Li, Zhiding Yu, David Austin, Mingsheng Fang, Shiyi Lan, Jan Kautz, Jose M. Alvarez• 2023

Related benchmarks

TaskDatasetResultRank
3D Occupancy PredictionOcc3D-nuScenes (val)
mIoU52.79
144
Semantic Occupancy PredictionOcc3D (val)
mIoU42.1
37
3D Semantic Occupancy PredictionSurroundOcc (val)
mIoU19.6
36
3D Semantic Occupancy PredictionOcc3D
RayIoU39.8
34
3D Semantic Occupancy PredictionSurroundOcc-nuScenes (val)
IoU31.5
31
Occupancy PredictionOcc3D v1.0 (test)
RayIoU (Default)39
24
3D Occupancy and Occupancy FlowOpenOcc (val)
OccScore39.2
10
3D Occupancy PredictionOcc3D CVPR2023 Occupancy Challenge
mIoU40.7
6
3D Scene ReconstructionnuScenes (val)
Abs Rel0.342
5
Showing 9 of 9 rows

Other info

Code

Follow for update