OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction
This work addresses vision-based perception for autonomous driving by advancing from bird-eye-view to 3D semantic occupancy, offering incremental improvements in accuracy and efficiency.
The paper tackles 3D semantic occupancy prediction for autonomous driving by proposing OccFormer, a dual-path transformer network that processes 3D voxel features, achieving significant performance improvements over existing methods on SemanticKITTI and nuScenes datasets.
The vision-based perception for autonomous driving has undergone a transformation from the bird-eye-view (BEV) representations to the 3D semantic occupancy. Compared with the BEV planes, the 3D semantic occupancy further provides structural information along the vertical direction. This paper presents OccFormer, a dual-path transformer network to effectively process the 3D volume for semantic occupancy prediction. OccFormer achieves a long-range, dynamic, and efficient encoding of the camera-generated 3D voxel features. It is obtained by decomposing the heavy 3D processing into the local and global transformer pathways along the horizontal plane. For the occupancy decoder, we adapt the vanilla Mask2Former for 3D semantic occupancy by proposing preserve-pooling and class-guided sampling, which notably mitigate the sparsity and class imbalance. Experimental results demonstrate that OccFormer significantly outperforms existing methods for semantic scene completion on SemanticKITTI dataset and for LiDAR semantic segmentation on nuScenes dataset. Code is available at \url{https://github.com/zhangyp15/OccFormer}.