English

COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction

Computer Vision and Pattern Recognition 2024-04-12 v2

Abstract

The autonomous driving community has shown significant interest in 3D occupancy prediction, driven by its exceptional geometric perception and general object recognition capabilities. To achieve this, current works try to construct a Tri-Perspective View (TPV) or Occupancy (OCC) representation extending from the Bird-Eye-View perception. However, compressed views like TPV representation lose 3D geometry information while raw and sparse OCC representation requires heavy but redundant computational costs. To address the above limitations, we propose Compact Occupancy TRansformer (COTR), with a geometry-aware occupancy encoder and a semantic-aware group decoder to reconstruct a compact 3D OCC representation. The occupancy encoder first generates a compact geometrical OCC feature through efficient explicit-implicit view transformation. Then, the occupancy decoder further enhances the semantic discriminability of the compact OCC representation by a coarse-to-fine semantic grouping strategy. Empirical experiments show that there are evident performance gains across multiple baselines, e.g., COTR outperforms baselines with a relative improvement of 8%-15%, demonstrating the superiority of our method.

Keywords

Cite

@article{arxiv.2312.01919,
  title  = {COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction},
  author = {Qihang Ma and Xin Tan and Yanyun Qu and Lizhuang Ma and Zhizhong Zhang and Yuan Xie},
  journal= {arXiv preprint arXiv:2312.01919},
  year   = {2024}
}

Comments

CVPR2024. Code is available at https://github.com/NotACracker/COTR

R2 v1 2026-06-28T13:40:23.430Z