English

Multi-Scale Occ: 4th Place Solution for CVPR 2023 3D Occupancy Prediction Challenge

Computer Vision and Pattern Recognition 2023-06-21 v1

Abstract

In this report, we present the 4th place solution for CVPR 2023 3D occupancy prediction challenge. We propose a simple method called Multi-Scale Occ for occupancy prediction based on lift-splat-shoot framework, which introduces multi-scale image features for generating better multi-scale 3D voxel features with temporal fusion of multiple past frames. Post-processing including model ensemble, test-time augmentation, and class-wise thresh are adopted to further boost the final performance. As shown on the leaderboard, our proposed occupancy prediction method ranks the 4th place with 49.36 mIoU.

Keywords

Cite

@article{arxiv.2306.11414,
  title  = {Multi-Scale Occ: 4th Place Solution for CVPR 2023 3D Occupancy Prediction Challenge},
  author = {Yangyang Ding and Luying Huang and Jiachen Zhong},
  journal= {arXiv preprint arXiv:2306.11414},
  year   = {2023}
}

Comments

The 4th place solution report for CVPR 2023 3D Occupancy Prediction Challenge

R2 v1 2026-06-28T11:09:28.701Z