解决3D占据预测中头尾类分布不均问题，提升精度与效率
SHTOcc: Effective 3D Occupancy Prediction with Sparse Head and Tail Voxels
- 通过稀疏头尾体素构建，精准识别关键体素
- 降低42.2%显存占用，推理速度提升58.6%，准确率提高7%
- 适合追求高效高精度3D感知的自动驾驶系统
3D占据预测在自动驾驶领域备受关注，因其具备强大的几何感知与目标识别能力。然而，现有方法未充分探索体素的类别分布与几何分布特性，导致性能受限。本文首次分析体素的类间分布与几何分布，针对性解决由类间分布引发的长尾问题及几何分布带来的性能下降。提出SHTOcc（Sparse Head-Tail Occupancy）方法，采用稀疏头尾体素构建，精准识别并平衡头类与尾类关键体素；同时使用解耦学习机制，减轻模型对主导类（头类）的偏倚，强化对尾类的关注。实验表明，在多个基线模型上取得显著提升：显存使用减少42.2%，推理速度提升58.6%，准确率提高约7%，验证了其有效性与高效性。代码已开源。
原文摘要 · Abstract (English)
3D occupancy prediction has attracted much attention in the field of autonomous driving due to its powerful geometric perception and object recognition capabilities. However, existing methods have not explored the most essential distribution patterns of voxels, resulting in unsatisfactory results. This paper first explores the inter-class distribution and geometric distribution of voxels, thereby solving the long-tail problem caused by the inter-class distribution and the poor performance caused by the geometric distribution. Specifically, this paper proposes SHTOcc (Sparse Head-Tail Occupancy), which uses sparse head-tail voxel construction to accurately identify and balance key voxels in the head and tail classes, while using decoupled learning to reduce the model's bias towards the dominant (head) category and enhance the focus on the tail class. Experiments show that significant improvements have been made on multiple baselines: SHTOcc reduces GPU memory usage by 42.2%, increases inference speed by 58.6%, and improves accuracy by about 7%, verifying its effectiveness and efficiency. The code is available at https://github.com/ge95net/SHTOcc
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。