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.

翻译：摘要：自动驾驶领域对3D占用预测展现出显著兴趣，这得益于其卓越的几何感知能力和通用目标识别能力。为实现这一目标，现有工作尝试构建从鸟瞰感知扩展而来的三视角或占用表示。然而，三视角表示等压缩视图会丢失3D几何信息，而原始稀疏的占用表示则需要高昂且冗余的计算成本。针对上述限制，我们提出了紧凑占用Transformer（COTR），其配备了几何感知的占用编码器和语义感知的组解码器，以重建紧凑的3D占用表示。占用编码器首先通过高效的显式-隐式视图转换生成紧凑的几何占用特征。随后，占用解码器通过由粗到细的语义分组策略，进一步增强紧凑占用表示的语义判别能力。实证实验表明，该方法在多个基线上实现了显著性能提升，例如COTR相比基线取得了8%-15%的相对改进，证明了我们方法的优越性。