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 reducant 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：三维占用预测因其卓越的几何感知与通用物体识别能力，在自动驾驶领域引起了广泛关注。为实现此目标，现有工作尝试构建从鸟瞰感知延伸而来的三视角（TPV）或占用（OCC）表示。然而，TPV表示等压缩视图会丢失三维几何信息，而原始稀疏的OCC表示虽无需压缩，却需要大量冗余计算成本。针对上述局限，我们提出紧凑占用Transformer（COTR），通过几何感知的占用编码器与语义感知的分组解码器，重构紧凑的三维OCC表示。占用编码器首先通过高效的显式-隐式视图变换生成紧凑的几何OCC特征；随后，占用解码器采用由粗到细的语义分组策略，进一步增强紧凑OCC表示的语义辨别能力。实验表明，该方法在多个基线上均取得显著性能提升，例如COTR相比基线获得8%-15%的相对改进，证明了我们方法的优越性。