Structure-Aware and Context-Modeling Point Cloud Compression

Abstract

To address the limited geometric representation capability and the coarse-grained context modeling in learning-based point cloud compression for LiDAR point cloud coding, we propose a structure-aware and context-modeling point cloud compression method (SACM-PCC). On the representation learning side, we design a Structure-Aware Target Embedding module to achieve structural alignment and effective propagation of cross-scale voxel features, thereby enhancing the expression of geometric relationships from local to global. On the probabilistic modeling side, we build a progressive bitwise target occupancy predictor that adopts a conditional autoregressive strategy to decompose each 8-bit occupancy code into four sub-codes and progressively refine the probability estimation from the most significant bits to the least significant bits, improving spatial context utilization and bit-level discrimination accuracy. Experiments on the KITTI and Ford datasets show that, at comparable reconstruction quality, SACM-PCC reduces the bitrate on KITTI by approximately 57%, 21%, and 8.7% relative to Draco, G-PCCv23, and RENO, respectively, and by approximately 54%, 21.7%, and 9% on Ford. These results demonstrate that the proposed method achieves a better rate–distortion trade-off across the full bitrate range while maintaining stable geometric reconstruction performance in complex scenes.