LOD-PCAC: Level-of-Detail-Based Deep Lossless Point Cloud Attribute Compression

Abstract

Point cloud attribute compression is a challenging issue in efficiently compressing large volumes of attributes. Despite notable advancements in lossy point cloud compression using deep learning, progress in lossless compression remains limited. Some methods have employed octree- or voxel-based partitioning techniques derived from geometric compression, achieving success on dense point clouds. However, these voxel-based approaches struggle with sparse or unevenly distributed point clouds, leading to performance degradation. In this work, we introduce a novel framework for learning-based lossless point cloud attribute compression, named LOD-PCAC, which leverages a Level-of-Detail (LOD) structure to ensure density-robust compression. Specifically, the input point cloud is divided into multiple detail levels, and vertices from these levels are selected to construct a Reference Set as context, which effectively captures multi-level information. Then we propose the Bit-level Residual Coder for efficient attribute compression. Instead of directly compressing attributes, our method first predicts attribute values and organizes the residual bits into a Bit Matrix as another context, simplifying predictions and fully exploiting channel correlations. Finally, a neural network with specialized encoders processes the context to estimate the probability of each residual bit. Experimental results demonstrate that the proposed method outperforms both traditional and learning-based approaches across various point clouds, exhibiting strong generalization across datasets and robustness to varying densities.