DALD-PCAC: Density-Adaptive Learning Descriptor for Point Cloud Lossless Attribute Compression

TL;DR

This paper introduces DALD-PCAC, a novel deep learning framework for lossless attribute compression of point clouds that adapts to varying densities using a density-aware descriptor and attention mechanisms.

Contribution

It proposes a density-adaptive learning descriptor and a permutation-invariant transformer for improved lossless attribute compression of point clouds with varying densities.

Findings

Achieves state-of-the-art compression performance on LiDAR and object point clouds.

Robust to varying point cloud densities, balancing performance and complexity.

Enhances point cloud attribute compression with a density-aware, attention-based approach.

Abstract

Recently, deep learning has significantly advanced the performance of point cloud geometry compression. However, the learning-based lossless attribute compression of point clouds with varying densities is under-explored. In this paper, we develop a learning-based framework, namely DALD-PCAC that leverages Levels of Detail (LoD) to tailor for point cloud lossless attribute compression. We develop a point-wise attention model using a permutation-invariant Transformer to tackle the challenges of sparsity and irregularity of point clouds during context modeling. We also propose a Density-Adaptive Learning Descriptor (DALD) capable of capturing structure and correlations among points across a large range of neighbors. In addition, we develop a prior-guided block partitioning to reduce the attribute variance within blocks and enhance the performance. Experiments on LiDAR and object point clouds show that DALD-PCAC achieves the state-of-the-art performance on most data. Our method boosts the compression performance and is robust to the varying densities of point clouds. Moreover, it guarantees a good trade-off between performance and complexity, exhibiting great potential in real-world applications. The source code is available at https://github.com/zb12138/DALD_PCAC.