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

2026-01-18

ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)

AI Summary

This work proposes a deep learning-based multi-level-of-detail (LoD) compression framework to address the limited performance of lossless attribute compression for point clouds under varying densities. The method employs a permutation-invariant Transformer to model point-wise attention, integrating a density-adaptive learned descriptor (DALD) with a prior-guided block partitioning strategy to effectively capture the sparsity and irregularity inherent in point cloud data. Evaluated on both LiDAR and object point cloud datasets, the proposed approach achieves state-of-the-art lossless compression performance, significantly improving robustness to density variations while maintaining computational efficiency and enhancing overall compression effectiveness.

Technology Category

• Data Mining & Knowledge Management: Data Compression
• Machine Learning: Learning on the Edge & Model Compression
• Computer Vision: Diffusion Models for Vision

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

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.

Problem

• point cloud
• lossless attribute compression
• varying densities
• sparsity
• irregularity

Innovation

• Density-Adaptive Learning Descriptor
• Point Cloud Compression
• Permutation-Invariant Transformer
• Levels of Detail
• Lossless Attribute Compression