4DAC: Learning Attribute Compression for Dynamic Point Clouds

TL;DR

This paper introduces 4DAC, a learning-based framework for compressing dynamic point cloud attributes by leveraging deep neural networks for motion estimation, residual encoding, and entropy modeling, achieving superior compression results.

Contribution

The paper presents a novel deep learning framework for attribute compression in dynamic point clouds, integrating motion estimation, residual encoding, and entropy modeling.

Findings

Outperforms existing methods in compression efficiency

Effectively leverages temporal correlations in point cloud sequences

Demonstrates superior results on public datasets

Abstract

With the development of the 3D data acquisition facilities, the increasing scale of acquired 3D point clouds poses a challenge to the existing data compression techniques. Although promising performance has been achieved in static point cloud compression, it remains under-explored and challenging to leverage temporal correlations within a point cloud sequence for effective dynamic point cloud compression. In this paper, we study the attribute (e.g., color) compression of dynamic point clouds and present a learning-based framework, termed 4DAC. To reduce temporal redundancy within data, we first build the 3D motion estimation and motion compensation modules with deep neural networks. Then, the attribute residuals produced by the motion compensation component are encoded by the region adaptive hierarchical transform into residual coefficients. In addition, we also propose a deep conditional entropy model to estimate the probability distribution of the transformed coefficients, by incorporating temporal context from consecutive point clouds and the motion estimation/compensation modules. Finally, the data stream is losslessly entropy coded with the predicted distribution. Extensive experiments on several public datasets demonstrate the superior compression performance of the proposed approach.