DeepRAHT: Learning Predictive RAHT for Point Cloud Attribute Compression

TL;DR

DeepRAHT introduces an end-to-end deep learning framework for point cloud attribute compression that integrates RAHT transforms, predictive modeling, and variable-rate coding, achieving superior performance and robustness.

Contribution

It presents a novel deep learning-based RAHT framework that performs transforms within the learning process, incorporating predictive modeling and bitrate proxy for improved compression.

Findings

Outperforms baseline methods in speed and robustness

Achieves lower bitrates with predictive RAHT

Provides a reversible, distortion-controllable compression framework

Abstract

Regional Adaptive Hierarchical Transform (RAHT) is an effective point cloud attribute compression (PCAC) method. However, its application in deep learning lacks research. In this paper, we propose an end-to-end RAHT framework for lossy PCAC based on the sparse tensor, called DeepRAHT. The RAHT transform is performed within the learning reconstruction process, without requiring manual RAHT for preprocessing. We also introduce the predictive RAHT to reduce bitrates and design a learning-based prediction model to enhance performance. Moreover, we devise a bitrate proxy that applies run-length coding to entropy model, achieving seamless variable-rate coding and improving robustness. DeepRAHT is a reversible and distortion-controllable framework, ensuring its lower bound performance and offering significant application potential. The experiments demonstrate that DeepRAHT is a high-performance, faster, and more robust solution than the baseline methods. Project Page: https://github.com/zb12138/DeepRAHT.