DeepRAHT: Learning Predictive RAHT for Point Cloud Attribute Compression

2026-01-18

AI Summary

This work proposes DeepRAHT, the first method to integrate the traditional Region-Adaptive Hierarchical Transform (RAHT) into an end-to-end learnable framework for point cloud attribute compression. By leveraging sparse tensors, DeepRAHT enables reconstruction learning without requiring preprocessing, and introduces a learnable prediction model coupled with a run-length coding entropy model. This design supports variable-rate control while guaranteeing a performance lower bound. Experimental results demonstrate that DeepRAHT significantly outperforms existing approaches in compression efficiency, decoding speed, and robustness, thereby achieving the first effective fusion of RAHT with deep learning for point cloud compression.

Technology Category

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

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Point Cloud Attribute Compression
• RAHT
• Deep Learning
• Variable-rate Coding
• Lossy Compression

Innovation

• DeepRAHT
• Predictive RAHT
• Point Cloud Attribute Compression
• Learnable Transform
• Variable-rate Coding