ECM-OPCC: Efficient Context Model for Octree-based Point Cloud Compression

TL;DR

This paper introduces an efficient deep learning-based octree point cloud compression method that leverages a dual transformer architecture and a novel coding strategy, achieving state-of-the-art results with significantly reduced decoding time.

Contribution

It proposes a new context model and deep learning codec that balances compression performance and decoding efficiency for octree-based point cloud compression.

Findings

Achieves state-of-the-art compression performance for lossy and lossless scenarios.

Reduces decoding time by 98% compared to previous methods.

Utilizes a dual transformer architecture with a window-constrained multi-group coding strategy.

Abstract

Recently, deep learning methods have shown promising results in point cloud compression. For octree-based point cloud compression, previous works show that the information of ancestor nodes and sibling nodes are equally important for predicting current node. However, those works either adopt insufficient context or bring intolerable decoding complexity (e.g. >600s). To address this problem, we propose a sufficient yet efficient context model and design an efficient deep learning codec for point clouds. Specifically, we first propose a window-constrained multi-group coding strategy to exploit the autoregressive context while maintaining decoding efficiency. Then, we propose a dual transformer architecture to utilize the dependency of current node on its ancestors and siblings. We also propose a random-masking pre-train method to enhance our model. Experimental results show that our approach achieves state-of-the-art performance for both lossy and lossless point cloud compression. Moreover, our multi-group coding strategy saves 98% decoding time compared with previous octree-based compression method.