End-to-end learned Lossy Dynamic Point Cloud Attribute Compression

TL;DR

This paper presents an end-to-end learned lossy attribute compression method for point clouds that outperforms traditional techniques by leveraging high-dimensional convolutions and context modeling, achieving significant bitrate savings.

Contribution

It introduces a novel deep learning-based attribute compression framework using high-dimensional convolutions and auto-regressive context models, improving efficiency and compression performance.

Findings

Achieves 38.1% Bjontegaard Delta-rate savings over MPEG's core method.

Demonstrates superior performance on standard point cloud datasets.

Ensures low-complexity encoding and decoding processes.

Abstract

Recent advancements in point cloud compression have primarily emphasized geometry compression while comparatively fewer efforts have been dedicated to attribute compression. This study introduces an end-to-end learned dynamic lossy attribute coding approach, utilizing an efficient high-dimensional convolution to capture extensive inter-point dependencies. This enables the efficient projection of attribute features into latent variables. Subsequently, we employ a context model that leverage previous latent space in conjunction with an auto-regressive context model for encoding the latent tensor into a bitstream. Evaluation of our method on widely utilized point cloud datasets from the MPEG and Microsoft demonstrates its superior performance compared to the core attribute compression module Region-Adaptive Hierarchical Transform method from MPEG Geometry Point Cloud Compression with 38.1% Bjontegaard Delta-rate saving in average while ensuring a low-complexity encoding/decoding.