Rate-distortion Optimized Point Cloud Preprocessing for Geometry-based Point Cloud Compression

TL;DR

This paper introduces a novel preprocessing framework that combines a learning-based voxelization network with a differentiable surrogate model of G-PCC, significantly improving compression efficiency while maintaining compatibility and low computational overhead.

Contribution

It proposes a rate-distortion optimized preprocessing method for G-PCC using a differentiable surrogate model and a learning-based voxelization network, enhancing compression performance without decoder modifications.

Findings

38.84% average BD-rate reduction over G-PCC

Effective end-to-end optimization of point cloud compression

No additional computational overhead during inference

Abstract

Geometry-based point cloud compression (G-PCC), an international standard designed by MPEG, provides a generic framework for compressing diverse types of point clouds while ensuring interoperability across applications and devices. However, G-PCC underperforms compared to recent deep learning-based PCC methods despite its lower computational power consumption. To enhance the efficiency of G-PCC without sacrificing its interoperability or computational flexibility, we propose a novel preprocessing framework that integrates a compression-oriented voxelization network with a differentiable G-PCC surrogate model, jointly optimized in the training phase. The surrogate model mimics the rate-distortion behaviour of the non-differentiable G-PCC codec, enabling end-to-end gradient propagation. The versatile voxelization network adaptively transforms input point clouds using learning-based voxelization and effectively manipulates point clouds via global scaling, fine-grained pruning, and point-level editing for rate-distortion trade-offs. During inference, only the lightweight voxelization network is appended to the G-PCC encoder, requiring no modifications to the decoder, thus introducing no computational overhead for end users. Extensive experiments demonstrate a 38.84% average BD-rate reduction over G-PCC. By bridging classical codecs with deep learning, this work offers a practical pathway to enhance legacy compression standards while preserving their backward compatibility, making it ideal for real-world deployment.