Robust Multi-generation Learned Compression of Point Cloud Attribute

TL;DR

This paper introduces novel constraints and training strategies to improve the robustness of learned point cloud attribute compression across multiple generations, addressing cumulative distortion issues.

Contribution

It proposes three new constraints—Mapping Idempotency, Transformation Reversibility, and Latent Variable Consistency—to enhance multi-generation robustness in learned point cloud compression.

Findings

Effectively suppresses multi-generation loss

Maintains single-pass rate-distortion performance

Validates on Owlii and 8iVFB datasets

Abstract

Existing learned point cloud attribute compression methods primarily focus on single-pass rate-distortion optimization, while overlooking the issue of cumulative distortion in multi-generation compression scenarios. This paper, for the first time, investigates the multi-generation issue in learned point cloud attribute compression. We identify two primary factors contributing to quality degradation in multi-generation compression: quantization-induced non-idempotency and transformation irreversibility. To address the former, we propose a Mapping Idempotency Constraint, that enables the network to learn the complete compression-decompression mapping, enhancing its robustness to repeated processes. To address the latter, we introduce a Transformation Reversibility Constraint, which preserves reversible information flow via a quantization-free training path. Further, we propose a Latent Variable Consistency Constraint which enhances the multi-generation compression robustness by incorporating a decompression-compression cross-generation path and a latent variable consistency loss term. Extensive experiments conducted on the Owlii and 8iVFB datasets verify that the proposed methods can effectively suppress multi-generation loss while maintaining single-pass rate-distortion performance comparable to baseline models.