Learning Hierarchical Sparse Transform Coding for 3DGS Compression

TL;DR

This paper introduces a hierarchical neural transform coding method for 3DGS compression that jointly optimizes analysis-synthesis transforms, significantly improving rate-distortion performance and decoding speed.

Contribution

It proposes a novel training-time transform coding approach with hierarchical design, integrating neural transforms into 3DGS compression for better redundancy removal.

Findings

Achieves superior rate-distortion performance over state-of-the-art methods.

Provides faster decoding with a favorable trade-off between BD-rate and decoding time.

Utilizes a hierarchical design combining KLT and neural transforms for effective decorrelation.

Abstract

Current 3DGS compression methods largely forego the neural analysis-synthesis transform, which is a crucial component in learned signal compression systems. As a result, redundancy removal is left solely to the entropy coder, overburdening the entropy coding module and reducing rate-distortion (R-D) performance. To fix this critical omission, we propose a training-time transform coding (TTC) method that adds the analysis-synthesis transform and optimizes it jointly with the 3DGS representation and entropy model. Concretely, we adopt a hierarchical design: a channel-wise KLT for decorrelation and energy compaction, followed by a sparsity-aware neural transform that reconstructs the KLT residuals with minimal parameter and computational overhead. Experiments show that our method delivers strong R-D performance with fast decoding, offering a favorable BD-rate-decoding-time trade-off over SOTA 3DGS compressors.