为3DGS压缩引入可训练的分层稀疏变换编码，提升压缩效率与解码速度。
Learning Hierarchical Sparse Transform Coding for 3DGS Compression
- 采用分层设计：先用KLT去相关，再用稀疏感知神经变换重建残差。
- 在相同质量下，比当前最优方法降低12.3%码率，解码速度提升35%。
- 适合追求高效压缩与快速解码的3D内容应用，如VR/AR传输。
当前3DGS压缩方法普遍忽略神经分析-合成变换这一学习信号压缩中的关键组件，导致冗余消除完全依赖熵编码器，过度负担其性能并降低率失真（R-D）表现。为解决这一核心缺陷，我们提出一种训练时变换编码（TTC）方法，将分析-合成变换引入系统，并与3DGS表示和熵模型联合优化。具体地，采用分层设计：首先使用通道级KLT实现去相关与能量集中，随后通过稀疏感知神经变换以极小参数和计算开销重构KLT残差。实验表明，该方法在保持快速解码的同时显著提升率失真性能，相较当前最优3DGS压缩器，在同等质量下实现12.3%的码率降低，解码速度提升35%，展现出更优的BD-rate-解码时间权衡。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。