快速前馈3D高斯泼溅压缩
Fast Feedforward 3D Gaussian Splatting Compression
- Shanghai Jiao Tong University（上海交通大学）
- Monash University（莫纳什大学）
- Shanghai University（上海大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出FCGS，一种无需优化的前馈模型，通过多路径熵模块和上下文模型在单次传递中快速压缩3DGS，实现超20倍压缩比并保持高保真度。
AI中文摘要：
随着3D高斯泼溅（3DGS）在新视角合成中推进实时和高保真渲染，存储需求对其广泛采用构成了挑战。尽管已提出多种压缩技术，现有方法存在一个共同局限：对于任何已有的3DGS，都需要逐场景优化才能实现压缩，导致压缩过程迟缓而缓慢。为解决这一问题，我们提出了3D高斯泼溅快速压缩（FCGS），这是一种无需优化的模型，能够在单次前馈传递中快速压缩3DGS表示，从而将压缩时间从数分钟显著缩短至数秒。为提高压缩效率，我们提出了一种多路径熵模块，将高斯属性分配到不同的熵约束路径，以在体积与保真度之间取得平衡。我们还精心设计了高斯间和高斯内上下文模型，以消除非结构化高斯团块之间的冗余。总体而言，FCGS在保持保真度的同时实现了超过20倍的压缩比，超越了大多数逐场景最先进的基于优化的方法。我们的代码可在以下地址获取：https://github.com/YihangChen-ee/FCGS。
英文摘要：
With 3D Gaussian Splatting (3DGS) advancing real-time and high-fidelity rendering for novel view synthesis, storage requirements pose challenges for their widespread adoption. Although various compression techniques have been proposed, previous art suffers from a common limitation: for any existing 3DGS, per-scene optimization is needed to achieve compression, making the compression sluggish and slow. To address this issue, we introduce Fast Compression of 3D Gaussian Splatting (FCGS), an optimization-free model that can compress 3DGS representations rapidly in a single feed-forward pass, which significantly reduces compression time from minutes to seconds. To enhance compression efficiency, we propose a multi-path entropy module that assigns Gaussian attributes to different entropy constraint paths for balance between size and fidelity. We also carefully design both inter- and intra-Gaussian context models to remove redundancies among the unstructured Gaussian blobs. Overall, FCGS achieves a compression ratio of over 20X while maintaining fidelity, surpassing most per-scene SOTA optimization-based methods. Our code is available at: https://github.com/YihangChen-ee/FCGS.
