发表机构
Fraunhofer HHI; Humboldt-Universität zu Berlin; Technische Universität Berlin（弗劳恩霍夫海因里希·赫兹研究所; 柏林洪堡大学; 柏林工业大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
KISS-GS是将压缩与训练解耦的模块化3DGS压缩流程，结合剪枝、SOG-XT编码等技术实现85-319倍压缩，解码依赖Web原生图像格式，率失真性能优于紧密集成方法。
AI 中文摘要
使用3D高斯溅射（3DGS）进行场景重建已十分普遍，但部署仍存在困难，因为未压缩文件的体积可能非常庞大。当前的3DGS压缩系统结合了多种减小文件体积的策略，这会导致压缩增益的来源不明确，并限制组件在不同训练流程中的复用。为使增益更透明，我们提出KISS-GS，这是一个遵循“保持简单”原则的模块化压缩流程，设计目的是将压缩完全与训练解耦。给定一个用普通3DGS重建的3DGS场景，我们通过结合最先进的剪枝方案，能够将其压缩15.7倍。然后将其编码为一种基于图像的格式，该格式旨在实现简单、通用的解码。对于SOG-XT格式，我们提出了自组织高斯（Self-Organizing Gaussians）的一种新扩展，包含两个主要贡献：（i）自组织2D码本，（ii）并行代表分配平滑（PRAS），它利用四元数和尺度参数化的对称性来生成更适合编码的2D属性网格。这种编码将场景体积减小6.6倍。我们表明，可选的编码感知微调可进一步减小2.2倍。在标准3DGS基准测试中，我们这种简单且模块化的方法因此在未压缩普通3DGS场景的体积上实现了85倍至319倍的总压缩比，在真实场景中树立了新的基准，并在率失真性能上超过了紧密集成的方法。解码仅依赖于原生Web图像格式，模块化设计使每个阶段都易于与未来的重建和压缩进展相结合。代码和项目页面：this https URL
英文摘要
Scene reconstruction with 3D Gaussian Splatting (3DGS) has become common, however deployment remains painful as the uncompressed file sizes can be massive. Current 3DGS compression systems combine multiple strategies for file size reduction, which can obscure where gains come from and limit component reuse across training pipelines. To make the gains more transparent, we propose KISS-GS, a modular compression pipeline named after the principle of keeping things simple, designed to decouple compression entirely from training. Given a 3DGS scene reconstructed with vanilla 3DGS, we are able to reduce it through compaction by 15.7x using a combination of state-of-the-art pruning schemes. Then we encode it into an image-based format designed for simple, ubiquitous decoding. With the SOG-XT format, we propose a novel extension to Self-Organizing Gaussians with two main contributions: (i) Self-organizing 2D Codebooks and (ii) Parallel Representative Assignment Smoothing (PRAS), which leverages the symmetry of quaternion and scale parameterizations to produce 2D attribute grids more amenable to encoding. This encoding reduces scene size by 6.6x. We show that optional encoding-aware fine-tuning yields a further 2.2x. Across standard 3DGS benchmarks, our simple and modular approach thus achieves a total of 85x to 319x reductions in the size of the scene over uncompressed vanilla 3DGS, setting new benchmarks for real-world scenes and surpassing tightly integrated methods in rate-distortion. Decoding relies solely on web-native image formats, and the modular design makes each stage easy to combine with future advances in reconstruction and compaction. Code and project page: https://fraunhoferhhi.github.io/KISS-GS/
Journal refEuropean Conference on Computer Vision (ECCV) 2026, pp. 677-694, Springer, 2026
DOI：10.1007/978-3-032-37461-5_37
