发表机构
Beijing Institute of Technology; Peking University（北京理工大学; 北京大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出CVT-GS，一种无需优化的后处理3DGS简化框架，通过几何感知质心沃罗诺伊镶嵌和轻量级神经单元合并器，实现100倍压缩且速度提升12倍、PSNR提高1.3 dB。
AI 中文摘要
尽管3D高斯泼溅（3DGS）已成为实时新视角合成的一种强大表示方法，但渲染高保真场景通常依赖于大量的高斯图元，导致巨大的存储和计算开销。现有的简化技术大多具有侵入性，需要训练时剪枝、架构修改或计算昂贵的逐场景微调。这些缺点限制了它们在现成预训练模型上的部署。在本文中，我们提出CVT-GS，一种新颖的无需优化的后处理简化框架，可直接压缩已训练的3DGS场景而不牺牲视觉保真度。我们的方法首先通过几何感知的质心沃罗诺伊镶嵌（CVT）在高斯中心上构建空间连贯的单元。随后，一个轻量级神经单元合并器在可微渲染监督下，为每个单元预测一个具有高度代表性的高斯图元的几何和外观。通过将简化表述为渲染感知的多对一合并过程，而非简单的图元剪枝，CVT-GS输出一个与现有渲染器无缝兼容的标准3DGS场景。在多个数据集上的实验证明了我们方法的优越性。值得注意的是，当实现高斯点减少100倍时，我们的方法比最先进的方法快12倍，同时将PSNR提高了1.3 dB。
英文摘要
While 3D Gaussian Splatting (3DGS) has emerged as a powerful representation for real-time novel view synthesis, rendering high-fidelity scenes often relies on a massive number of Gaussian primitives, incurring substantial storage and computational overhead. Existing simplification techniques are largely intrusive, requiring training-time pruning, architectural modifications, or computationally expensive per-scene fine-tuning. These drawbacks limit their deployment on off-the-shelf pretrained models. In this paper, we propose CVT-GS, a novel optimization-free post-hoc simplification framework that directly compresses trained 3DGS scenes without sacrificing visual fidelity. Our approach first constructs spatially coherent cells over Gaussian centers via a geometry-aware Centroidal Voronoi Tessellation (CVT). Subsequently, a lightweight neural cell merger predicts the geometry and appearance of a single, highly representative Gaussian primitive for each cell under differentiable rendering supervision. By formulating simplification as a rendering-aware many-to-one merging process rather than naive primitive pruning, CVT-GS outputs a standard 3DGS scene that is seamlessly compatible with existing renderers. Experiments on various datasets demonstrate the superiority of our method. Notably, when achieving a 100-fold reduction in Gaussian points, our method operates 12 times faster than state-of-the-art methods while improving the PSNR by 1.3 dB.
