优化最小化三维高斯溅射

Optimized Minimal 3D Gaussian Splatting

March 21, 2025

作者: Joo Chan Lee, Jong Hwan Ko, Eunbyung Park

cs.AI

摘要

3D高斯溅射（3DGS）作为一种强大的表示方法，已广泛应用于实时高性能渲染领域。然而，使用大量显式高斯基元来表示3D场景会带来显著的存储和内存开销。近期研究表明，通过高精度属性表示，可以在大幅减少高斯基元数量的同时实现高质量渲染。尽管如此，现有的3DGS压缩方法仍依赖于相对较多的高斯基元，主要侧重于属性压缩。这是因为较少的高斯基元对属性有损压缩更为敏感，容易导致严重的质量下降。鉴于高斯基元数量直接关联计算成本，有效减少基元数量而非仅优化存储显得尤为重要。本文提出了一种优化最小高斯表示（OMG），在显著降低存储需求的同时，使用最少数量的基元。首先，我们通过区分邻近高斯基元来最小化冗余，且不牺牲质量。其次，我们提出了一种紧凑且精确的属性表示方法，有效捕捉基元间的连续性与不规则性。此外，我们还引入了一种子向量量化技术，以改进不规则性表示，在保持快速训练的同时，代码本大小可忽略不计。大量实验证明，与现有最先进技术相比，OMG将存储需求降低了近50%，并在保持高渲染质量的同时实现了600+ FPS的渲染速度。我们的源代码可在https://maincold2.github.io/omg/获取。

English

3D Gaussian Splatting (3DGS) has emerged as a powerful representation for real-time, high-performance rendering, enabling a wide range of applications. However, representing 3D scenes with numerous explicit Gaussian primitives imposes significant storage and memory overhead. Recent studies have shown that high-quality rendering can be achieved with a substantially reduced number of Gaussians when represented with high-precision attributes. Nevertheless, existing 3DGS compression methods still rely on a relatively large number of Gaussians, focusing primarily on attribute compression. This is because a smaller set of Gaussians becomes increasingly sensitive to lossy attribute compression, leading to severe quality degradation. Since the number of Gaussians is directly tied to computational costs, it is essential to reduce the number of Gaussians effectively rather than only optimizing storage. In this paper, we propose Optimized Minimal Gaussians representation (OMG), which significantly reduces storage while using a minimal number of primitives. First, we determine the distinct Gaussian from the near ones, minimizing redundancy without sacrificing quality. Second, we propose a compact and precise attribute representation that efficiently captures both continuity and irregularity among primitives. Additionally, we propose a sub-vector quantization technique for improved irregularity representation, maintaining fast training with a negligible codebook size. Extensive experiments demonstrate that OMG reduces storage requirements by nearly 50% compared to the previous state-of-the-art and enables 600+ FPS rendering while maintaining high rendering quality. Our source code is available at https://maincold2.github.io/omg/.