球面 Voronoi：将方向外观作为球面的可微划分
Spherical Voronoi: Directional Appearance as a Differentiable Partition of the Sphere
用可微的球面 Voronoi 分区替代球谐函数来参数化 3DGS 的视角相关颜色，可直接替换现有管线中的 SH 系数，并进一步把反射方向作为输入当作可学习反射探针，解决 SH 无法表达高光和吉布斯振铃的问题。
原文依据 We propose Spherical Voronoi (SV) as a unified framework for appearance representation in 3D Gaussian Splatting.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论辐射场方法（如 3D 高斯泼溅）已成为新视角合成的强大范式，但其外观建模往往依赖球谐函数（SH），后者存在根本性局限。SH 难以处理高频信号，会出现吉布斯振铃伪影，并且无法捕捉镜面反射——而镜面反射是真实感渲染的关键组成部分。尽管球面高斯等替代方案有所改进，却带来了显著的优化复杂度。我们提出球面 Voronoi（SV），作为 3D 高斯泼溅中外观表示的统一框架。SV 将方向域划分为具有平滑边界的可学习区域，为视角相关效应提供直观且稳定的参数化。对于漫反射外观，SV 在保持优化比现有替代方案更简单的同时取得了有竞争力的结果。对于 SH 失效的反射，我们依据经典图形学原理，将 SV 用作可学习反射探针，以反射方向作为输入。该形式在合成与真实数据集上取得了最优结果，表明 SV 为显式三维表示中的外观建模提供了一种有原则、高效且通用的解决方案。
英文原文摘要 1271 字符
Radiance field methods (e.g. 3D Gaussian Splatting) have emerged as a powerful paradigm for novel view synthesis, yet their appearance modeling often relies on Spherical Harmonics (SH), which impose fundamental limitations. SH struggle with high-frequency signals, exhibit Gibbs ringing artifacts, and fail to capture specular reflections---a key component of realistic rendering. Although alternatives like spherical Gaussians offer improvements, they add significant optimization complexity. We propose Spherical Voronoi (SV) as a unified framework for appearance representation in 3D Gaussian Splatting. SV partitions the directional domain into learnable regions with smooth boundaries, providing an intuitive and stable parameterization for view-dependent effects. For diffuse appearance, SV achieves competitive results while keeping optimization simpler than existing alternatives. For reflections---where SH fail---we leverage SV as learnable reflection probes, taking reflected directions as input following principles from classical graphics. This formulation attains state-of-the-art results on synthetic and real-world datasets, demonstrating that SV offers a principled, efficient, and general solution for appearance modeling in explicit 3D representations.