Saved in:
Bibliographic Details
Main Authors: Di Sario, Francesco, Rebain, Daniel, Verbin, Dor, Grangetto, Marco, Tagliasacchi, Andrea
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.14180
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917525798780928
author Di Sario, Francesco
Rebain, Daniel
Verbin, Dor
Grangetto, Marco
Tagliasacchi, Andrea
author_facet Di Sario, Francesco
Rebain, Daniel
Verbin, Dor
Grangetto, Marco
Tagliasacchi, Andrea
contents 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. Project page: https://sphericalvoronoi.github.io/
format Preprint
id arxiv_https___arxiv_org_abs_2512_14180
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Spherical Voronoi: Directional Appearance as a Differentiable Partition of the Sphere
Di Sario, Francesco
Rebain, Daniel
Verbin, Dor
Grangetto, Marco
Tagliasacchi, Andrea
Computer Vision and Pattern Recognition
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. Project page: https://sphericalvoronoi.github.io/
title Spherical Voronoi: Directional Appearance as a Differentiable Partition of the Sphere
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.14180