MrNeRF (@janusch_patas)
2025-12-17 | โค๏ธ 85 | ๐ 11
Spherical Voronoi: Directional Appearance as a Differentiable Partition of the Sphere
TL;DR: New spherical function representation for 3DGS appearance modeling that replaces Spherical Harmonics.
Abstract: Radiance field methods, such as 3D Gaussian Splatting, have emerged as a powerful paradigm for novel view synthesis. However, their appearance modeling often relies on Spherical Harmonics (SH), which impose fundamental limitations. SH struggles with high-frequency signals, exhibits Gibbs ringing artifacts, and fails 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 fails, 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.
๋ฏธ๋์ด
