TTE replaces fixed spherical bases with differentiable Voronoi partitions plus shared semantic tokens to create adaptive geolocation encoders that reach new SOTA on geospatial tasks and iNaturalist species classification.
arXiv preprint arXiv:2512.14180 (2025) 2, 10, 11
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
abstract
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/
citation-role summary
background 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
Power Foam unifies real-time differentiable ray tracing and rasterization by replacing unbounded Voronoi cells with controllable bounded power diagrams, oriented surfaces, and embedded textures.
SAD is a new explicit differentiable image representation based on soft anisotropic additively weighted Voronoi partitions that achieves higher PSNR and 4-19x faster training than Image-GS and Instant-NGP at matched bitrate.
A learnable confidence framework in 3D Gaussian Splatting balances photometric and geometric losses while penalizing per-primitive variance to produce state-of-the-art unbounded meshes efficiently.
Neural Harmonic Textures add periodic feature interpolation and deferred neural decoding to primitive representations, achieving state-of-the-art real-time novel-view synthesis and bridging primitive and neural-field methods.
citing papers explorer
-
Tessellating The Earth
TTE replaces fixed spherical bases with differentiable Voronoi partitions plus shared semantic tokens to create adaptive geolocation encoders that reach new SOTA on geospatial tasks and iNaturalist species classification.
-
Power Foam: Unifying Real-Time Differentiable Ray Tracing and Rasterization
Power Foam unifies real-time differentiable ray tracing and rasterization by replacing unbounded Voronoi cells with controllable bounded power diagrams, oriented surfaces, and embedded textures.
-
Soft Anisotropic Diagrams for Differentiable Image Representation
SAD is a new explicit differentiable image representation based on soft anisotropic additively weighted Voronoi partitions that achieves higher PSNR and 4-19x faster training than Image-GS and Instant-NGP at matched bitrate.
-
Confidence-Based Mesh Extraction from 3D Gaussians
A learnable confidence framework in 3D Gaussian Splatting balances photometric and geometric losses while penalizing per-primitive variance to produce state-of-the-art unbounded meshes efficiently.
-
Neural Harmonic Textures for High-Quality Primitive Based Neural Reconstruction
Neural Harmonic Textures add periodic feature interpolation and deferred neural decoding to primitive representations, achieving state-of-the-art real-time novel-view synthesis and bridging primitive and neural-field methods.