Neural Gabor Splatting: Enhanced Gaussian Splatting with Neural Gabor for High-frequency Surface Reconstruction

TL;DR

This paper introduces neural Gabor splatting, enhancing 3D Gaussian splatting by modeling intra-primitive color variations with neural networks, enabling better high-frequency surface reconstruction.

Contribution

It proposes augmenting Gaussian primitives with neural networks and a frequency-aware densification strategy to improve high-frequency detail reconstruction in 3D scenes.

Findings

Achieves accurate high-frequency surface reconstruction.

Reduces primitive count for scenes with detailed textures.

Demonstrates effectiveness on standard benchmarks and datasets.

Abstract

Recent years have witnessed the rapid emergence of 3D Gaussian splatting (3DGS) as a powerful approach for 3D reconstruction and novel view synthesis. Its explicit representation with Gaussian primitives enables fast training, real-time rendering, and convenient post-processing such as editing and surface reconstruction. However, 3DGS suffers from a critical drawback: the number of primitives grows drastically for scenes with high-frequency appearance details, since each primitive can represent only a single color, requiring multiple primitives for every sharp color transition. To overcome this limitation, we propose neural Gabor splatting, which augments each Gaussian primitive with a lightweight multi-layer perceptron that models a wide range of color variations within a single primitive. To further control primitive numbers, we introduce a frequency-aware densification strategy that selects mismatch primitives for pruning and cloning based on frequency energy. Our method achieves accurate reconstruction of challenging high-frequency surfaces. We demonstrate its effectiveness through extensive experiments on both standard benchmarks, such as Mip-NeRF360 and High-Frequency datasets (e.g., checkered patterns), supported by comprehensive ablation studies.