2DGH: 2D Gaussian-Hermite Splatting for High-quality Rendering and Better Geometry Reconstruction

TL;DR

This paper introduces a novel 2D Gaussian-Hermite splatting method that significantly improves 3D reconstruction and rendering quality by using an advanced kernel inspired by quantum physics, outperforming traditional Gaussian approaches.

Contribution

The paper proposes a Gaussian-Hermite kernel for Gaussian splatting, enhancing anisotropy and deformation capabilities for superior 3D reconstruction and rendering.

Findings

Outperforms traditional Gaussian kernels in geometry reconstruction

Achieves higher quality novel-view synthesis

Demonstrates superior rendering and reconstruction performance

Abstract

2D Gaussian Splatting has recently emerged as a significant method in 3D reconstruction, enabling novel view synthesis and geometry reconstruction simultaneously. While the well-known Gaussian kernel is broadly used, its lack of anisotropy and deformation ability leads to dim and vague edges at object silhouettes, limiting the reconstruction quality of current Gaussian splatting methods. To enhance the representation power, we draw inspiration from quantum physics and propose to use the Gaussian-Hermite kernel as the new primitive in Gaussian splatting. The new kernel takes a unified mathematical form and extends the Gaussian function, which serves as the zero-rank term in the updated formulation. Our experiments demonstrate the extraordinary performance of Gaussian-Hermite kernel in both geometry reconstruction and novel-view synthesis tasks. The proposed kernel outperforms traditional Gaussian Splatting kernels, showcasing its potential for high-quality 3D reconstruction and rendering.