3D-HGS: 3D Half-Gaussian Splatting

TL;DR

This paper introduces 3D Half-Gaussian kernels to improve 3D Gaussian Splatting, enhancing rendering quality while maintaining speed, and addressing shape and color discontinuities in neural rendering.

Contribution

The paper proposes 3D Half-Gaussian kernels as a novel, plug-and-play enhancement for 3D Gaussian Splatting methods to improve rendering quality.

Findings

Achieves state-of-the-art rendering quality.

Maintains high rendering speed.

Addresses shape and color discontinuities.

Abstract

Photo-realistic image rendering from 3D scene reconstruction has advanced significantly with neural rendering techniques. Among these, 3D Gaussian Splatting (3D-GS) outperforms Neural Radiance Fields (NeRFs) in quality and speed but struggles with shape and color discontinuities. We propose 3D Half-Gaussian (3D-HGS) kernels as a plug-and-play solution to address these limitations. Our experiments show that 3D-HGS enhances existing 3D-GS methods, achieving state-of-the-art rendering quality without compromising speed.