DisC-GS: Discontinuity-aware Gaussian Splatting

TL;DR

This paper introduces DisC-GS, a framework that enhances Gaussian Splatting for 3D scene rendering by effectively handling discontinuities and boundaries, improving image quality in novel view synthesis.

Contribution

We propose a discontinuity-aware Gaussian Splatting framework with a Bézier-boundary gradient approximation to improve boundary rendering in 3D scene synthesis.

Findings

Significantly improves boundary rendering accuracy.

Maintains differentiability with the Bézier-boundary gradient strategy.

Demonstrates superior results in novel view synthesis experiments.

Abstract

Recently, Gaussian Splatting, a method that represents a 3D scene as a collection of Gaussian distributions, has gained significant attention in addressing the task of novel view synthesis. In this paper, we highlight a fundamental limitation of Gaussian Splatting: its inability to accurately render discontinuities and boundaries in images due to the continuous nature of Gaussian distributions. To address this issue, we propose a novel framework enabling Gaussian Splatting to perform discontinuity-aware image rendering. Additionally, we introduce a B\'ezier-boundary gradient approximation strategy within our framework to keep the "differentiability" of the proposed discontinuity-aware rendering process. Extensive experiments demonstrate the efficacy of our framework.