DisC-GS: Discontinuity-aware Gaussian Splatting

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Qu, Haoxuan, Li, Zhuoling, Rahmani, Hossein, Cai, Yujun, Liu, Jun
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913567583764480
author Qu, Haoxuan
Li, Zhuoling
Rahmani, Hossein
Cai, Yujun
Liu, Jun
author_facet Qu, Haoxuan
Li, Zhuoling
Rahmani, Hossein
Cai, Yujun
Liu, Jun
contents 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 Bézier-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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_15196
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DisC-GS: Discontinuity-aware Gaussian Splatting
Qu, Haoxuan
Li, Zhuoling
Rahmani, Hossein
Cai, Yujun
Liu, Jun
Computer Vision and Pattern Recognition
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 Bézier-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.
title DisC-GS: Discontinuity-aware Gaussian Splatting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.15196