G-Style: Stylized Gaussian Splatting

Kovács, Áron Samuel; Hermosilla, Pedro; Raidou, Renata Georgia

G-Style: Stylized Gaussian Splatting

dc.contributor.author	Kovács, Áron Samuel	en_US
dc.contributor.author	Hermosilla, Pedro	en_US
dc.contributor.author	Raidou, Renata Georgia	en_US
dc.contributor.editor	Chen, Renjie	en_US
dc.contributor.editor	Ritschel, Tobias	en_US
dc.contributor.editor	Whiting, Emily	en_US
dc.date.accessioned	2024-10-13T18:09:57Z
dc.date.available	2024-10-13T18:09:57Z
dc.date.issued	2024
dc.description.abstract	We introduce G -Style, a novel algorithm designed to transfer the style of an image onto a 3D scene represented using Gaussian Splatting. Gaussian Splatting is a powerful 3D representation for novel view synthesis, as-compared to other approaches based on Neural Radiance Fields-it provides fast scene renderings and user control over the scene. Recent pre-prints have demonstrated that the style of Gaussian Splatting scenes can be modified using an image exemplar. However, since the scene geometry remains fixed during the stylization process, current solutions fall short of producing satisfactory results. Our algorithm aims to address these limitations by following a three-step process: In a pre-processing step, we remove undesirable Gaussians with large projection areas or highly elongated shapes. Subsequently, we combine several losses carefully designed to preserve different scales of the style in the image, while maintaining as much as possible the integrity of the original scene content. During the stylization process and following the original design of Gaussian Splatting, we split Gaussians where additional detail is necessary within our scene by tracking the gradient of the stylized color. Our experiments demonstrate that G -Style generates high-quality stylizations within just a few minutes, outperforming existing methods both qualitatively and quantitatively	en_US
dc.description.number	7
dc.description.sectionheaders	Advanced 3D Synthesis and Stylization
dc.description.seriesinformation	Computer Graphics Forum
dc.description.volume	43
dc.identifier.doi	10.1111/cgf.15259
dc.identifier.issn	1467-8659
dc.identifier.pages	13 pages
dc.identifier.uri	https://doi.org/10.1111/cgf.15259
dc.identifier.uri	https://diglib.eg.org/handle/10.1111/cgf15259
dc.publisher	The Eurographics Association and John Wiley & Sons Ltd.	en_US
dc.rights	Attribution 4.0 International License
dc.rights.uri	https://creativecommons.org/licenses/by/4.0/
dc.subject	CCS Concepts: Computing methodologies → Computer graphics; Artificial intelligence; Neural networks
dc.subject	Computing methodologies → Computer graphics
dc.subject	Artificial intelligence
dc.subject	Neural networks
dc.title	G-Style: Stylized Gaussian Splatting	en_US