G-Style: Stylized Gaussian Splatting
This addresses the challenge of stylizing 3D scenes for applications like graphics and VR, though it is incremental as it builds on prior Gaussian Splatting stylization work.
The paper tackles the problem of transferring image style to 3D scenes represented by Gaussian Splatting, where existing methods produce unsatisfactory results due to fixed geometry, and introduces G-Style, which generates high-quality stylizations in minutes, outperforming others both qualitatively and quantitatively.
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.