ArtNVG: Content-Style Separated Artistic Neighboring-View Gaussian Stylization

TL;DR

ArtNVG is a novel 3D stylization framework that leverages reference images and innovative techniques to produce high-quality, consistent stylized scenes suitable for film and gaming industries.

Contribution

It introduces Content-Style Separated Control and Attention-based Neighboring-View Alignment techniques to enhance local consistency and style transfer in 3D scene stylization.

Findings

Outperforms existing methods in content preservation and style alignment

Achieves rapid optimization and high-quality rendering

Ensures local color and texture consistency across views

Abstract

As demand from the film and gaming industries for 3D scenes with target styles grows, the importance of advanced 3D stylization techniques increases. However, recent methods often struggle to maintain local consistency in color and texture throughout stylized scenes, which is essential for maintaining aesthetic coherence. To solve this problem, this paper introduces ArtNVG, an innovative 3D stylization framework that efficiently generates stylized 3D scenes by leveraging reference style images. Built on 3D Gaussian Splatting (3DGS), ArtNVG achieves rapid optimization and rendering while upholding high reconstruction quality. Our framework realizes high-quality 3D stylization by incorporating two pivotal techniques: Content-Style Separated Control and Attention-based Neighboring-View Alignment. Content-Style Separated Control uses the CSGO model and the Tile ControlNet to decouple the content and style control, reducing risks of information leakage. Concurrently, Attention-based Neighboring-View Alignment ensures consistency of local colors and textures across neighboring views, significantly improving visual quality. Extensive experiments validate that ArtNVG surpasses existing methods, delivering superior results in content preservation, style alignment, and local consistency.