GAGS: graph-guided adaptive Gaussian splatting for scene stylization
The advancement of digital media technologies has greatly expanded the need for realistic and artistically expressive 3D content. As an emerging technology, 3D scene stylization, which transfers artistic characteristics from reference images to reconstructed 3D scenes, has become a prominent research direction in computer vision and computer graphics. Although Neural Radiance Fields (NeRF)-based approaches have achieved promising results in stylized novel view synthesis, they still suffer from issues such as slow optimization, high computational cost, and susceptibility to geometric artifacts. Recently, 3D Gaussian Splatting has demonstrated superior efficiency and real-time rendering capabilities. However, its discrete structure and fixed geometry restrict the accurate representation of continuous textures and fine-grained style features across multiple views. To overcome these limitations, we propose Graph-Guided Adaptive Gaussian Splatting for Scene Stylization (GAGS)—an efficient 3D scene stylization framework for Gaussian Splatting representations. First, we leverage a pre-trained 3DGS scene representation as the foundation and introduce a style-aware alignment module. This module learns cross-view style patterns to capture fine-grained, high-frequency texture information, thereby ensuring multi-view consistency. Next, we propose to construct a spatial adjacency graph over Gaussian ellipsoids to identify inter-ellipsoid style discrepancies and fuse style features from neighboring regions. In addition, we propose a Style-Intensity-Aware Gaussian Refinement module. Leveraging the previously constructed adjacency graph, this mechanism adaptively adjusts the sizes of Gaussian ellipsoids according to node affinities, thereby achieving effective stylization while preventing geometric distortion. Compared with state-of-the-art methods, our proposed approach can generate high-quality stylizations and outperforms existing methods both qualitatively and quantitatively.