Optimization-Free Style Transfer for 3D Gaussian Splats
Abstract
A novel method for style transfer of 3D Gaussian splats involves generating a graph structure and using a feed-forward, surface-based stylization technique without reconstruction or optimization.
The task of style transfer for 3D Gaussian splats has been explored in many previous works, but these require reconstructing or fine-tuning the splat while incorporating style information or optimizing a feature extraction network on the splat representation. We propose a reconstruction- and optimization-free approach to stylizing 3D Gaussian splats. This is done by generating a graph structure across the implicit surface of the splat representation. A feed-forward, surface-based stylization method is then used and interpolated back to the individual splats in the scene. This allows for any style image and 3D Gaussian splat to be used without any additional training or optimization. This also allows for fast stylization of splats, achieving speeds under 2 minutes even on consumer-grade hardware. We demonstrate the quality results this approach achieves and compare to other 3D Gaussian splat style transfer methods. Code is publicly available at https://github.com/davidmhart/FastSplatStyler.
Community
We are excited to share our work on stylizing Gaussian Splats directly from the .splat files, without the need to have the original training views. Check out some of our saved outputs here: https://drive.google.com/drive/folders/10YmtcCOKGosXfPEi84ho1AfYRYioYo12
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Improving Masked Style Transfer using Blended Partial Convolution (2025)
- Gaussian Set Surface Reconstruction through Per-Gaussian Optimization (2025)
- SurfaceSplat: Connecting Surface Reconstruction and Gaussian Splatting (2025)
- GDGS: 3D Gaussian Splatting Via Geometry-Guided Initialization And Dynamic Density Control (2025)
- 2D Triangle Splatting for Direct Differentiable Mesh Training (2025)
- FantasyStyle: Controllable Stylized Distillation for 3D Gaussian Splatting (2025)
- MILo: Mesh-In-the-Loop Gaussian Splatting for Detailed and Efficient Surface Reconstruction (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper