Optimization-Free Style Transfer for 3D Gaussian Splats
This provides a fast and flexible solution for stylizing 3D Gaussian splats without training or optimization, which is incremental over prior methods that required such steps.
The paper tackles the problem of style transfer for 3D Gaussian splats by proposing a reconstruction- and optimization-free method that uses a graph structure and feed-forward stylization, achieving speeds under 2 minutes on consumer hardware.
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.