Optimization-Free Style Transfer for 3D Gaussian Splats
Raphael Du Sablon, David Hart

TL;DR
This paper introduces a fast, optimization-free method for stylizing 3D Gaussian splats directly from file inputs, enabling quick stylization without reconstruction or fine-tuning, suitable for consumer hardware.
Contribution
It presents a novel, direct stylization approach for 3D Gaussian splats that does not require reconstruction, optimization, or training, significantly reducing processing time.
Findings
Achieves stylization in under 2 minutes on CPU hardware.
Produces high-quality stylized 3D Gaussian splats.
Outperforms previous style transfer methods for 3D splats.
Abstract
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, allowing for direct stylization on a .ply or .splat file without requiring the original camera views. 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 also allows for fast stylization of splats with no additional training, achieving speeds under 2 minutes even on CPU-based consumer hardware. We demonstrate the quality results this approach achieves and compare to…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Data Compression Techniques · Face recognition and analysis
