CLIPGaussian: Universal and Multimodal Style Transfer Based on Gaussian Splatting
Kornel Howil, Joanna Waczynska, Piotr Borycki, Tadeusz Dziarmaga, Marcin Mazur, Przemysław Spurek
Abstract
Gaussian Splatting (GS) has recently emerged as an efficient representation for rendering 3D scenes from 2D images and has been extended to images, videos, and dynamic 4D content. However, applying style transfer to GS-based representations, especially beyond simple color changes, remains challenging. In this work, we introduce CLIPGaussian, the first unified style transfer framework that supports text- and image-guided stylization across multiple modalities: 2D images, videos, 3D objects, and 4D scenes. Our method operates directly on Gaussian primitives and integrates into existing GS pipelines as a plug-in module, without requiring large generative models or retraining from scratch. The CLIPGaussian approach enables joint optimization of color and geometry in 3D and 4D settings, and achieves temporal coherence in videos, while preserving the model size. We demonstrate superior style fidelity and consistency across all tasks, validating CLIPGaussian as a universal and efficient solution for multimodal style transfer.
BibTeX
@inproceedings{
howil2025clipgaussian,
title={{CLIPG}aussian: Universal and Multimodal Style Transfer Based on Gaussian Splatting},
author={Kornel Howil and Joanna Waczynska and Piotr Borycki and Tadeusz Dziarmaga and Marcin Mazur and Przemys{\l}aw Spurek},
booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
year={2025},
url={https://openreview.net/forum?id=kjWB8iaO3l}
}