CLIPGaussian: Universal and Multimodal Style Transfer Based on Gaussian Splatting

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Howil, Kornel, Waczyńska, Joanna, Borycki, Piotr, Dziarmaga, Tadeusz, Mazur, Marcin, Spurek, Przemysław
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912667043627008
author Howil, Kornel
Waczyńska, Joanna
Borycki, Piotr
Dziarmaga, Tadeusz
Mazur, Marcin
Spurek, Przemysław
author_facet Howil, Kornel
Waczyńska, Joanna
Borycki, Piotr
Dziarmaga, Tadeusz
Mazur, Marcin
Spurek, Przemysław
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_22854
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CLIPGaussian: Universal and Multimodal Style Transfer Based on Gaussian Splatting
Howil, Kornel
Waczyńska, Joanna
Borycki, Piotr
Dziarmaga, Tadeusz
Mazur, Marcin
Spurek, Przemysław
Computer Vision and Pattern Recognition
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.
title CLIPGaussian: Universal and Multimodal Style Transfer Based on Gaussian Splatting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.22854