Meet-in-Style: Text-Driven Real-Time Video Stylization Using Diffusion Models
IEEE Computer Graphics and Applications · 2025-03 · 45 (2) · 47-56
DOI: 10.1109/mcg.2025.3554312 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Computer Graphics and Applications, 2025-03. Verfasst von David Kunz und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 25 Literaturangaben. Gefördert von: Natural Sciences and Engineering Research Council of Canada, Agency of the Czech Technical University in Prague, Research Center for Informatics, Czech Technical University in Prague.
Abstract (Originalsprache)
We present Meet-in-Style-a new approach to real-time stylization of live video streams using text prompts. In contrast to previous text-based techniques, our system is able to stylize input video at 30 fps on commodity graphics hardware while preserving structural consistency of the stylized sequence and minimizing temporal flicker. A key idea of our approach is to combine diffusion-based image stylization with a few-shot patch-based training strategy that can produce a custom image-to-image stylization network with real-time inference capabilities. Such a combination not only allows for fast stylization, but also greatly improves consistency of individual stylized frames compared to a scenario where diffusion is applied to each video frame separately. We conducted a number of user experiments in which we found our approach to be particularly useful in video conference scenarios enabling participants to interactively apply different visual styles to themselves (or to each other) to enhance the overall chatting experience.
Förderung
- Natural Sciences and Engineering Research Council of Canada
- Agency of the Czech Technical University in Prague
- Research Center for Informatics, Czech Technical University in Prague
Zitieren
APA
Kunz, D., Texler, O., Mould, D., & Sykora, D. (2025). Meet-in-Style: Text-Driven Real-Time Video Stylization Using Diffusion Models. IEEE Computer Graphics and Applications, 45(2), 47-56. https://doi.org/10.1109/mcg.2025.3554312
Vancouver
Kunz D, Texler O, Mould D, Sykora D. Meet-in-Style: Text-Driven Real-Time Video Stylization Using Diffusion Models. IEEE Computer Graphics and Applications. 2025;45(2):47-56. doi:10.1109/mcg.2025.3554312
BibTeX
@article{Kunz2025,
author = {Kunz, David and Texler, Ondrej and Mould, David and Sykora, Daniel},
title = {Meet-in-Style: Text-Driven Real-Time Video Stylization Using Diffusion Models},
journal = {IEEE Computer Graphics and Applications},
year = {2025},
volume = {45},
number = {2},
pages = {47--56},
doi = {10.1109/mcg.2025.3554312}
}
EUVIMED