English

ZDySS -- Zero-Shot Dynamic Scene Stylization using Gaussian Splatting

Computer Vision and Pattern Recognition 2025-01-08 v1

Abstract

Stylizing a dynamic scene based on an exemplar image is critical for various real-world applications, including gaming, filmmaking, and augmented and virtual reality. However, achieving consistent stylization across both spatial and temporal dimensions remains a significant challenge. Most existing methods are designed for static scenes and often require an optimization process for each style image, limiting their adaptability. We introduce ZDySS, a zero-shot stylization framework for dynamic scenes, allowing our model to generalize to previously unseen style images at inference. Our approach employs Gaussian splatting for scene representation, linking each Gaussian to a learned feature vector that renders a feature map for any given view and timestamp. By applying style transfer on the learned feature vectors instead of the rendered feature map, we enhance spatio-temporal consistency across frames. Our method demonstrates superior performance and coherence over state-of-the-art baselines in tests on real-world dynamic scenes, making it a robust solution for practical applications.

Keywords

Cite

@article{arxiv.2501.03875,
  title  = {ZDySS -- Zero-Shot Dynamic Scene Stylization using Gaussian Splatting},
  author = {Abhishek Saroha and Florian Hofherr and Mariia Gladkova and Cecilia Curreli and Or Litany and Daniel Cremers},
  journal= {arXiv preprint arXiv:2501.03875},
  year   = {2025}
}
R2 v1 2026-06-28T20:58:52.802Z