Learning Linear Transformations for Fast Image and Video Style Transfer
Abstract
Given a random pair of images, a universal style transfer method extracts the feel from a reference image to synthesize an output based on the look of a content image. Recent algorithms based on second-order statistics, however, are either computationally expensive or prone to generate artifacts due to the trade-off between image quality and runtime performance. In this work, we present an approach for universal style transfer that learns the transformation matrix in a data-driven fashion. Our algorithm is efficient yet flexible to transfer different levels of styles with the same auto-encoder network. It also produces stable video style transfer results due to the preservation of the content affinity. In addition, we propose a linear propagation module to enable a feed-forward network for photo-realistic style transfer. We demonstrate the effectiveness of our approach on three tasks: artistic style, photo-realistic and video style transfer, with comparisons to state-of-the-art methods.
Cite
Text
Li et al. "Learning Linear Transformations for Fast Image and Video Style Transfer." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019. doi:10.1109/CVPR.2019.00393Markdown
[Li et al. "Learning Linear Transformations for Fast Image and Video Style Transfer." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019.](https://mlanthology.org/cvpr/2019/li2019cvpr-learning/) doi:10.1109/CVPR.2019.00393BibTeX
@inproceedings{li2019cvpr-learning,
title = {{Learning Linear Transformations for Fast Image and Video Style Transfer}},
author = {Li, Xueting and Liu, Sifei and Kautz, Jan and Yang, Ming-Hsuan},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2019},
doi = {10.1109/CVPR.2019.00393},
url = {https://mlanthology.org/cvpr/2019/li2019cvpr-learning/}
}