1. [Publications](/publications) 2. Learning Linear Transformations for Fast Image and Video Style Transfer # Learning Linear Transformations for Fast Image and Video Style Transfer ![](/sites/default/files/styles/wide/public/publications/style.png?itok=H30FUyJh) 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 run-time 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. 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. ## Authors Xueting Li (UCMerced) [Sifei Liu](/person/sifei-liu) Ming-Hsuan Yang (UCMerced) [Jan Kautz](/person/jan-kautz) ## Publication Date Monday, April 1, 2019 ## Published in [CVPR 2019](https://sites.google.com/view/linear-style-transfer-cvpr19) ## Research Area [Computer Vision](/research-area/computer-vision) ## External Links [\[project page\]](https://sites.google.com/view/linear-style-transfer-cvpr19) [\[codes\]](https://github.com/sunshineatnoon/LinearStyleTransfer) [\[media\]](https://news.developer.nvidia.com/new-ai-style-transfer-algorithm-allows-users-to-create-millions-of-artistic-combinations/) ## Copyright This material is posted here with permission of the IEEE. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to .