Understanding Generalized Whitening and Coloring Transform for Universal Style Transfer

Tai-Yin Chiu; The IEEE International Conference on Computer Vision (ICCV), 2019, pp. 4452-4460

Abstract


Style transfer is a task of rendering images in the styles of other images. In the past few years, neural style transfer has achieved a great success in this task, yet suffers from either the inability to generalize to unseen style images or fast style transfer. Recently, an universal style transfer technique that applies zero-phase component analysis (ZCA) for whitening and coloring image features realizes fast and arbitrary style transfer. However, using ZCA for style transfer is empirical and does not have any theoretical support. In addition, other whitening and coloring transforms (WCT) than ZCA have not been investigated. In this report, we generalize ZCA to the general form of WCT, provide an analytical performance analysis from the angle of neural style transfer, and show why ZCA is a good choice for style transfer among different WCTs and why some WCTs are not well applicable for style transfer.

Related Material


[pdf]
[bibtex]
@InProceedings{Chiu_2019_ICCV,
author = {Chiu, Tai-Yin},
title = {Understanding Generalized Whitening and Coloring Transform for Universal Style Transfer},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}