CVPR2021
Learning To Warp for Style Transfer
Xiao-Chang Liu, Yong-Liang Yang, Peter Hall
Abstract
Figure 1. Our method performs non-parametric warping to match artistic geometric style. Output has comparable quality (or better) than state-of-the art, but warping is two orders of magnitude faster. The teaser shows content, style (geometry+texture), and output images for a Picasso style transfer (left) and a Salvaor Dali style transfer (right).