While implicit generative models such as GANs have shown impressive results in high quality image reconstruction and manipulation using a combination of various losses, we consider a simpler approach leading to surprisingly strong results. We show that texture loss alone allows the generation of perceptually high quality images. We provide a better understanding of texture constraining mechanism and develop a novel semantically guided texture constraining method for further improvement. Using a recently developed perceptual metric employing "deep features" and termed LPIPS, the method obtains state-of-the-art results. Moreover, we show that a texture representation of those deep features better capture the perceptual quality of an image than the original deep features. Using texture information, off-the-shelf deep classification networks (without training) perform as well as the best performing (tuned and calibrated) LPIPS metrics. The code is publicly available.
@article{arxiv.1808.00043,
title = {The Unreasonable Effectiveness of Texture Transfer for Single Image Super-resolution},
author = {Muhammad Waleed Gondal and Bernhard Schölkopf and Michael Hirsch},
journal= {arXiv preprint arXiv:1808.00043},
year = {2018}
}