The Unreasonable Effectiveness of Texture Transfer for Single Image Super-resolution
This provides a simpler, effective approach for image super-resolution, potentially benefiting computer vision applications, though it builds incrementally on existing texture and deep feature methods.
The paper tackles single image super-resolution by showing that texture loss alone can generate perceptually high-quality images, achieving state-of-the-art results with a perceptual metric (LPIPS) and demonstrating that texture representations from deep features outperform original features in capturing perceptual quality.
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.