{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/the-unreasonable-effectiveness-of-texture","title":"The Unreasonable Effectiveness of Texture Transfer for Single Image Super-resolution","arxiv_id":"1808.00043","date":"2018-07-31","proceeding":null,"authors":["Muhammad Waleed Gondal","Bernhard Schölkopf","Michael Hirsch"],"abstract":"While implicit generative models such as GANs have shown impressive results\nin high quality image reconstruction and manipulation using a combination of\nvarious losses, we consider a simpler approach leading to surprisingly strong\nresults. We show that texture loss alone allows the generation of perceptually\nhigh quality images. We provide a better understanding of texture constraining\nmechanism and develop a novel semantically guided texture constraining method\nfor further improvement. Using a recently developed perceptual metric employing\n\"deep features\" and termed LPIPS, the method obtains state-of-the-art results.\nMoreover, we show that a texture representation of those deep features better\ncapture the perceptual quality of an image than the original deep features.\nUsing texture information, off-the-shelf deep classification networks (without\ntraining) perform as well as the best performing (tuned and calibrated) LPIPS\nmetrics. The code is publicly available.","url_abs":"http://arxiv.org/abs/1808.00043v1","url_pdf":"http://arxiv.org/pdf/1808.00043v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"the-unreasonable-effectiveness-of-texture","repo_url":"https://github.com/waleedgondal/Texture-based-Super-Resolution-Network","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-reconstruction","task_name":"Image Reconstruction"},{"task_slug":"image-super-resolution","task_name":"Image Super-Resolution"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1808.00043","atlas_url":"https://app.syntology.ai/?focus=1808.00043","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}