{"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/learning-a-no-reference-quality-metric-for","title":"Learning a No-Reference Quality Metric for Single-Image Super-Resolution","arxiv_id":"1612.05890","date":"2016-12-18","proceeding":null,"authors":["Chao Ma","Chih-Yuan Yang","Xiaokang Yang","Ming-Hsuan Yang"],"abstract":"Numerous single-image super-resolution algorithms have been proposed in the\nliterature, but few studies address the problem of performance evaluation based\non visual perception. While most super-resolution images are evaluated by\nfullreference metrics, the effectiveness is not clear and the required\nground-truth images are not always available in practice. To address these\nproblems, we conduct human subject studies using a large set of\nsuper-resolution images and propose a no-reference metric learned from visual\nperceptual scores. Specifically, we design three types of low-level statistical\nfeatures in both spatial and frequency domains to quantify super-resolved\nartifacts, and learn a two-stage regression model to predict the quality scores\nof super-resolution images without referring to ground-truth images. Extensive\nexperimental results show that the proposed metric is effective and efficient\nto assess the quality of super-resolution images based on human perception.","url_abs":"http://arxiv.org/abs/1612.05890v1","url_pdf":"http://arxiv.org/pdf/1612.05890v1.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":"learning-a-no-reference-quality-metric-for","repo_url":"https://github.com/chaoma99/sr-metric","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-a-no-reference-quality-metric-for","repo_url":"https://github.com/ryanxingql/image-quality-assessment-toolbox","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"image-super-resolution","task_name":"Image Super-Resolution"},{"task_slug":"super-resolution","task_name":"Super-Resolution"},{"task_slug":"video-quality-assessment","task_name":"Video Quality Assessment"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-quality-assessment-on-msu-sr-qa-dataset","task":"Video Quality Assessment","dataset":"MSU SR-QA Dataset","model":"Ma-Metric","rank_in_archive_order":7,"of":60,"metrics":{"KLCC":"0.52301","PLCC":"0.65357","SROCC":"0.67362","Type":"NR"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1612.05890","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}