{"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/unique-unsupervised-image-quality-estimation","title":"UNIQUE: Unsupervised Image Quality Estimation","arxiv_id":"1810.06631","date":"2018-10-15","proceeding":null,"authors":["D. Temel","M. Prabhushankar","G. AlRegib"],"abstract":"In this paper, we estimate perceived image quality using sparse\nrepresentations obtained from generic image databases through an unsupervised\nlearning approach. A color space transformation, a mean subtraction, and a\nwhitening operation are used to enhance descriptiveness of images by reducing\nspatial redundancy; a linear decoder is used to obtain sparse representations;\nand a thresholding stage is used to formulate suppression mechanisms in a\nvisual system. A linear decoder is trained with 7 GB worth of data, which\ncorresponds to 100,000 8x8 image patches randomly obtained from nearly 1,000\nimages in the ImageNet 2013 database. A patch-wise training approach is\npreferred to maintain local information. The proposed quality estimator UNIQUE\nis tested on the LIVE, the Multiply Distorted LIVE, and the TID 2013 databases\nand compared with thirteen quality estimators. Experimental results show that\nUNIQUE is generally a top performing quality estimator in terms of accuracy,\nconsistency, linearity, and monotonic behavior.","url_abs":"http://arxiv.org/abs/1810.06631v2","url_pdf":"http://arxiv.org/pdf/1810.06631v2.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":"unique-unsupervised-image-quality-estimation","repo_url":"https://github.com/olivesgatech/UNIQUE-Project-Repository","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"unique-unsupervised-image-quality-estimation","repo_url":"https://github.com/olivesgatech/UNIQUE-Unsupervised-Image-Quality-Estimation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-quality-assessment","task_name":"Image Quality Assessment"},{"task_slug":"video-quality-assessment","task_name":"Video Quality Assessment"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-quality-assessment-on-msu-nr-vqa","task":"Image Quality Assessment","dataset":"MSU NR VQA Database","model":"UNIQUE","rank_in_archive_order":1,"of":10,"metrics":{"KLCC":"0.7648","PLCC":"0.9238","SRCC":"0.9148"},"uses_additional_data":false},{"leaderboard":"/sota/video-quality-assessment-on-msu-video-quality","task":"Video Quality Assessment","dataset":"MSU NR VQA Database","model":"UNIQUE","rank_in_archive_order":3,"of":21,"metrics":{"KLCC":"0.7648","PLCC":"0.9238","SRCC":"0.9148","Type":"NR"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1810.06631","atlas_url":"https://app.syntology.ai/?focus=1810.06631","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}