{"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/ms-unique-multi-model-and-sharpness-weighted","title":"MS-UNIQUE: Multi-model and Sharpness-weighted Unsupervised Image Quality Estimation","arxiv_id":"1811.08947","date":"2018-11-21","proceeding":null,"authors":["Mohit Prabhushankar","Dogancan Temel","Ghassan AlRegib"],"abstract":"In this paper, we train independent linear decoder models to estimate the\nperceived quality of images. More specifically, we calculate the responses of\nindividual non-overlapping image patches to each of the decoders and scale\nthese responses based on the sharpness characteristics of filter set. We use\nmultiple linear decoders to capture different abstraction levels of the image\npatches. Training each model is carried out on 100,000 image patches from the\nImageNet database in an unsupervised fashion. Color space selection and ZCA\nWhitening are performed over these patches to enhance the descriptiveness of\nthe data. The proposed quality estimator is tested on the LIVE and the TID 2013\nimage quality assessment databases. Performance of the proposed method is\ncompared against eleven other state of the art methods in terms of accuracy,\nconsistency, linearity, and monotonic behavior. Based on experimental results,\nthe proposed method is generally among the top performing quality estimators in\nall categories.","url_abs":"http://arxiv.org/abs/1811.08947v1","url_pdf":"http://arxiv.org/pdf/1811.08947v1.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":"ms-unique-multi-model-and-sharpness-weighted","repo_url":"https://github.com/LONG-9621/IQA03","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"ms-unique-multi-model-and-sharpness-weighted","repo_url":"https://github.com/olivesgatech/MS-UNIQUE","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"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.08947","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}