{"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/nima-neural-image-assessment","title":"NIMA: Neural Image Assessment","arxiv_id":"1709.05424","date":"2017-09-15","proceeding":null,"authors":["Hossein Talebi","Peyman Milanfar"],"abstract":"Automatically learned quality assessment for images has recently become a hot\ntopic due to its usefulness in a wide variety of applications such as\nevaluating image capture pipelines, storage techniques and sharing media.\nDespite the subjective nature of this problem, most existing methods only\npredict the mean opinion score provided by datasets such as AVA [1] and TID2013\n[2]. Our approach differs from others in that we predict the distribution of\nhuman opinion scores using a convolutional neural network. Our architecture\nalso has the advantage of being significantly simpler than other methods with\ncomparable performance. Our proposed approach relies on the success (and\nretraining) of proven, state-of-the-art deep object recognition networks. Our\nresulting network can be used to not only score images reliably and with high\ncorrelation to human perception, but also to assist with adaptation and\noptimization of photo editing/enhancement algorithms in a photographic\npipeline. All this is done without need for a \"golden\" reference image,\nconsequently allowing for single-image, semantic- and perceptually-aware,\nno-reference quality assessment.","url_abs":"http://arxiv.org/abs/1709.05424v2","url_pdf":"http://arxiv.org/pdf/1709.05424v2.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":"nima-neural-image-assessment","repo_url":"https://github.com/idealo/image-quality-assessment","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"nima-neural-image-assessment","repo_url":"https://github.com/kentsyx/Neural-IMage-Assessment","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"nima-neural-image-assessment","repo_url":"https://github.com/titu1994/neural-image-assessment","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"nima-neural-image-assessment","repo_url":"https://github.com/truskovskiyk/nima.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"nima-neural-image-assessment","repo_url":"https://github.com/MS-Mind/MS-Code-06/tree/main/nima","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"nima-neural-image-assessment","repo_url":"https://github.com/MS-Mind/MS-Code-08/tree/main/nima","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"nima-neural-image-assessment","repo_url":"https://github.com/Mind23-2/MindCode-101/tree/main/nima","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"nima-neural-image-assessment","repo_url":"https://github.com/Mind23-2/MindCode-3/tree/main/nima","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"nima-neural-image-assessment","repo_url":"https://github.com/code-implementation1/Code6/tree/main/nasnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"nima-neural-image-assessment","repo_url":"https://github.com/code-implementation1/Code6/tree/main/nima","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"nima-neural-image-assessment","repo_url":"https://github.com/code-implementation1/Code6/tree/main/nima_vgg16","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"nima-neural-image-assessment","repo_url":"https://github.com/mindspore-ai/models/tree/master/official/cv/nima","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"aesthetics-quality-assessment","task_name":"Aesthetics Quality Assessment"},{"task_slug":"image-quality-assessment","task_name":"Image Quality Assessment"},{"task_slug":"video-quality-assessment","task_name":"Video Quality Assessment"}],"methods":[{"method_slug":"nima","method_name":"NIMA"}],"datasets_introduced":[],"methods_introduced":[{"slug":"nima","name":"NIMA","full_name":"Neural Image Assessment"}],"results":[{"leaderboard":"/sota/aesthetics-quality-assessment-on-ava","task":"Aesthetics Quality Assessment","dataset":"AVA","model":"NIMA","rank_in_archive_order":4,"of":9,"metrics":{"Accuracy":"81.5%"},"uses_additional_data":false},{"leaderboard":"/sota/image-quality-assessment-on-msu-nr-vqa","task":"Image Quality Assessment","dataset":"MSU NR VQA Database","model":"NIMA","rank_in_archive_order":8,"of":10,"metrics":{"KLCC":"0.6745","PLCC":"0.8784","SRCC":"0.8494"},"uses_additional_data":false},{"leaderboard":"/sota/video-quality-assessment-on-msu-video-quality","task":"Video Quality Assessment","dataset":"MSU NR VQA Database","model":"NIMA","rank_in_archive_order":15,"of":21,"metrics":{"KLCC":"0.6745","PLCC":"0.8784","SRCC":"0.8494","Type":"NR"},"uses_additional_data":false},{"leaderboard":"/sota/video-quality-assessment-on-msu-sr-qa-dataset","task":"Video Quality Assessment","dataset":"MSU SR-QA Dataset","model":"NIMA","rank_in_archive_order":49,"of":60,"metrics":{"KLCC":"0.20377","PLCC":"0.26550","SROCC":"0.25887","Type":"NR"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1709.05424","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}