{"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/deep-neural-networks-for-no-reference-and","title":"Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment","arxiv_id":"1612.01697","date":"2016-12-06","proceeding":null,"authors":["Sebastian Bosse","Dominique Maniry","Klaus-Robert Müller","Thomas Wiegand","Wojciech Samek"],"abstract":"We present a deep neural network-based approach to image quality assessment\n(IQA). The network is trained end-to-end and comprises ten convolutional layers\nand five pooling layers for feature extraction, and two fully connected layers\nfor regression, which makes it significantly deeper than related IQA models.\nUnique features of the proposed architecture are that: 1) with slight\nadaptations it can be used in a no-reference (NR) as well as in a\nfull-reference (FR) IQA setting and 2) it allows for joint learning of local\nquality and local weights, i.e., relative importance of local quality to the\nglobal quality estimate, in an unified framework. Our approach is purely\ndata-driven and does not rely on hand-crafted features or other types of prior\ndomain knowledge about the human visual system or image statistics. We evaluate\nthe proposed approach on the LIVE, CISQ, and TID2013 databases as well as the\nLIVE In the wild image quality challenge database and show superior performance\nto state-of-the-art NR and FR IQA methods. Finally, cross-database evaluation\nshows a high ability to generalize between different databases, indicating a\nhigh robustness of the learned features.","url_abs":"http://arxiv.org/abs/1612.01697v2","url_pdf":"http://arxiv.org/pdf/1612.01697v2.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":"deep-neural-networks-for-no-reference-and","repo_url":"https://github.com/dmaniry/deepIQA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deep-neural-networks-for-no-reference-and","repo_url":"https://github.com/lidq92/WaDIQaM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"full-reference-image-quality-assessment","task_name":"Full reference image quality assessment"},{"task_slug":"full-reference-image-quality-assessment-2","task_name":"Full-Reference Image Quality Assessment"},{"task_slug":"image-quality-assessment","task_name":"Image Quality Assessment"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1612.01697","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}