{"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/will-people-like-your-image-learning-the","title":"Will People Like Your Image? Learning the Aesthetic Space","arxiv_id":"1611.05203","date":"2016-11-16","proceeding":null,"authors":["Katharina Schwarz","Patrick Wieschollek","Hendrik P. A. Lensch"],"abstract":"Rating how aesthetically pleasing an image appears is a highly complex matter\nand depends on a large number of different visual factors. Previous work has\ntackled the aesthetic rating problem by ranking on a 1-dimensional rating\nscale, e.g., incorporating handcrafted attributes. In this paper, we propose a\nrather general approach to automatically map aesthetic pleasingness with all\nits complexity into an \"aesthetic space\" to allow for a highly fine-grained\nresolution. In detail, making use of deep learning, our method directly learns\nan encoding of a given image into this high-dimensional feature space\nresembling visual aesthetics. Additionally to the mentioned visual factors,\ndifferences in personal judgments have a large impact on the likeableness of a\nphotograph. Nowadays, online platforms allow users to \"like\" or favor certain\ncontent with a single click. To incorporate a huge diversity of people, we make\nuse of such multi-user agreements and assemble a large data set of 380K images\n(AROD) with associated meta information and derive a score to rate how visually\npleasing a given photo is. We validate our derived model of aesthetics in a\nuser study. Further, without any extra data labeling or handcrafted features,\nwe achieve state-of-the art accuracy on the AVA benchmark data set. Finally, as\nour approach is able to predict the aesthetic quality of any arbitrary image or\nvideo, we demonstrate our results on applications for resorting photo\ncollections, capturing the best shot on mobile devices and aesthetic key-frame\nextraction from videos.","url_abs":"http://arxiv.org/abs/1611.05203v2","url_pdf":"http://arxiv.org/pdf/1611.05203v2.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":"will-people-like-your-image-learning-the","repo_url":"https://github.com/cgtuebingen/will-people-like-your-image","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"will-people-like-your-image-learning-the","repo_url":"https://github.com/winfried-loetzsch/will-people-like-your-image","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1611.05203","atlas_url":"https://app.syntology.ai/?focus=1611.05203","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}