{"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/learning-to-compose-with-professional","title":"Learning to Compose with Professional Photographs on the Web","arxiv_id":"1702.00503","date":"2017-02-01","proceeding":null,"authors":["Yi-Ling Chen","Jan Klopp","Min Sun","Shao-Yi Chien","Kwan-Liu Ma"],"abstract":"Photo composition is an important factor affecting the aesthetics in\nphotography. However, it is a highly challenging task to model the aesthetic\nproperties of good compositions due to the lack of globally applicable rules to\nthe wide variety of photographic styles. Inspired by the thinking process of\nphoto taking, we formulate the photo composition problem as a view finding\nprocess which successively examines pairs of views and determines their\naesthetic preferences. We further exploit the rich professional photographs on\nthe web to mine unlimited high-quality ranking samples and demonstrate that an\naesthetics-aware deep ranking network can be trained without explicitly\nmodeling any photographic rules. The resulting model is simple and effective in\nterms of its architectural design and data sampling method. It is also generic\nsince it naturally learns any photographic rules implicitly encoded in\nprofessional photographs. The experiments show that the proposed view finding\nnetwork achieves state-of-the-art performance with sliding window search\nstrategy on two image cropping datasets.","url_abs":"http://arxiv.org/abs/1702.00503v2","url_pdf":"http://arxiv.org/pdf/1702.00503v2.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":"learning-to-compose-with-professional","repo_url":"https://github.com/yiling-chen/view-finding-network","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"image-cropping","task_name":"Image Cropping"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1702.00503","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}