{"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/learned-multi-patch-similarity","title":"Learned Multi-Patch Similarity","arxiv_id":"1703.08836","date":"2017-03-26","proceeding":"ICCV 2017 10","authors":["Wilfried Hartmann","Silvano Galliani","Michal Havlena","Luc van Gool","Konrad Schindler"],"abstract":"Estimating a depth map from multiple views of a scene is a fundamental task\nin computer vision. As soon as more than two viewpoints are available, one\nfaces the very basic question how to measure similarity across >2 image\npatches. Surprisingly, no direct solution exists, instead it is common to fall\nback to more or less robust averaging of two-view similarities. Encouraged by\nthe success of machine learning, and in particular convolutional neural\nnetworks, we propose to learn a matching function which directly maps multiple\nimage patches to a scalar similarity score. Experiments on several multi-view\ndatasets demonstrate that this approach has advantages over methods based on\npairwise patch similarity.","url_abs":"http://arxiv.org/abs/1703.08836v2","url_pdf":"http://arxiv.org/pdf/1703.08836v2.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":"learned-multi-patch-similarity","repo_url":"https://github.com/paschalidoud/raynet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1703.08836","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}