{"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-compare-image-patches-via","title":"Learning to Compare Image Patches via Convolutional Neural Networks","arxiv_id":"1504.03641","date":"2015-04-14","proceeding":"CVPR 2015 6","authors":["Sergey Zagoruyko","Nikos Komodakis"],"abstract":"In this paper we show how to learn directly from image data (i.e., without\nresorting to manually-designed features) a general similarity function for\ncomparing image patches, which is a task of fundamental importance for many\ncomputer vision problems. To encode such a function, we opt for a CNN-based\nmodel that is trained to account for a wide variety of changes in image\nappearance. To that end, we explore and study multiple neural network\narchitectures, which are specifically adapted to this task. We show that such\nan approach can significantly outperform the state-of-the-art on several\nproblems and benchmark datasets.","url_abs":"http://arxiv.org/abs/1504.03641v1","url_pdf":"http://arxiv.org/pdf/1504.03641v1.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-compare-image-patches-via","repo_url":"https://github.com/szagoruyko/cvpr15deepcompare","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"torch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1504.03641","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}