{"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/lift-learned-invariant-feature-transform","title":"LIFT: Learned Invariant Feature Transform","arxiv_id":"1603.09114","date":"2016-03-30","proceeding":null,"authors":["Kwang Moo Yi","Eduard Trulls","Vincent Lepetit","Pascal Fua"],"abstract":"We introduce a novel Deep Network architecture that implements the full\nfeature point handling pipeline, that is, detection, orientation estimation,\nand feature description. While previous works have successfully tackled each\none of these problems individually, we show how to learn to do all three in a\nunified manner while preserving end-to-end differentiability. We then\ndemonstrate that our Deep pipeline outperforms state-of-the-art methods on a\nnumber of benchmark datasets, without the need of retraining.","url_abs":"http://arxiv.org/abs/1603.09114v2","url_pdf":"http://arxiv.org/pdf/1603.09114v2.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":"lift-learned-invariant-feature-transform","repo_url":"https://github.com/cvlab-epfl/LIFT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1603.09114","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}