{"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/deep-functional-maps-structured-prediction","title":"Deep Functional Maps: Structured Prediction for Dense Shape Correspondence","arxiv_id":"1704.08686","date":"2017-04-27","proceeding":"ICCV 2017 10","authors":["Or Litany","Tal Remez","Emanuele Rodolà","Alex M. Bronstein","Michael M. Bronstein"],"abstract":"We introduce a new framework for learning dense correspondence between\ndeformable 3D shapes. Existing learning based approaches model shape\ncorrespondence as a labelling problem, where each point of a query shape\nreceives a label identifying a point on some reference domain; the\ncorrespondence is then constructed a posteriori by composing the label\npredictions of two input shapes. We propose a paradigm shift and design a\nstructured prediction model in the space of functional maps, linear operators\nthat provide a compact representation of the correspondence. We model the\nlearning process via a deep residual network which takes dense descriptor\nfields defined on two shapes as input, and outputs a soft map between the two\ngiven objects. The resulting correspondence is shown to be accurate on several\nchallenging benchmarks comprising multiple categories, synthetic models, real\nscans with acquisition artifacts, topological noise, and partiality.","url_abs":"http://arxiv.org/abs/1704.08686v2","url_pdf":"http://arxiv.org/pdf/1704.08686v2.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":"deep-functional-maps-structured-prediction","repo_url":"https://github.com/orlitany/DeepFunctionalMaps","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"deep-functional-maps-structured-prediction","repo_url":"https://github.com/JM-data/Unsupervised_DeepFunctionalMaps","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deep-functional-maps-structured-prediction","repo_url":"https://github.com/pvnieo/FMNet-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"structured-prediction","task_name":"Structured Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1704.08686","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}