3D morphable models are low-dimensional parametrizations of 3D object classes which provide a powerful means of associating 3D geometry to 2D images. However, morphable models are currently generated from 3D scans, so for general object classes such as animals they are economically and practically infeasible. We show that, given a small amount of user interaction (little more than that required to build a conventional morphable model), there is enough information in a collection of 2D pictures of certain object classes to generate a full 3D morphable model, even in the absence of surface texture. The key restriction is that the object class should not be strongly articulated, and that a very rough rigid model should be provided as an initial estimate of the \u2018mean shape\u2019.<\/p>\n
The model representation is a linear combination of subdivision surfaces, which we fit to image silhouettes and any identifiable key points using a novel combined continuous-discrete optimization strategy. Results are demonstrated on several natural object classes, and show that models of rather high quality can be obtained from this limited information.<\/p>\n","protected":false},"excerpt":{"rendered":"
3D morphable models are low-dimensional parametrizations of 3D object classes which provide a powerful means of associating 3D geometry to 2D images. However, morphable models are currently generated from 3D scans, so for general object classes such as animals they are economically and practically infeasible. We show that, given a small amount of user interaction […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","msr-author-ordering":[{"type":"user_nicename","value":"tcashman"},{"type":"user_nicename","value":"awf"}],"msr_publishername":"IEEE - Institute of Electrical and Electronics Engineers","msr_publisher_other":"","msr_booktitle":"","msr_chapter":"","msr_edition":"IEEE Transactions on Pattern Analysis and Maching Intelligence","msr_editors":"","msr_how_published":"","msr_isbn":"","msr_issue":"","msr_journal":"IEEE Transactions on Pattern Analysis and Maching Intelligence","msr_number":"","msr_organization":"","msr_pages_string":"232 - 244","msr_page_range_start":"232","msr_page_range_end":"","msr_series":"","msr_volume":"35","msr_copyright":"\u00a9 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting\/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.","msr_conference_name":"","msr_doi":"10.1109\/TPAMI.2012.68","msr_arxiv_id":"","msr_s2_paper_id":"","msr_mag_id":"","msr_pubmed_id":"","msr_other_authors":"","msr_other_contributors":"","msr_speaker":"","msr_award":"","msr_affiliation":"","msr_institution":"","msr_host":"","msr_version":"","msr_duration":"","msr_original_fields_of_study":"","msr_release_tracker_id":"","msr_s2_match_type":"","msr_citation_count_updated":"","msr_published_date":"2013-01-01","msr_highlight_text":"","msr_notes":"","msr_longbiography":"","msr_publicationurl":"","msr_external_url":"","msr_secondary_video_url":"","msr_conference_url":"","msr_journal_url":"","msr_s2_pdf_url":"","msr_year":0,"msr_citation_count":0,"msr_influential_citations":0,"msr_reference_count":0,"msr_s2_match_confidence":0,"msr_microsoftintellectualproperty":true,"msr_s2_open_access":false,"msr_s2_author_ids":[],"msr_pub_ids":[],"msr_hide_image_in_river":0,"footnotes":""},"msr-research-highlight":[],"research-area":[13562],"msr-publication-type":[193715],"msr-publisher":[],"msr-focus-area":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-242477","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-computer-vision","msr-locale-en_us"],"msr_publishername":"IEEE - Institute of Electrical and Electronics Engineers","msr_edition":"IEEE Transactions on Pattern Analysis and Maching Intelligence","msr_affiliation":"","msr_published_date":"2013-01-01","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"232 - 244","msr_chapter":"","msr_isbn":"","msr_journal":"IEEE Transactions on Pattern Analysis and Maching Intelligence","msr_volume":"35","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"242501","msr_publicationurl":"","msr_doi":"10.1109\/TPAMI.2012.68","msr_publication_uploader":[{"type":"file","title":"Cashman.2012.WSD","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2013\/01\/Cashman.2012.WSD_.pdf","id":242501,"label_id":0},{"type":"doi","title":"10.1109\/TPAMI.2012.68","viewUrl":false,"id":false,"label_id":0}],"msr_related_uploader":"","msr_citation_count":0,"msr_citation_count_updated":"","msr_s2_paper_id":"","msr_influential_citations":0,"msr_reference_count":0,"msr_arxiv_id":"","msr_s2_author_ids":[],"msr_s2_open_access":false,"msr_s2_pdf_url":null,"msr_attachments":[],"msr-author-ordering":[{"type":"user_nicename","value":"tcashman","user_id":33914,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=tcashman"},{"type":"user_nicename","value":"awf","user_id":31157,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=awf"}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[],"msr_project":[238767],"publication":[],"video":[],"msr-tool":[],"msr_publication_type":"article","related_content":{"projects":[{"ID":238767,"post_title":"Subdivision Surfaces in Computer Vision","post_name":"subdivision-surfaces-in-computer-vision","post_type":"msr-project","post_date":"2016-10-05 05:54:25","post_modified":"2020-07-14 01:50:14","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/subdivision-surfaces-in-computer-vision\/","post_excerpt":"In vision and machine learning, almost everything we do may be considered to be a form of model fitting. Whether estimating the parameters of a convolutional neural network, computing structure and motion from image collections, tracking objects in video, computing low-dimensional representations of datasets, estimating parameters for an inference model such as Markov random fields, or extracting shape spaces such as active appearance models, it almost always boils down to minimizing an objective containing some…","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/238767"}]}}]},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/242477","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":2,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/242477\/revisions"}],"predecessor-version":[{"id":542417,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/242477\/revisions\/542417"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=242477"}],"wp:term":[{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=242477"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=242477"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=242477"},{"taxonomy":"msr-publisher","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publisher?post=242477"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=242477"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=242477"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=242477"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=242477"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=242477"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=242477"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=242477"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=242477"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}