We tackle the problem of highly-accurate, holistic performance capture for the face, body and hands simultaneously. Motion-capture technologies used in film and game production typically focus only on face, body or hand capture independently, involve complex and expensive hardware and a high degree of manual intervention from skilled operators. While machine-learning-based approaches exist to overcome these problems, they usually only support a single camera, often operate on a single part of the body, do not produce precise world-space results, and rarely generalize outside specific contexts. In this work, we introduce the first technique for marker-free, high-quality reconstruction of the complete human body, including eyes and tongue, without requiring any calibration, manual intervention or custom hardware. Our approach produces stable world-space results from arbitrary camera rigs as well as supporting varied capture environments and clothing. We achieve this through a hybrid approach that leverages machine learning models trained exclusively on synthetic data and powerful parametric models of human shape and motion. We evaluate our method on a number of body, face and hand reconstruction benchmarks and demonstrate state-of-the-art results that generalize on diverse datasets.<\/p>\n","protected":false},"excerpt":{"rendered":"
We tackle the problem of highly-accurate, holistic performance capture for the face, body and hands simultaneously. Motion-capture technologies used in film and game production typically focus only on face, body or hand capture independently, involve complex and expensive hardware and a high degree of manual intervention from skilled operators. While machine-learning-based approaches exist to overcome […]<\/p>\n","protected":false},"featured_media":1094709,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","msr-author-ordering":null,"msr_publishername":"","msr_publisher_other":"","msr_booktitle":"","msr_chapter":"","msr_edition":"","msr_editors":"","msr_how_published":"","msr_isbn":"","msr_issue":"6","msr_journal":"","msr_number":"","msr_organization":"","msr_pages_string":"","msr_page_range_start":"235:1","msr_page_range_end":"235:12","msr_series":"","msr_volume":"36","msr_copyright":"","msr_conference_name":"","msr_doi":"","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":"2024-12-1","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":null,"footnotes":""},"msr-research-highlight":[],"research-area":[13562,13551],"msr-publication-type":[193715],"msr-publisher":[],"msr-focus-area":[],"msr-locale":[268875],"msr-post-option":[269148,269142],"msr-field-of-study":[248113,246688],"msr-conference":[],"msr-journal":[266817],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-1094703","msr-research-item","type-msr-research-item","status-publish","has-post-thumbnail","hentry","msr-research-area-computer-vision","msr-research-area-graphics-and-multimedia","msr-locale-en_us","msr-post-option-approved-for-river","msr-post-option-include-in-river","msr-field-of-study-computer-graphics","msr-field-of-study-computer-vision"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2024-12-1","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"36","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"6","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":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/aka.ms\/SynthMoCap","label_id":"243109","label":0},{"type":"doi","viewUrl":"false","id":"false","title":"10.1145\/3687772","label_id":"243106","label":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":"edited_text","value":"Charlie Hewitt","user_id":40840,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Charlie Hewitt"},{"type":"user_nicename","value":"Fatemeh Saleh","user_id":43938,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Fatemeh Saleh"},{"type":"edited_text","value":"Sadegh Aliakbarian","user_id":40837,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Sadegh Aliakbarian"},{"type":"user_nicename","value":"Lohit Petikam","user_id":42999,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Lohit Petikam"},{"type":"user_nicename","value":"Shideh Rezaeifar","user_id":41506,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Shideh Rezaeifar"},{"type":"text","value":"Louis Florentin","user_id":0,"rest_url":false},{"type":"text","value":"Zafiirah Hosenie","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Tom Cashman","user_id":33914,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Tom Cashman"},{"type":"user_nicename","value":"Julien Valentin","user_id":42111,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Julien Valentin"},{"type":"user_nicename","value":"Prof. Darren Cosker","user_id":40618,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Prof. Darren Cosker"},{"type":"user_nicename","value":"Tadas Baltrusaitis","user_id":39378,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Tadas Baltrusaitis"}],"msr_impact_theme":[],"msr_research_lab":[734161],"msr_event":[],"msr_group":[],"msr_project":[],"publication":[],"video":[],"msr-tool":[],"msr_publication_type":"article","related_content":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1094703","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":7,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1094703\/revisions"}],"predecessor-version":[{"id":1145158,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1094703\/revisions\/1145158"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/1094709"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=1094703"}],"wp:term":[{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=1094703"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=1094703"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=1094703"},{"taxonomy":"msr-publisher","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publisher?post=1094703"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=1094703"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=1094703"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=1094703"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=1094703"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=1094703"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=1094703"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=1094703"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=1094703"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}