{"id":675435,"date":"2020-07-28T16:37:52","date_gmt":"2020-07-28T23:37:52","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-research-item&p=675435"},"modified":"2021-03-22T14:26:52","modified_gmt":"2021-03-22T21:26:52","slug":"the-phong-surface-efficient-3d-model-fitting-using-lifted-optimization","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/the-phong-surface-efficient-3d-model-fitting-using-lifted-optimization\/","title":{"rendered":"The Phong Surface: Efficient 3D Model Fitting Using Lifted Optimization"},"content":{"rendered":"

Realtime perceptual and interaction capabilities in mixed reality require a range of 3D tracking problems to be solved at low latency on resource-constrained hardware such as head-mounted devices. Indeed, for devices such as HoloLens 2 where the CPU and GPU are left available for applications, multiple tracking subsystems are required to run on a continuous, real-time basis while sharing a single Digital Signal Processor. To solve model-fitting problems for HoloLens 2 hand tracking, where the computational budget is approximately 100 times smaller than an iPhone 7, we introduce a new surface model: the \u2018Phong surface\u2019. Using ideas from computer graphics, the Phong surface describes the same 3D shape as a triangulated mesh model, but with continuous surface normals which enable the use of lifting-based optimization, providing significant efficiency gains over ICP-based methods. We show that Phong surfaces retain the convergence benefits of smoother surface models, while triangle meshes do not.<\/p>\n","protected":false},"excerpt":{"rendered":"

Realtime perceptual and interaction capabilities in mixed reality require a range of 3D tracking problems to be solved at low latency on resource-constrained hardware such as head-mounted devices. Indeed, for devices such as HoloLens 2 where the CPU and GPU are left available for applications, multiple tracking subsystems are required to run on a continuous, […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13562,13551],"msr-publication-type":[193716],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-field-of-study":[254458,248467,248113,246691,246949,254464,254467,254455,254461],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-675435","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-computer-vision","msr-research-area-graphics-and-multimedia","msr-locale-en_us","msr-field-of-study-central-processing-unit","msr-field-of-study-computational-science","msr-field-of-study-computer-graphics","msr-field-of-study-computer-science","msr-field-of-study-convergence-routing","msr-field-of-study-digital-signal-processor","msr-field-of-study-mixed-reality","msr-field-of-study-polygon-mesh","msr-field-of-study-pose"],"msr_publishername":"Springer, Cham","msr_edition":"","msr_affiliation":"","msr_published_date":"2020-8-22","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","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":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/07\/PhongSurface_2597_ECCV2020.pdf","id":"676971","title":"phongsurface_2597_eccv2020","label_id":"243132","label":0},{"type":"doi","viewUrl":"false","id":"false","title":"10.1007\/978-3-030-58452-8_40","label_id":"243106","label":0}],"msr_related_uploader":[{"type":"file","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/07\/PhongSurfaceSupplementary.pdf","id":"675444","title":"phongsurfacesupplementary","label_id":"243118","label":0}],"msr_attachments":[{"id":676974,"url":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/07\/PhongSurfaceSupplementary-5f16ac95a4ccc.pdf"},{"id":676971,"url":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/07\/PhongSurface_2597_ECCV2020.pdf"},{"id":675447,"url":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/07\/PhongSurface.pdf"},{"id":675444,"url":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/07\/PhongSurfaceSupplementary.pdf"},{"id":675441,"url":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/07\/2597.pdf"},{"id":675438,"url":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/07\/PhongSurface_eccv2020.pdf"}],"msr-author-ordering":[{"type":"user_nicename","value":"Jingjing Shen","user_id":39375,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Jingjing Shen"},{"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":"text","value":"Qi Ye","user_id":0,"rest_url":false},{"type":"text","value":"Tim Hutton","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Toby Sharp","user_id":34344,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Toby Sharp"},{"type":"user_nicename","value":"Federica Bogo","user_id":36263,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Federica Bogo"},{"type":"user_nicename","value":"Andrew Fitzgibbon","user_id":31157,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Andrew Fitzgibbon"},{"type":"user_nicename","value":"Jamie Shotton","user_id":32162,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Jamie Shotton"}],"msr_impact_theme":[],"msr_research_lab":[602418,734161],"msr_event":[679467],"msr_group":[],"msr_project":[171411],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/675435"}],"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":9,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/675435\/revisions"}],"predecessor-version":[{"id":735463,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/675435\/revisions\/735463"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=675435"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=675435"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=675435"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=675435"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=675435"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=675435"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=675435"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=675435"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=675435"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=675435"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=675435"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=675435"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=675435"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=675435"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=675435"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}