{"id":16,"date":"2025-05-10T02:55:54","date_gmt":"2025-05-10T02:55:54","guid":{"rendered":"https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/?page_id=16"},"modified":"2025-12-13T03:29:32","modified_gmt":"2025-12-13T03:29:32","slug":"proposed-solution","status":"publish","type":"page","link":"https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/proposed-solution\/","title":{"rendered":"Method"},"content":{"rendered":"\n<p>Human, camera trajectories, and world are not independent.<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"590\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/wp-content\/uploads\/sites\/121\/2025\/12\/\u622a\u5c4f2025-12-12-22.20.41-1024x590.png\" alt=\"\" class=\"wp-image-83\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/wp-content\/uploads\/sites\/121\/2025\/12\/\u622a\u5c4f2025-12-12-22.20.41-1024x590.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/wp-content\/uploads\/sites\/121\/2025\/12\/\u622a\u5c4f2025-12-12-22.20.41-300x173.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/wp-content\/uploads\/sites\/121\/2025\/12\/\u622a\u5c4f2025-12-12-22.20.41-768x443.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/wp-content\/uploads\/sites\/121\/2025\/12\/\u622a\u5c4f2025-12-12-22.20.41-1536x886.png 1536w, https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/wp-content\/uploads\/sites\/121\/2025\/12\/\u622a\u5c4f2025-12-12-22.20.41.png 1833w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Part 1: Camera-World Geometric Consistency Constraints<\/strong><\/h2>\n\n\n\n<p>We design a constraint that enforces geometric consistency of human mesh between the camera coordinate frame and the world coordinate frame. This helps ensure that the reconstructed human motion makes sense globally \u2014 not just from the camera\u2019s point of view, but also in the world space.<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"592\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/wp-content\/uploads\/sites\/121\/2025\/12\/\u622a\u5c4f2025-12-12-22.23.36-1024x592.png\" alt=\"\" class=\"wp-image-84\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/wp-content\/uploads\/sites\/121\/2025\/12\/\u622a\u5c4f2025-12-12-22.23.36-1024x592.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/wp-content\/uploads\/sites\/121\/2025\/12\/\u622a\u5c4f2025-12-12-22.23.36-300x173.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/wp-content\/uploads\/sites\/121\/2025\/12\/\u622a\u5c4f2025-12-12-22.23.36-768x444.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/wp-content\/uploads\/sites\/121\/2025\/12\/\u622a\u5c4f2025-12-12-22.23.36-1536x888.png 1536w, https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/wp-content\/uploads\/sites\/121\/2025\/12\/\u622a\u5c4f2025-12-12-22.23.36-2048x1184.png 2048w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Part 2: Test-Time Camera Trajectory Fusion<\/strong><\/h2>\n\n\n\n<p>Use HMR-predicted trajectory for scale &amp; absolute pose; use feed-forward trajectory for smoothness and global consistency.<\/p>\n\n\n\n<p>(1) HMR-predicted trajectory:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u00a0\u00a0\u00a0\u00a0 <strong>Pros<\/strong>: Contains depth information \u2192 less affected by scale ambiguity<\/li>\n\n\n\n<li>\u00a0\u00a0\u00a0\u00a0 <strong>Cons<\/strong>: However, less smooth since it is estimated frame-by-frame from human joints<\/li>\n<\/ul>\n\n\n\n<p>(2) Feed-forward trajectory:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u00a0\u00a0\u00a0\u00a0 <strong>Pros<\/strong>: Smoother and globally more reliable<\/li>\n\n\n\n<li>\u00a0\u00a0\u00a0\u00a0 <strong>Cons<\/strong>: But susceptible to scale ambiguity<\/li>\n<\/ul>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"310\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/wp-content\/uploads\/sites\/121\/2025\/12\/\u622a\u5c4f2025-12-12-22.28.37-1024x310.png\" alt=\"\" class=\"wp-image-89\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/wp-content\/uploads\/sites\/121\/2025\/12\/\u622a\u5c4f2025-12-12-22.28.37-1024x310.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/wp-content\/uploads\/sites\/121\/2025\/12\/\u622a\u5c4f2025-12-12-22.28.37-300x91.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/wp-content\/uploads\/sites\/121\/2025\/12\/\u622a\u5c4f2025-12-12-22.28.37-768x233.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/wp-content\/uploads\/sites\/121\/2025\/12\/\u622a\u5c4f2025-12-12-22.28.37-1536x466.png 1536w, https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/wp-content\/uploads\/sites\/121\/2025\/12\/\u622a\u5c4f2025-12-12-22.28.37.png 1781w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><\/figure>\n\n\n\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Human, camera trajectories, and world are not independent. Part 1: Camera-World Geometric Consistency Constraints We design a constraint that enforces geometric consistency of human mesh between the camera coordinate frame and the world coordinate frame. This helps ensure that the reconstructed human motion makes sense globally \u2014 not just from the camera\u2019s point of view, &hellip; <\/p>\n<p class=\"link-more\"><a href=\"https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/proposed-solution\/\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;Method&#8221;<\/span><\/a><\/p>\n","protected":false},"author":235,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-16","page","type-page","status-publish","hentry"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v28.1 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Method - World-Grounded Human Mesh Recovery from Video<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/proposed-solution\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Method - World-Grounded Human Mesh Recovery from Video\" \/>\n<meta property=\"og:description\" content=\"Human, camera trajectories, and world are not independent. Part 1: Camera-World Geometric Consistency Constraints We design a constraint that enforces geometric consistency of human mesh between the camera coordinate frame and the world coordinate frame. This helps ensure that the reconstructed human motion makes sense globally \u2014 not just from the camera\u2019s point of view, &hellip; Continue reading &quot;Method&quot;\" \/>\n<meta property=\"og:url\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/proposed-solution\/\" \/>\n<meta property=\"og:site_name\" content=\"World-Grounded Human Mesh Recovery from Video\" \/>\n<meta property=\"article:modified_time\" content=\"2025-12-13T03:29:32+00:00\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"2 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team9-1\\\/proposed-solution\\\/\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team9-1\\\/proposed-solution\\\/\",\"name\":\"Method - World-Grounded Human Mesh Recovery from Video\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team9-1\\\/#website\"},\"datePublished\":\"2025-05-10T02:55:54+00:00\",\"dateModified\":\"2025-12-13T03:29:32+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team9-1\\\/proposed-solution\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team9-1\\\/proposed-solution\\\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team9-1\\\/proposed-solution\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team9-1\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Method\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team9-1\\\/#website\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team9-1\\\/\",\"name\":\"World-Grounded Human Mesh Recovery from Video\",\"description\":\"Liting Wen, Yiwen Zhao, Ce Zheng, L\u00e1szl\u00f3 A. Jeni \",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team9-1\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Method - World-Grounded Human Mesh Recovery from Video","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/proposed-solution\/","og_locale":"en_US","og_type":"article","og_title":"Method - World-Grounded Human Mesh Recovery from Video","og_description":"Human, camera trajectories, and world are not independent. Part 1: Camera-World Geometric Consistency Constraints We design a constraint that enforces geometric consistency of human mesh between the camera coordinate frame and the world coordinate frame. This helps ensure that the reconstructed human motion makes sense globally \u2014 not just from the camera\u2019s point of view, &hellip; Continue reading \"Method\"","og_url":"https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/proposed-solution\/","og_site_name":"World-Grounded Human Mesh Recovery from Video","article_modified_time":"2025-12-13T03:29:32+00:00","twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/proposed-solution\/","url":"https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/proposed-solution\/","name":"Method - World-Grounded Human Mesh Recovery from Video","isPartOf":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/#website"},"datePublished":"2025-05-10T02:55:54+00:00","dateModified":"2025-12-13T03:29:32+00:00","breadcrumb":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/proposed-solution\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/proposed-solution\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/proposed-solution\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/"},{"@type":"ListItem","position":2,"name":"Method"}]},{"@type":"WebSite","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/#website","url":"https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/","name":"World-Grounded Human Mesh Recovery from Video","description":"Liting Wen, Yiwen Zhao, Ce Zheng, L\u00e1szl\u00f3 A. Jeni ","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"}]}},"_links":{"self":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/wp-json\/wp\/v2\/pages\/16","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/wp-json\/wp\/v2\/users\/235"}],"replies":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/wp-json\/wp\/v2\/comments?post=16"}],"version-history":[{"count":6,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/wp-json\/wp\/v2\/pages\/16\/revisions"}],"predecessor-version":[{"id":90,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/wp-json\/wp\/v2\/pages\/16\/revisions\/90"}],"wp:attachment":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team9-1\/wp-json\/wp\/v2\/media?parent=16"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}