{"id":26,"date":"2024-05-10T14:59:58","date_gmt":"2024-05-10T14:59:58","guid":{"rendered":"https:\/\/mscvprojects.ri.cmu.edu\/2024team3\/?page_id=26"},"modified":"2024-12-12T16:41:22","modified_gmt":"2024-12-12T16:41:22","slug":"methodology","status":"publish","type":"page","link":"https:\/\/mscvprojects.ri.cmu.edu\/2024team3\/methodology\/","title":{"rendered":"Methodology"},"content":{"rendered":"\n<h2 class=\"wp-block-heading\">Dataset Collection<\/h2>\n\n\n\n<p>We collect monocular RGB-D videos using an iPhone with the <a href=\"https:\/\/record3d.app\/\">Record3D<\/a> app. For each scene, we capture two types of data: <\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>A static object filmed with a moving camera<\/li>\n\n\n\n<li>A dynamic object filmed by two synchronized cameras.<\/li>\n<\/ul>\n\n\n\n<h2 class=\"wp-block-heading\">Pipeline<\/h2>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"508\" src=\"http:\/\/mscvprojects.ri.cmu.edu\/2024team3\/wp-content\/uploads\/sites\/101\/2024\/12\/pipeline_v2-1024x508.png\" alt=\"\" class=\"wp-image-198\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team3\/wp-content\/uploads\/sites\/101\/2024\/12\/pipeline_v2-1024x508.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2024team3\/wp-content\/uploads\/sites\/101\/2024\/12\/pipeline_v2-300x149.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2024team3\/wp-content\/uploads\/sites\/101\/2024\/12\/pipeline_v2-768x381.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2024team3\/wp-content\/uploads\/sites\/101\/2024\/12\/pipeline_v2-1536x761.png 1536w, https:\/\/mscvprojects.ri.cmu.edu\/2024team3\/wp-content\/uploads\/sites\/101\/2024\/12\/pipeline_v2.png 1606w\" sizes=\"auto, (max-width: 706px) 89vw, (max-width: 767px) 82vw, 740px\" \/><figcaption class=\"wp-element-caption\">Fig:4 Canonical Gaussians are initialized from a static sequence. At each timestep, deformation is decomposed into a global rigid transformation (via segmentation) and a local non-rigid deformation (using sparse node deformation). Finally, liveframe Gaussians are splatted to render RGB and depth images.<\/figcaption><\/figure>\n\n\n\n<p>In the process outlined in Figure 4, initialization of the canonical Gaussians from a static sequence marks the starting point. This initialization sets the foundation for subsequent steps, where at each timestep, the deformation is broken down into two distinct components: a rigid global transformation and a non-rigid local deformation. This decomposition strategy allows for a nuanced understanding of the evolving scene dynamics, capturing both global shifts and localized changes over time. The frames are processed in a progressive fashion.<\/p>\n\n\n\n<p>The non-rigid local deformation is modeled using a sparse node representation obtained by performing farthest sampling on canonical Gaussians to obtain canonical sparse points. Each point is associated with a radius to determine its influence and neighborhood connectivity. The deformed Gaussians are obtained by performing Dual Quaternion Blending(DQB) using the nearest neighbor nodes at time &#8216;t&#8217;. The rigid global transformation is obtained for each gaussian by blending the individual segment global transformations based on the neighborhood segment category of the gaussians.<\/p>\n\n\n\n<p>Finally, as the process unfolds, liveframe Gaussians are effectively utilized to generate RGB and depth images, providing a comprehensive representation of the scene&#8217;s visual and spatial characteristics. Through this systematic approach, the framework ensures a robust and accurate rendering of dynamic scenes, offering valuable insights into their temporal evolution.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Dataset Collection We collect monocular RGB-D videos using an iPhone with the Record3D app. For each scene, we capture two types of data: Pipeline In the process outlined in Figure 4, initialization of the canonical Gaussians from a static sequence marks the starting point. This initialization sets the foundation for subsequent steps, where at each &hellip; <\/p>\n<p class=\"link-more\"><a href=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team3\/methodology\/\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;Methodology&#8221;<\/span><\/a><\/p>\n","protected":false},"author":197,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-26","page","type-page","status-publish","hentry"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.4 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Methodology - Dynamic Reconstruction of Non-rigid Scenes from Monocular RGB-D Videos<\/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\/2024team3\/methodology\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Methodology - Dynamic Reconstruction of Non-rigid Scenes from Monocular RGB-D Videos\" \/>\n<meta property=\"og:description\" content=\"Dataset Collection We collect monocular RGB-D videos using an iPhone with the Record3D app. For each scene, we capture two types of data: Pipeline In the process outlined in Figure 4, initialization of the canonical Gaussians from a static sequence marks the starting point. This initialization sets the foundation for subsequent steps, where at each &hellip; Continue reading &quot;Methodology&quot;\" \/>\n<meta property=\"og:url\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team3\/methodology\/\" \/>\n<meta property=\"og:site_name\" content=\"Dynamic Reconstruction of Non-rigid Scenes from Monocular RGB-D Videos\" \/>\n<meta property=\"article:modified_time\" content=\"2024-12-12T16:41:22+00:00\" \/>\n<meta property=\"og:image\" content=\"http:\/\/mscvprojects.ri.cmu.edu\/2024team3\/wp-content\/uploads\/sites\/101\/2024\/12\/pipeline_v2-1024x508.png\" \/>\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\\\/2024team3\\\/methodology\\\/\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team3\\\/methodology\\\/\",\"name\":\"Methodology - Dynamic Reconstruction of Non-rigid Scenes from Monocular RGB-D Videos\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team3\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team3\\\/methodology\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team3\\\/methodology\\\/#primaryimage\"},\"thumbnailUrl\":\"http:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team3\\\/wp-content\\\/uploads\\\/sites\\\/101\\\/2024\\\/12\\\/pipeline_v2-1024x508.png\",\"datePublished\":\"2024-05-10T14:59:58+00:00\",\"dateModified\":\"2024-12-12T16:41:22+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team3\\\/methodology\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team3\\\/methodology\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team3\\\/methodology\\\/#primaryimage\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team3\\\/wp-content\\\/uploads\\\/sites\\\/101\\\/2024\\\/12\\\/pipeline_v2.png\",\"contentUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team3\\\/wp-content\\\/uploads\\\/sites\\\/101\\\/2024\\\/12\\\/pipeline_v2.png\",\"width\":1606,\"height\":796},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team3\\\/methodology\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team3\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Methodology\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team3\\\/#website\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team3\\\/\",\"name\":\"Dynamic Reconstruction of Non-rigid Scenes from Monocular RGB-D Videos\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team3\\\/?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":"Methodology - Dynamic Reconstruction of Non-rigid Scenes from Monocular RGB-D Videos","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\/2024team3\/methodology\/","og_locale":"en_US","og_type":"article","og_title":"Methodology - Dynamic Reconstruction of Non-rigid Scenes from Monocular RGB-D Videos","og_description":"Dataset Collection We collect monocular RGB-D videos using an iPhone with the Record3D app. For each scene, we capture two types of data: Pipeline In the process outlined in Figure 4, initialization of the canonical Gaussians from a static sequence marks the starting point. This initialization sets the foundation for subsequent steps, where at each &hellip; Continue reading \"Methodology\"","og_url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team3\/methodology\/","og_site_name":"Dynamic Reconstruction of Non-rigid Scenes from Monocular RGB-D Videos","article_modified_time":"2024-12-12T16:41:22+00:00","og_image":[{"url":"http:\/\/mscvprojects.ri.cmu.edu\/2024team3\/wp-content\/uploads\/sites\/101\/2024\/12\/pipeline_v2-1024x508.png","type":"","width":"","height":""}],"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\/2024team3\/methodology\/","url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team3\/methodology\/","name":"Methodology - Dynamic Reconstruction of Non-rigid Scenes from Monocular RGB-D Videos","isPartOf":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team3\/#website"},"primaryImageOfPage":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team3\/methodology\/#primaryimage"},"image":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team3\/methodology\/#primaryimage"},"thumbnailUrl":"http:\/\/mscvprojects.ri.cmu.edu\/2024team3\/wp-content\/uploads\/sites\/101\/2024\/12\/pipeline_v2-1024x508.png","datePublished":"2024-05-10T14:59:58+00:00","dateModified":"2024-12-12T16:41:22+00:00","breadcrumb":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team3\/methodology\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/mscvprojects.ri.cmu.edu\/2024team3\/methodology\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team3\/methodology\/#primaryimage","url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team3\/wp-content\/uploads\/sites\/101\/2024\/12\/pipeline_v2.png","contentUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2024team3\/wp-content\/uploads\/sites\/101\/2024\/12\/pipeline_v2.png","width":1606,"height":796},{"@type":"BreadcrumbList","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team3\/methodology\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/mscvprojects.ri.cmu.edu\/2024team3\/"},{"@type":"ListItem","position":2,"name":"Methodology"}]},{"@type":"WebSite","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team3\/#website","url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team3\/","name":"Dynamic Reconstruction of Non-rigid Scenes from Monocular RGB-D Videos","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/mscvprojects.ri.cmu.edu\/2024team3\/?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\/2024team3\/wp-json\/wp\/v2\/pages\/26","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team3\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team3\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team3\/wp-json\/wp\/v2\/users\/197"}],"replies":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team3\/wp-json\/wp\/v2\/comments?post=26"}],"version-history":[{"count":8,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team3\/wp-json\/wp\/v2\/pages\/26\/revisions"}],"predecessor-version":[{"id":203,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team3\/wp-json\/wp\/v2\/pages\/26\/revisions\/203"}],"wp:attachment":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team3\/wp-json\/wp\/v2\/media?parent=26"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}