{"id":53,"date":"2026-05-07T04:29:53","date_gmt":"2026-05-07T04:29:53","guid":{"rendered":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/related-work\/"},"modified":"2026-05-07T05:21:51","modified_gmt":"2026-05-07T05:21:51","slug":"related-work","status":"publish","type":"page","link":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/related-work\/","title":{"rendered":"Related Work"},"content":{"rendered":"\n<p class=\"is-style-text-subtitle is-style-text-subtitle--1\"><strong><a href=\"https:\/\/arxiv.org\/pdf\/2503.11651\" data-type=\"link\" data-id=\"https:\/\/arxiv.org\/pdf\/2503.11651\">VGGT<\/a><\/strong><\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"391\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/wp-content\/uploads\/sites\/149\/2026\/05\/image-3-1024x391.png\" alt=\"\" class=\"wp-image-66\" title=\"Screenshot 2026-02-23 at 2.56.48\u202fPM.png\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/wp-content\/uploads\/sites\/149\/2026\/05\/image-3-1024x391.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/wp-content\/uploads\/sites\/149\/2026\/05\/image-3-300x115.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/wp-content\/uploads\/sites\/149\/2026\/05\/image-3-768x293.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/wp-content\/uploads\/sites\/149\/2026\/05\/image-3.png 1366w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Alternating-Attention Transformer: <\/strong>Inputs patch tokens and leverages global attention and frame attention, combining per-view detail with multi-view consistency.<\/li>\n\n\n\n<li><strong>Training Strategy: <\/strong>Conducts multi-task supervision, including pose estimation, reconstruction and point tracking.<\/li>\n<\/ul>\n\n\n\n<p> <\/p>\n\n\n\n<p class=\"is-style-text-subtitle is-style-text-subtitle--2\"><strong><a href=\"https:\/\/arxiv.org\/pdf\/2507.11539\" data-type=\"link\" data-id=\"https:\/\/arxiv.org\/pdf\/2507.11539\">StreamVGGT<\/a><\/strong><\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"669\" height=\"334\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/wp-content\/uploads\/sites\/149\/2026\/05\/image-4.png\" alt=\"\" class=\"wp-image-67\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/wp-content\/uploads\/sites\/149\/2026\/05\/image-4.png 669w, https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/wp-content\/uploads\/sites\/149\/2026\/05\/image-4-300x150.png 300w\" sizes=\"auto, (max-width: 669px) 100vw, 669px\" \/><\/figure>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Causal Streaming Architecture: <\/strong>Replaces global self-attention with temporal causal attention to enable real-time, sequential 4D updates for up to 100 frames.<\/li>\n\n\n\n<li><strong>Knowledge Distillation: <\/strong>Leverages a pre-trained VGGT teacher to maintain high-fidelity reconstruction quality in the streaming student model.<\/li>\n<\/ul>\n\n\n\n<p> <\/p>\n\n\n\n<p class=\"is-style-text-subtitle is-style-text-subtitle--3\"><strong><a href=\"https:\/\/henry123-boy.github.io\/SpaTracker\/\" data-type=\"link\" data-id=\"https:\/\/henry123-boy.github.io\/SpaTracker\/\">Spatial Tracker<\/a><\/strong><\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"962\" height=\"423\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/wp-content\/uploads\/sites\/149\/2026\/05\/image-5.png\" alt=\"\" class=\"wp-image-68\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/wp-content\/uploads\/sites\/149\/2026\/05\/image-5.png 962w, https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/wp-content\/uploads\/sites\/149\/2026\/05\/image-5-300x132.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/wp-content\/uploads\/sites\/149\/2026\/05\/image-5-768x338.png 768w\" sizes=\"auto, (max-width: 962px) 100vw, 962px\" \/><\/figure>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>3D point tracking Decomposition: <\/strong>Decomposes world-space 3D motion into scene geometry, camera ego-motion, and pixel-wise object motion<\/li>\n\n\n\n<li><strong>A unified and differentiable pipeline:<\/strong> A fully differentiable pipeline that supports scalable joint training across heterogeneous data.<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>VGGT StreamVGGT Spatial Tracker<\/p>\n","protected":false},"author":278,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-53","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>Related Work - Slot4D: Learning Object Slots for 4D Reconstruction<\/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\/2026teamf7\/related-work\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Related Work - Slot4D: Learning Object Slots for 4D Reconstruction\" \/>\n<meta property=\"og:description\" content=\"VGGT StreamVGGT Spatial Tracker\" \/>\n<meta property=\"og:url\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/related-work\/\" \/>\n<meta property=\"og:site_name\" content=\"Slot4D: Learning Object Slots for 4D Reconstruction\" \/>\n<meta property=\"article:modified_time\" content=\"2026-05-07T05:21:51+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/wp-content\/uploads\/sites\/149\/2026\/05\/image-3.png\" \/>\n\t<meta property=\"og:image:width\" content=\"1366\" \/>\n\t<meta property=\"og:image:height\" content=\"522\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/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=\"1 minute\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf7\\\/related-work\\\/\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf7\\\/related-work\\\/\",\"name\":\"Related Work - Slot4D: Learning Object Slots for 4D Reconstruction\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf7\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf7\\\/related-work\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf7\\\/related-work\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf7\\\/wp-content\\\/uploads\\\/sites\\\/149\\\/2026\\\/05\\\/image-3-1024x391.png\",\"datePublished\":\"2026-05-07T04:29:53+00:00\",\"dateModified\":\"2026-05-07T05:21:51+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf7\\\/related-work\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf7\\\/related-work\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf7\\\/related-work\\\/#primaryimage\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf7\\\/wp-content\\\/uploads\\\/sites\\\/149\\\/2026\\\/05\\\/image-3.png\",\"contentUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf7\\\/wp-content\\\/uploads\\\/sites\\\/149\\\/2026\\\/05\\\/image-3.png\",\"width\":1366,\"height\":522},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf7\\\/related-work\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf7\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Related Work\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf7\\\/#website\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf7\\\/\",\"name\":\"Slot4D: Learning Object Slots for 4D Reconstruction\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf7\\\/?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":"Related Work - Slot4D: Learning Object Slots for 4D Reconstruction","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\/2026teamf7\/related-work\/","og_locale":"en_US","og_type":"article","og_title":"Related Work - Slot4D: Learning Object Slots for 4D Reconstruction","og_description":"VGGT StreamVGGT Spatial Tracker","og_url":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/related-work\/","og_site_name":"Slot4D: Learning Object Slots for 4D Reconstruction","article_modified_time":"2026-05-07T05:21:51+00:00","og_image":[{"width":1366,"height":522,"url":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/wp-content\/uploads\/sites\/149\/2026\/05\/image-3.png","type":"image\/png"}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"1 minute"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/related-work\/","url":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/related-work\/","name":"Related Work - Slot4D: Learning Object Slots for 4D Reconstruction","isPartOf":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/#website"},"primaryImageOfPage":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/related-work\/#primaryimage"},"image":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/related-work\/#primaryimage"},"thumbnailUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/wp-content\/uploads\/sites\/149\/2026\/05\/image-3-1024x391.png","datePublished":"2026-05-07T04:29:53+00:00","dateModified":"2026-05-07T05:21:51+00:00","breadcrumb":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/related-work\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/related-work\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/related-work\/#primaryimage","url":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/wp-content\/uploads\/sites\/149\/2026\/05\/image-3.png","contentUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/wp-content\/uploads\/sites\/149\/2026\/05\/image-3.png","width":1366,"height":522},{"@type":"BreadcrumbList","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/related-work\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/"},{"@type":"ListItem","position":2,"name":"Related Work"}]},{"@type":"WebSite","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/#website","url":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/","name":"Slot4D: Learning Object Slots for 4D Reconstruction","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/?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\/2026teamf7\/wp-json\/wp\/v2\/pages\/53","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/wp-json\/wp\/v2\/users\/278"}],"replies":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/wp-json\/wp\/v2\/comments?post=53"}],"version-history":[{"count":4,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/wp-json\/wp\/v2\/pages\/53\/revisions"}],"predecessor-version":[{"id":73,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/wp-json\/wp\/v2\/pages\/53\/revisions\/73"}],"wp:attachment":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf7\/wp-json\/wp\/v2\/media?parent=53"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}