{"id":12,"date":"2024-05-12T22:58:08","date_gmt":"2024-05-12T22:58:08","guid":{"rendered":"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/?page_id=12"},"modified":"2024-12-15T11:32:59","modified_gmt":"2024-12-15T11:32:59","slug":"related-work","status":"publish","type":"page","link":"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/related-work\/","title":{"rendered":"Related Work"},"content":{"rendered":"\n<h4 class=\"wp-block-heading\">3D-LFM: Lifting Foundation Model<\/h4>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"569\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-content\/uploads\/sites\/111\/2024\/05\/Image-5-12-24-at-9.15\u202fPM-1024x569.jpeg\" alt=\"\" class=\"wp-image-43\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-content\/uploads\/sites\/111\/2024\/05\/Image-5-12-24-at-9.15\u202fPM-1024x569.jpeg 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-content\/uploads\/sites\/111\/2024\/05\/Image-5-12-24-at-9.15\u202fPM-300x167.jpeg 300w, https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-content\/uploads\/sites\/111\/2024\/05\/Image-5-12-24-at-9.15\u202fPM-768x427.jpeg 768w, https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-content\/uploads\/sites\/111\/2024\/05\/Image-5-12-24-at-9.15\u202fPM-1536x854.jpeg 1536w, https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-content\/uploads\/sites\/111\/2024\/05\/Image-5-12-24-at-9.15\u202fPM.jpeg 1906w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Utilizes Graph Transformer with Procrustean alignment to learn non-rigid deformations<\/li>\n\n\n\n<li>Robust against order and number of input keypoints &#8211; displays permutation equivariance<\/li>\n\n\n\n<li>Shows OOD generalization on unseen categories<\/li>\n<\/ul>\n\n\n\n<p><\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity is-style-wide\" \/>\n\n\n\n<h4 class=\"wp-block-heading\">Unsupervised Keypoints from Pretrained Diffusion Models<\/h4>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"344\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-content\/uploads\/sites\/111\/2024\/05\/Image-5-12-24-at-9.17\u202fPM-1024x344.jpeg\" alt=\"\" class=\"wp-image-45\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-content\/uploads\/sites\/111\/2024\/05\/Image-5-12-24-at-9.17\u202fPM-1024x344.jpeg 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-content\/uploads\/sites\/111\/2024\/05\/Image-5-12-24-at-9.17\u202fPM-300x101.jpeg 300w, https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-content\/uploads\/sites\/111\/2024\/05\/Image-5-12-24-at-9.17\u202fPM-768x258.jpeg 768w, https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-content\/uploads\/sites\/111\/2024\/05\/Image-5-12-24-at-9.17\u202fPM-1536x516.jpeg 1536w, https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-content\/uploads\/sites\/111\/2024\/05\/Image-5-12-24-at-9.17\u202fPM.jpeg 1832w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Detects semantically meaningful 2D key points in an unsupervised way<\/li>\n\n\n\n<li>Uses emergent knowledge within pretrained Stable Diffusion model<\/li>\n\n\n\n<li>A randomized text embedding is optimized with the diffusion model to learn to attend to the relevant keypoints in the image<\/li>\n<\/ul>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity is-style-wide\" \/>\n\n\n\n<h4 class=\"wp-block-heading\">MotionBERT: A Unified Perspective on Learning Human Motion Representations<\/h4>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"1344\" height=\"424\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-content\/uploads\/sites\/111\/2024\/05\/Image-5-12-24-at-9.19\u202fPM-1.jpeg\" alt=\"\" class=\"wp-image-47\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-content\/uploads\/sites\/111\/2024\/05\/Image-5-12-24-at-9.19\u202fPM-1.jpeg 1344w, https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-content\/uploads\/sites\/111\/2024\/05\/Image-5-12-24-at-9.19\u202fPM-1-300x95.jpeg 300w, https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-content\/uploads\/sites\/111\/2024\/05\/Image-5-12-24-at-9.19\u202fPM-1-1024x323.jpeg 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-content\/uploads\/sites\/111\/2024\/05\/Image-5-12-24-at-9.19\u202fPM-1-768x242.jpeg 768w\" sizes=\"auto, (max-width: 1344px) 100vw, 1344px\" \/><\/figure>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Motion encoder learns human motion patterns using pretraining on noisy, occluded inputs<\/li>\n\n\n\n<li>Uses dual-stage spatio temporal attention&nbsp;blocks<\/li>\n\n\n\n<li>Finetuned MLP for downstream tasks &#8211; pose estimation, mesh reconstruction, activity recognition<\/li>\n<\/ul>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity is-style-wide\" \/>\n\n\n\n<h4 class=\"wp-block-heading\">TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation<\/h4>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"949\" height=\"552\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-content\/uploads\/sites\/111\/2024\/12\/img3.png\" alt=\"\" class=\"wp-image-142\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-content\/uploads\/sites\/111\/2024\/12\/img3.png 949w, https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-content\/uploads\/sites\/111\/2024\/12\/img3-300x174.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-content\/uploads\/sites\/111\/2024\/12\/img3-768x447.png 768w\" sizes=\"auto, (max-width: 949px) 100vw, 949px\" \/><\/figure>\n\n\n\n<ul class=\"wp-block-list\">\n<li>A feature extractor + vision transformer backbone with seperate MLP heads to predict camera parameters, pose and shape from an input image<\/li>\n\n\n\n<li>Instead of regressing SMPL pose, it predicts a pose token class which is then reconstructed into a continuous pose using the pretrained codebook<\/li>\n\n\n\n<li>A VQ-VAE is pretrained to act as a tokenizer codebook where SMPL poses are encoded into discrete tokens and reconstructed by the decoder<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>3D-LFM: Lifting Foundation Model Unsupervised Keypoints from Pretrained Diffusion Models MotionBERT: A Unified Perspective on Learning Human Motion Representations TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation<\/p>\n","protected":false},"author":217,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-12","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 - Towards Universal 3D Lifting<\/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\/2024team13\/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 - Towards Universal 3D Lifting\" \/>\n<meta property=\"og:description\" content=\"3D-LFM: Lifting Foundation Model Unsupervised Keypoints from Pretrained Diffusion Models MotionBERT: A Unified Perspective on Learning Human Motion Representations TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation\" \/>\n<meta property=\"og:url\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/related-work\/\" \/>\n<meta property=\"og:site_name\" content=\"Towards Universal 3D Lifting\" \/>\n<meta property=\"article:modified_time\" content=\"2024-12-15T11:32:59+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-content\/uploads\/sites\/111\/2024\/12\/img3.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\\\/2024team13\\\/related-work\\\/\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team13\\\/related-work\\\/\",\"name\":\"Related Work - Towards Universal 3D Lifting\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team13\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team13\\\/related-work\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team13\\\/related-work\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team13\\\/wp-content\\\/uploads\\\/sites\\\/111\\\/2024\\\/12\\\/img3.png\",\"datePublished\":\"2024-05-12T22:58:08+00:00\",\"dateModified\":\"2024-12-15T11:32:59+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team13\\\/related-work\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team13\\\/related-work\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team13\\\/related-work\\\/#primaryimage\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team13\\\/wp-content\\\/uploads\\\/sites\\\/111\\\/2024\\\/12\\\/img3.png\",\"contentUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team13\\\/wp-content\\\/uploads\\\/sites\\\/111\\\/2024\\\/12\\\/img3.png\",\"width\":949,\"height\":552},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team13\\\/related-work\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team13\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Related Work\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team13\\\/#website\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team13\\\/\",\"name\":\"Towards Universal 3D Lifting\",\"description\":\"\",\"publisher\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team13\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team13\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team13\\\/#organization\",\"name\":\"Towards Universal 3D Lifting\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team13\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team13\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team13\\\/wp-content\\\/uploads\\\/sites\\\/111\\\/2024\\\/05\\\/Screenshot-2024-05-12-at-8.26.44\u202fPM.png\",\"contentUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team13\\\/wp-content\\\/uploads\\\/sites\\\/111\\\/2024\\\/05\\\/Screenshot-2024-05-12-at-8.26.44\u202fPM.png\",\"width\":588,\"height\":325,\"caption\":\"Towards Universal 3D Lifting\"},\"image\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team13\\\/#\\\/schema\\\/logo\\\/image\\\/\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Related Work - Towards Universal 3D Lifting","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\/2024team13\/related-work\/","og_locale":"en_US","og_type":"article","og_title":"Related Work - Towards Universal 3D Lifting","og_description":"3D-LFM: Lifting Foundation Model Unsupervised Keypoints from Pretrained Diffusion Models MotionBERT: A Unified Perspective on Learning Human Motion Representations TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation","og_url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/related-work\/","og_site_name":"Towards Universal 3D Lifting","article_modified_time":"2024-12-15T11:32:59+00:00","og_image":[{"url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-content\/uploads\/sites\/111\/2024\/12\/img3.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\/2024team13\/related-work\/","url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/related-work\/","name":"Related Work - Towards Universal 3D Lifting","isPartOf":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/#website"},"primaryImageOfPage":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/related-work\/#primaryimage"},"image":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/related-work\/#primaryimage"},"thumbnailUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-content\/uploads\/sites\/111\/2024\/12\/img3.png","datePublished":"2024-05-12T22:58:08+00:00","dateModified":"2024-12-15T11:32:59+00:00","breadcrumb":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/related-work\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/related-work\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/related-work\/#primaryimage","url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-content\/uploads\/sites\/111\/2024\/12\/img3.png","contentUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-content\/uploads\/sites\/111\/2024\/12\/img3.png","width":949,"height":552},{"@type":"BreadcrumbList","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/related-work\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/"},{"@type":"ListItem","position":2,"name":"Related Work"}]},{"@type":"WebSite","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/#website","url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/","name":"Towards Universal 3D Lifting","description":"","publisher":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/#organization","name":"Towards Universal 3D Lifting","url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/#\/schema\/logo\/image\/","url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-content\/uploads\/sites\/111\/2024\/05\/Screenshot-2024-05-12-at-8.26.44\u202fPM.png","contentUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-content\/uploads\/sites\/111\/2024\/05\/Screenshot-2024-05-12-at-8.26.44\u202fPM.png","width":588,"height":325,"caption":"Towards Universal 3D Lifting"},"image":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/#\/schema\/logo\/image\/"}}]}},"_links":{"self":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-json\/wp\/v2\/pages\/12","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-json\/wp\/v2\/users\/217"}],"replies":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-json\/wp\/v2\/comments?post=12"}],"version-history":[{"count":8,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-json\/wp\/v2\/pages\/12\/revisions"}],"predecessor-version":[{"id":147,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-json\/wp\/v2\/pages\/12\/revisions\/147"}],"wp:attachment":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team13\/wp-json\/wp\/v2\/media?parent=12"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}