{"id":11,"date":"2026-05-06T07:24:35","date_gmt":"2026-05-06T07:24:35","guid":{"rendered":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/?page_id=11"},"modified":"2026-05-08T01:36:02","modified_gmt":"2026-05-08T01:36:02","slug":"home","status":"publish","type":"page","link":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/","title":{"rendered":"Team F11 Projects"},"content":{"rendered":"\n
\n
\n
\n

Disentangled\nGaussian Transformers for Animatable Humans<\/h4>\n

Soham Dasgupta<\/em><\/p>\n

Reconstructing animatable 3D human avatars from casual inputs \u2014 a single image or monocular video \u2014 remains a difficult problem. Recent feed-forward models such as LHM regress Gaussian avatars directly from images but suffer from spatial misalignment with the input and over-smoothed textures, both stemming from a reliance on linear blend skinning (LBS) to explain inherently non-rigid motion.\nWe propose Disentangled Gaussian Transformers (DGT), a transformer-based framework that produces animatable 3D Gaussian avatars from variable inputs while separating canonical geometry from pose-dependent deformation. DGT uses a multi-stream point transformer: a canonical T-stream refines a shared T-pose avatar across all inputs, and per-image P-streams predict residual deformations in the posed space. A Foreground Point Projection module injects localized 2D evidence into the 3D Gaussians, correcting pixel-level misalignment without compromising geometric consistency.<\/p>\n<\/div>\n<\/div>\n\n\n\n

\n
\n

Cooperative Foundation Models For Object Detection Active Learning\n<\/h4>\n

Zizheng Zhou<\/em><\/p>\n

Object detection requires costly bounding-box annotations. Active learning reduces the number of images to label, but selected samples still need manual box drawing, which remains slow and expensive. We propose CoMODAL, an active learning framework that uses multiple foundation models cooperatively to reduce annotation effort. A vision-language model committee first mines reliable negative images without human labeling. Then, a dual-objective query strategy selects diverse high-uncertainty samples and likely high-confidence false positives using DINOv3 patch embeddings. Finally, foundation models propose candidate boxes, so the human oracle only needs to approve or reject them instead of drawing boxes from scratch. This turns object detection active learning into a more efficient, lower-cost annotation pipeline.<\/p>\n<\/div>\n<\/div>\n<\/div>\n\n\n\n

\n
\n
\n
View<\/a><\/div>\n<\/div>\n<\/div>\n\n\n\n
\n
\n
View<\/a><\/div>\n<\/div>\n<\/div>\n<\/div>\n\n\n\n

<\/p>\n","protected":false},"excerpt":{"rendered":"

Disentangled Gaussian Transformers for Animatable Humans Soham Dasgupta Reconstructing animatable 3D human avatars from casual inputs \u2014 a single image or monocular video \u2014 remains a difficult problem. Recent feed-forward models such as LHM regress Gaussian avatars directly from images but suffer from spatial misalignment with the input and over-smoothed textures, both stemming from a […]<\/p>\n","protected":false},"author":288,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-11","page","type-page","status-publish","hentry"],"yoast_head":"\nTeam F11 Projects - Disentangled Gaussian Transformers for Animatable Humans | Cooperative Foundation Models For Object Detection Active Learning<\/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\/2026teamf11\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Team F11 Projects - Disentangled Gaussian Transformers for Animatable Humans | Cooperative Foundation Models For Object Detection Active Learning\" \/>\n<meta property=\"og:description\" content=\"Disentangled Gaussian Transformers for Animatable Humans Soham Dasgupta Reconstructing animatable 3D human avatars from casual inputs \u2014 a single image or monocular video \u2014 remains a difficult problem. Recent feed-forward models such as LHM regress Gaussian avatars directly from images but suffer from spatial misalignment with the input and over-smoothed textures, both stemming from a […]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/\" \/>\n<meta property=\"og:site_name\" content=\"Disentangled Gaussian Transformers for Animatable Humans | Cooperative Foundation Models For Object Detection Active Learning\" \/>\n<meta property=\"article:modified_time\" content=\"2026-05-08T01:36:02+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\\\/2026teamf11\\\/\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf11\\\/\",\"name\":\"Team F11 Projects - Disentangled Gaussian Transformers for Animatable Humans | Cooperative Foundation Models For Object Detection Active Learning\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf11\\\/#website\"},\"datePublished\":\"2026-05-06T07:24:35+00:00\",\"dateModified\":\"2026-05-08T01:36:02+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf11\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf11\\\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf11\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf11\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Team F11 Projects\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf11\\\/#website\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf11\\\/\",\"name\":\"Disentangled Gaussian Transformers for Animatable Humans | Cooperative Foundation Models For Object Detection Active Learning\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf11\\\/?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":"Team F11 Projects - Disentangled Gaussian Transformers for Animatable Humans | Cooperative Foundation Models For Object Detection Active Learning","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\/2026teamf11\/","og_locale":"en_US","og_type":"article","og_title":"Team F11 Projects - Disentangled Gaussian Transformers for Animatable Humans | Cooperative Foundation Models For Object Detection Active Learning","og_description":"Disentangled Gaussian Transformers for Animatable Humans Soham Dasgupta Reconstructing animatable 3D human avatars from casual inputs \u2014 a single image or monocular video \u2014 remains a difficult problem. Recent feed-forward models such as LHM regress Gaussian avatars directly from images but suffer from spatial misalignment with the input and over-smoothed textures, both stemming from a […]","og_url":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/","og_site_name":"Disentangled Gaussian Transformers for Animatable Humans | Cooperative Foundation Models For Object Detection Active Learning","article_modified_time":"2026-05-08T01:36:02+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\/2026teamf11\/","url":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/","name":"Team F11 Projects - Disentangled Gaussian Transformers for Animatable Humans | Cooperative Foundation Models For Object Detection Active Learning","isPartOf":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/#website"},"datePublished":"2026-05-06T07:24:35+00:00","dateModified":"2026-05-08T01:36:02+00:00","breadcrumb":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/"},{"@type":"ListItem","position":2,"name":"Team F11 Projects"}]},{"@type":"WebSite","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/#website","url":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/","name":"Disentangled Gaussian Transformers for Animatable Humans | Cooperative Foundation Models For Object Detection Active Learning","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/?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\/2026teamf11\/wp-json\/wp\/v2\/pages\/11","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/wp-json\/wp\/v2\/users\/288"}],"replies":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/wp-json\/wp\/v2\/comments?post=11"}],"version-history":[{"count":22,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/wp-json\/wp\/v2\/pages\/11\/revisions"}],"predecessor-version":[{"id":182,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/wp-json\/wp\/v2\/pages\/11\/revisions\/182"}],"wp:attachment":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf11\/wp-json\/wp\/v2\/media?parent=11"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}