{"id":27,"date":"2026-05-06T23:35:52","date_gmt":"2026-05-06T23:35:52","guid":{"rendered":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf3\/?page_id=27"},"modified":"2026-05-07T21:08:03","modified_gmt":"2026-05-07T21:08:03","slug":"related-work","status":"publish","type":"page","link":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf3\/related-work\/","title":{"rendered":"Related Works"},"content":{"rendered":"\n

Related Works<\/strong><\/h2>\n\n\n\n

Non-rigging Methods<\/strong><\/h3>\n\n\n\n

Current non-rigging video-to-4D methods, either per-object optimization methods or feed-forward methods [1],[2], solve this task by optimizing\/predicting a canonical mesh (M)’s deformation at each timestep ({D_t}), so the rendered video aligns with the input. They start by generating a canonical mesh from a chosen canonical frame (I) via off-the-shelf image-to-3D models. Some feed-forward methods [1] further leverage 3D priors for deformation prediction. However, these methods fail to handle occlusions, extreme motion, or drastic shape\/topology changes over time due to the insufficient information provided by the canonical image and limitations of an image-to-3D model. We formulate this kind of failure as
M* != Imageto3D(I*), M: canon. mesh, I: frame, *: optimal<\/em>.<\/p>\n\n\n\n

To resolve this problem, we proposed to learn an optimal canonical mesh M* instead of simply using image-to-3D for canonical mesh generation.<\/p>\n\n\n\n

\n
\"\"<\/figure>\n<\/figure>\n\n\n\n

ActionMesh<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

Motion324<\/p>\n\n\n\n

Rigging-based Methods<\/strong><\/h3>\n\n\n\n

Current rigging-based methods approach the problem by automatically generating skeletal rigs and predicting skinning weights for 3D characters. Puppeteer [3] proposes an auto-regressive transformer for skeleton joint prediction with hierarchical ordering, combined with a topology-aware attention mechanism that encodes inter-joint relationships via skeletal graph distance. Animation is further optimized based on text-generated videos.<\/p>\n\n\n\n

However, these methods lack interactive editing capabilities, they do not support user-guided skeleton adjustment or editing-driven rig generation, making it difficult to refine or adapt the pipeline for specific characters or dynamic real-world objects.<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n
\"\"<\/figure>\n\n\n\n

References<\/strong><\/h3>\n\n\n\n

[1] R. Sabathier, D. Novotny, N. J. Mitra, and T. Monnier, \u201cActionMesh: Animated 3D Mesh Generation with Temporal 3D Diffusion,\u201d 2026, arXiv:2601.16148 [cs.CV]<\/p>\n\n\n\n

[2] H. Chen, X. Chen, Y. Zhang, Z. Xu, and A. Chen, \u201cMotion 3-to-4: 3D Motion Reconstruction for 4D Synthesis,\u201d 2026, arXiv:2601.14253 [cs.CV]<\/p>\n\n\n\n

[3] Song, Chaoyue, Xiu Li, Fan Yang, Zhongcong Xu, Jiacheng Wei, Fayao Liu, Jiashi Feng, Guosheng Lin, and Jianfeng Zhang. “Puppeteer: Rig and animate your 3d models.” 2025 arXiv:2508.10898<\/p>\n\n\n\n

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

Related Works Non-rigging Methods Current non-rigging video-to-4D methods, either per-object optimization methods or feed-forward methods [1],[2], solve this task by optimizing\/predicting a canonical mesh (M)’s deformation at each timestep ({D_t}), so the rendered video aligns with the input. They start by generating a canonical mesh from a chosen canonical frame (I) via off-the-shelf image-to-3D models. […]<\/p>\n","protected":false},"author":269,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-27","page","type-page","status-publish","hentry"],"yoast_head":"\nRelated Works - 3D Asset Generation: Generating Action Primitives<\/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\/2026teamf3\/related-work\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Related Works - 3D Asset Generation: Generating Action Primitives\" \/>\n<meta property=\"og:description\" content=\"Related Works Non-rigging Methods Current non-rigging video-to-4D methods, either per-object optimization methods or feed-forward methods [1],[2], solve this task by optimizing\/predicting a canonical mesh (M)’s deformation at each timestep ({D_t}), so the rendered video aligns with the input. They start by generating a canonical mesh from a chosen canonical frame (I) via off-the-shelf image-to-3D models. […]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf3\/related-work\/\" \/>\n<meta property=\"og:site_name\" content=\"3D Asset Generation: Generating Action Primitives\" \/>\n<meta property=\"article:modified_time\" content=\"2026-05-07T21:08:03+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf3\/wp-content\/uploads\/sites\/145\/2026\/05\/img2.png\" \/>\n\t<meta property=\"og:image:width\" content=\"1326\" \/>\n\t<meta property=\"og:image:height\" content=\"633\" \/>\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=\"3 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf3\\\/related-work\\\/\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf3\\\/related-work\\\/\",\"name\":\"Related Works - 3D Asset Generation: Generating Action Primitives\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf3\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf3\\\/related-work\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf3\\\/related-work\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf3\\\/wp-content\\\/uploads\\\/sites\\\/145\\\/2026\\\/05\\\/img2-1024x489.png\",\"datePublished\":\"2026-05-06T23:35:52+00:00\",\"dateModified\":\"2026-05-07T21:08:03+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf3\\\/related-work\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf3\\\/related-work\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf3\\\/related-work\\\/#primaryimage\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf3\\\/wp-content\\\/uploads\\\/sites\\\/145\\\/2026\\\/05\\\/img2.png\",\"contentUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf3\\\/wp-content\\\/uploads\\\/sites\\\/145\\\/2026\\\/05\\\/img2.png\",\"width\":1326,\"height\":633},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf3\\\/related-work\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf3\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Related Works\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf3\\\/#website\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf3\\\/\",\"name\":\"3D Asset Generation: Generating Action Primitives\",\"description\":\"Carnegie Mellon University\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2026teamf3\\\/?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 Works - 3D Asset Generation: Generating Action Primitives","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\/2026teamf3\/related-work\/","og_locale":"en_US","og_type":"article","og_title":"Related Works - 3D Asset Generation: Generating Action Primitives","og_description":"Related Works Non-rigging Methods Current non-rigging video-to-4D methods, either per-object optimization methods or feed-forward methods [1],[2], solve this task by optimizing\/predicting a canonical mesh (M)’s deformation at each timestep ({D_t}), so the rendered video aligns with the input. They start by generating a canonical mesh from a chosen canonical frame (I) via off-the-shelf image-to-3D models. […]","og_url":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf3\/related-work\/","og_site_name":"3D Asset Generation: Generating Action Primitives","article_modified_time":"2026-05-07T21:08:03+00:00","og_image":[{"width":1326,"height":633,"url":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf3\/wp-content\/uploads\/sites\/145\/2026\/05\/img2.png","type":"image\/png"}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf3\/related-work\/","url":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf3\/related-work\/","name":"Related Works - 3D Asset Generation: Generating Action Primitives","isPartOf":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf3\/#website"},"primaryImageOfPage":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf3\/related-work\/#primaryimage"},"image":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf3\/related-work\/#primaryimage"},"thumbnailUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf3\/wp-content\/uploads\/sites\/145\/2026\/05\/img2-1024x489.png","datePublished":"2026-05-06T23:35:52+00:00","dateModified":"2026-05-07T21:08:03+00:00","breadcrumb":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf3\/related-work\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/mscvprojects.ri.cmu.edu\/2026teamf3\/related-work\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf3\/related-work\/#primaryimage","url":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf3\/wp-content\/uploads\/sites\/145\/2026\/05\/img2.png","contentUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf3\/wp-content\/uploads\/sites\/145\/2026\/05\/img2.png","width":1326,"height":633},{"@type":"BreadcrumbList","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf3\/related-work\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf3\/"},{"@type":"ListItem","position":2,"name":"Related Works"}]},{"@type":"WebSite","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf3\/#website","url":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf3\/","name":"3D Asset Generation: Generating Action Primitives","description":"Carnegie Mellon University","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf3\/?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\/2026teamf3\/wp-json\/wp\/v2\/pages\/27","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf3\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf3\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf3\/wp-json\/wp\/v2\/users\/269"}],"replies":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf3\/wp-json\/wp\/v2\/comments?post=27"}],"version-history":[{"count":18,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf3\/wp-json\/wp\/v2\/pages\/27\/revisions"}],"predecessor-version":[{"id":116,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf3\/wp-json\/wp\/v2\/pages\/27\/revisions\/116"}],"wp:attachment":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2026teamf3\/wp-json\/wp\/v2\/media?parent=27"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}