{"id":10,"date":"2025-05-09T21:20:26","date_gmt":"2025-05-09T21:20:26","guid":{"rendered":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/?page_id=10"},"modified":"2025-05-09T22:00:37","modified_gmt":"2025-05-09T22:00:37","slug":"related-works","status":"publish","type":"page","link":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/related-works\/","title":{"rendered":"Related Works"},"content":{"rendered":"\n<p>[1]<strong>EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation<\/strong><\/p>\n\n\n\n<p>EchoMimicV2, that leverages a novel\u00a0Audio-Pose Dynamic Harmonization\u00a0strategy, including\u00a0Pose Sampling\u00a0and\u00a0Audio Diffusion, to enhance half-body details, facial and gestural expressiveness, and meanwhile reduce conditions redundancy. To compensate for the scarcity of half-body data, we utilize\u00a0Head Partial Attention\u00a0to seamlessly accommodate headshot data into our training framework, which can be omitted during inference, providing a free lunch for animation. Furthermore, we design the\u00a0Phase-specific Denoising Loss\u00a0to guide motion, detail, and low-level quality for animation in specific phases, respectively. Besides, we also present a novel benchmark for evaluating the effectiveness of half-body human animation. Extensive experiments and analyses demonstrate that EchoMimicV2 surpasses existing methods in both quantitative and qualitative evaluations.<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"635\" height=\"333\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/wp-content\/uploads\/sites\/138\/2025\/05\/echo.png\" alt=\"\" class=\"wp-image-37\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/wp-content\/uploads\/sites\/138\/2025\/05\/echo.png 635w, https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/wp-content\/uploads\/sites\/138\/2025\/05\/echo-300x157.png 300w\" sizes=\"auto, (max-width: 635px) 100vw, 635px\" \/><\/figure>\n\n\n\n<p>Limitation of EchoMimicV2:<\/p>\n\n\n\n<p>&#8211; Requires manual input of hand pose sequences at inference time<\/p>\n\n\n\n<p>&#8211; Lacks gesture diversity due to fixed poses<\/p>\n\n\n\n<p>&#8211; Generated gestures can appear unnatural or repetitive<\/p>\n\n\n\n<p>&#8211; Not suitable for real-time or interactive applications<\/p>\n\n\n\n<p><\/p>\n\n\n\n<p><\/p>\n\n\n\n<p>[2]<strong>TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio-Motion Embedding<\/strong><\/p>\n\n\n\n<p> TANGO, a framework for generating co-speech body-gesture videos. Given a few-minute, single-speaker reference video and target speech audio, TANGO produces high-fidelity videos with synchronized body gestures. TANGO builds on Gesture Video Reenactment (GVR), which splits and retrieves video clips using a directed graph structure &#8211; representing video frames as nodes and valid transitions as edges. We address two key limitations of GVR: audio-motion misalignment and visual artifacts in GAN-generated transition frames. <\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"834\" height=\"193\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/wp-content\/uploads\/sites\/138\/2025\/05\/tango.png\" alt=\"\" class=\"wp-image-41\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/wp-content\/uploads\/sites\/138\/2025\/05\/tango.png 834w, https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/wp-content\/uploads\/sites\/138\/2025\/05\/tango-300x69.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/wp-content\/uploads\/sites\/138\/2025\/05\/tango-768x178.png 768w\" sizes=\"auto, (max-width: 706px) 89vw, (max-width: 767px) 82vw, 740px\" \/><\/figure>\n\n\n\n<p><\/p>\n\n\n\n<p>[3] <strong>From Slow Bidirectional toFast Autoregressive Video Diffusion Models<\/strong><\/p>\n\n\n\n<p>Current video diffusion models achieve impressive generation quality but struggle in interactive applications due to bidirectional attention dependencies. The generation of a single frame requires the model to process the entire sequence, including the future. We address this limitation by adapting a pretrained bidirectional diffusion transformer to an autoregressive transformer that generates frames on-the-fly. To further reduce latency, we extend distribution matching distillation (DMD) to videos, distilling 50-step diffusion model into a 4-step generator.\u00a0<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"369\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/wp-content\/uploads\/sites\/138\/2025\/05\/caus-1024x369.png\" alt=\"\" class=\"wp-image-46\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/wp-content\/uploads\/sites\/138\/2025\/05\/caus-1024x369.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/wp-content\/uploads\/sites\/138\/2025\/05\/caus-300x108.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/wp-content\/uploads\/sites\/138\/2025\/05\/caus-768x277.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/wp-content\/uploads\/sites\/138\/2025\/05\/caus.png 1464w\" sizes=\"auto, (max-width: 706px) 89vw, (max-width: 767px) 82vw, 740px\" \/><\/figure>\n","protected":false},"excerpt":{"rendered":"<p>[1]EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation EchoMimicV2, that leverages a novel\u00a0Audio-Pose Dynamic Harmonization\u00a0strategy, including\u00a0Pose Sampling\u00a0and\u00a0Audio Diffusion, to enhance half-body details, facial and gestural expressiveness, and meanwhile reduce conditions redundancy. To compensate for the scarcity of half-body data, we utilize\u00a0Head Partial Attention\u00a0to seamlessly accommodate headshot data into our training framework, which can be omitted &hellip; <\/p>\n<p class=\"link-more\"><a href=\"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/related-works\/\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;Related Works&#8221;<\/span><\/a><\/p>\n","protected":false},"author":260,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-10","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 Works - 2025 Team 16-1 Project<\/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\/2025team16-1\/related-works\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Related Works - 2025 Team 16-1 Project\" \/>\n<meta property=\"og:description\" content=\"[1]EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation EchoMimicV2, that leverages a novel\u00a0Audio-Pose Dynamic Harmonization\u00a0strategy, including\u00a0Pose Sampling\u00a0and\u00a0Audio Diffusion, to enhance half-body details, facial and gestural expressiveness, and meanwhile reduce conditions redundancy. To compensate for the scarcity of half-body data, we utilize\u00a0Head Partial Attention\u00a0to seamlessly accommodate headshot data into our training framework, which can be omitted &hellip; Continue reading &quot;Related Works&quot;\" \/>\n<meta property=\"og:url\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/related-works\/\" \/>\n<meta property=\"og:site_name\" content=\"2025 Team 16-1 Project\" \/>\n<meta property=\"article:modified_time\" content=\"2025-05-09T22:00:37+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/wp-content\/uploads\/sites\/138\/2025\/05\/echo.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\\\/2025team16-1\\\/related-works\\\/\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team16-1\\\/related-works\\\/\",\"name\":\"Related Works - 2025 Team 16-1 Project\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team16-1\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team16-1\\\/related-works\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team16-1\\\/related-works\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team16-1\\\/wp-content\\\/uploads\\\/sites\\\/138\\\/2025\\\/05\\\/echo.png\",\"datePublished\":\"2025-05-09T21:20:26+00:00\",\"dateModified\":\"2025-05-09T22:00:37+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team16-1\\\/related-works\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team16-1\\\/related-works\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team16-1\\\/related-works\\\/#primaryimage\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team16-1\\\/wp-content\\\/uploads\\\/sites\\\/138\\\/2025\\\/05\\\/echo.png\",\"contentUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team16-1\\\/wp-content\\\/uploads\\\/sites\\\/138\\\/2025\\\/05\\\/echo.png\",\"width\":635,\"height\":333},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team16-1\\\/related-works\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team16-1\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Related Works\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team16-1\\\/#website\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team16-1\\\/\",\"name\":\"2025 Team 16-1 Project\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team16-1\\\/?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 - 2025 Team 16-1 Project","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\/2025team16-1\/related-works\/","og_locale":"en_US","og_type":"article","og_title":"Related Works - 2025 Team 16-1 Project","og_description":"[1]EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation EchoMimicV2, that leverages a novel\u00a0Audio-Pose Dynamic Harmonization\u00a0strategy, including\u00a0Pose Sampling\u00a0and\u00a0Audio Diffusion, to enhance half-body details, facial and gestural expressiveness, and meanwhile reduce conditions redundancy. To compensate for the scarcity of half-body data, we utilize\u00a0Head Partial Attention\u00a0to seamlessly accommodate headshot data into our training framework, which can be omitted &hellip; Continue reading \"Related Works\"","og_url":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/related-works\/","og_site_name":"2025 Team 16-1 Project","article_modified_time":"2025-05-09T22:00:37+00:00","og_image":[{"url":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/wp-content\/uploads\/sites\/138\/2025\/05\/echo.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\/2025team16-1\/related-works\/","url":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/related-works\/","name":"Related Works - 2025 Team 16-1 Project","isPartOf":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/#website"},"primaryImageOfPage":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/related-works\/#primaryimage"},"image":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/related-works\/#primaryimage"},"thumbnailUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/wp-content\/uploads\/sites\/138\/2025\/05\/echo.png","datePublished":"2025-05-09T21:20:26+00:00","dateModified":"2025-05-09T22:00:37+00:00","breadcrumb":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/related-works\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/related-works\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/related-works\/#primaryimage","url":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/wp-content\/uploads\/sites\/138\/2025\/05\/echo.png","contentUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/wp-content\/uploads\/sites\/138\/2025\/05\/echo.png","width":635,"height":333},{"@type":"BreadcrumbList","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/related-works\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/"},{"@type":"ListItem","position":2,"name":"Related Works"}]},{"@type":"WebSite","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/#website","url":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/","name":"2025 Team 16-1 Project","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/?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\/2025team16-1\/wp-json\/wp\/v2\/pages\/10","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/wp-json\/wp\/v2\/users\/260"}],"replies":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/wp-json\/wp\/v2\/comments?post=10"}],"version-history":[{"count":5,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/wp-json\/wp\/v2\/pages\/10\/revisions"}],"predecessor-version":[{"id":47,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/wp-json\/wp\/v2\/pages\/10\/revisions\/47"}],"wp:attachment":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team16-1\/wp-json\/wp\/v2\/media?parent=10"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}