{"id":34,"date":"2019-12-06T01:51:58","date_gmt":"2019-12-06T01:51:58","guid":{"rendered":"http:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/?p=34"},"modified":"2019-12-11T04:00:57","modified_gmt":"2019-12-11T04:00:57","slug":"detailed-description","status":"publish","type":"post","link":"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/2019\/12\/06\/detailed-description\/","title":{"rendered":"Detailed Description"},"content":{"rendered":"<ul>\n<li>Introduction<\/li>\n<\/ul>\n<p><span style=\"font-weight: 400\">We\u2019re trying to build realistic human models for virtual reality. The goal is to build human body models from multi-view RGB images given camera parameters, with highest possible level of detail. The high quality human we reconstruct may help overcome the uncanny valley problem, and eventually enable the next generation of gaming and social applications in VR context.<\/span><\/p>\n<p>&nbsp;<\/p>\n<ul>\n<li>Device and Setting<\/li>\n<\/ul>\n<p><span style=\"font-weight: 400\">There are more than one hundred cameras, all of 4K resolution, half of which are colored and the other half are grayscale. All cameras are pre-calibrated. The subject being captured is inside a capture room with static background.\u00a0<\/span><\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-medium wp-image-47\" src=\"http:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image9-195x300.png\" alt=\"\" width=\"195\" height=\"300\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image9-195x300.png 195w, https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image9.png 325w\" sizes=\"auto, (max-width: 195px) 100vw, 195px\" \/> <img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-medium wp-image-48\" src=\"http:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image13-195x300.png\" alt=\"\" width=\"195\" height=\"300\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image13-195x300.png 195w, https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image13.png 325w\" sizes=\"auto, (max-width: 195px) 100vw, 195px\" \/><\/p>\n<p>On the left is an image of our capture room. All the black dots are cameras. On the right is a showcase of a standard capture setup, with a subject standing inside the room.<\/p>\n<p>&nbsp;<\/p>\n<ul>\n<li>Pipeline<\/li>\n<\/ul>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone wp-image-50\" src=\"http:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/16622-Final-300x169.jpg\" alt=\"\" width=\"470\" height=\"265\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/16622-Final-300x169.jpg 300w, https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/16622-Final-768x432.jpg 768w, https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/16622-Final.jpg 960w\" sizes=\"auto, (max-width: 470px) 100vw, 470px\" \/><\/p>\n<p>The pipeline consists of several components. First, dense multi-view reconstruction is performed on all the images captured. We perform foreground segmentation for each image to acquire a high-resolution human mask, which builds a visual hull that constraints the reconstruction. After that, a parametrized, personalized human template mesh will be optimized to fit its shape and pose to the reconstructed mesh. This involves an optimization process developed by us, including several loss terms which will be introduced later. Finally, some additional optimization will be applied to the human template, which further improves the level of details.<\/p>\n<p>&nbsp;<\/p>\n<ul>\n<li>High-Resolution Foreground Segmentation<\/li>\n<\/ul>\n<p>In order to deal with all the difficulty induced by shadow, color confusion and grayscale images, we developed an end-to-end encoder-decoder network for high-resolution human foreground segmentation. We trained this network with synthetic data and it&#8217;s able to generate masks with pixel-level accuracy regardless of color or grayscale. Checkout the detailed structure in our slides.\u00a0 Here are some example results:<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-medium wp-image-55\" src=\"http:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image2-1-195x300.png\" alt=\"\" width=\"195\" height=\"300\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image2-1-195x300.png 195w, https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image2-1-768x1179.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image2-1-667x1024.png 667w, https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image2-1.png 1302w\" sizes=\"auto, (max-width: 195px) 100vw, 195px\" \/> <img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-medium wp-image-56\" src=\"http:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image3-2-195x300.png\" alt=\"\" width=\"195\" height=\"300\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image3-2-195x300.png 195w, https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image3-2-768x1179.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image3-2-667x1024.png 667w, https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image3-2.png 1302w\" sizes=\"auto, (max-width: 195px) 100vw, 195px\" \/><\/p>\n<p>&nbsp;<\/p>\n<ul>\n<li>MVS and Poisson Reconstruction<\/li>\n<\/ul>\n<p>Standard multi-view stereo reconstruction only gives us a pointcloud. We use Poisson reconstruction to turn that into a mesh. In this process we leverage a visual hull generated by the segmentation masks to improve the result mesh: outlier points with wrong normals can be filtered out. This is implemented by inspecting the indicator oct-tree nodes. Here are some examples of colored Poisson reconstruction mesh.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-medium wp-image-58\" src=\"http:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image1-1-144x300.png\" alt=\"\" width=\"144\" height=\"300\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image1-1-144x300.png 144w, https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image1-1-490x1024.png 490w, https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image1-1.png 522w\" sizes=\"auto, (max-width: 144px) 100vw, 144px\" \/> <img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-medium wp-image-59\" src=\"http:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image4-1-98x300.png\" alt=\"\" width=\"98\" height=\"300\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image4-1-98x300.png 98w, https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image4-1-334x1024.png 334w, https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image4-1.png 368w\" sizes=\"auto, (max-width: 98px) 100vw, 98px\" \/>\u00a0<img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-medium wp-image-68\" src=\"http:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image14-154x300.png\" alt=\"\" width=\"154\" height=\"300\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image14-154x300.png 154w, https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image14-526x1024.png 526w, https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image14.png 530w\" sizes=\"auto, (max-width: 154px) 100vw, 154px\" \/><\/p>\n<p>&nbsp;<\/p>\n<ul>\n<li>Fitting Personalized and Parametrized Body Template<\/li>\n<\/ul>\n<p>In this step we optimize the pose and shape parameters of a personalized body template to fit it closely with the reconstructed mesh. The template mesh uses linear blend skinning model to model how the skeleton affects surface shape. There is a kinematic chain as shown in the figure below. We also demonstrate a visualization of the human-designed skinning weights.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone wp-image-61\" src=\"http:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image8-1-269x300.png\" alt=\"\" width=\"133\" height=\"148\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image8-1-269x300.png 269w, https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image8-1-768x856.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image8-1-919x1024.png 919w, https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image8-1.png 959w\" sizes=\"auto, (max-width: 133px) 100vw, 133px\" \/>\u00a0<img loading=\"lazy\" decoding=\"async\" class=\"alignnone wp-image-62\" style=\"font-size: 1rem\" src=\"http:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image17-300x292.png\" alt=\"\" width=\"124\" height=\"121\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image17-300x292.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image17.png 640w\" sizes=\"auto, (max-width: 124px) 100vw, 124px\" \/><span style=\"font-size: 1rem\">\u00a0<\/span><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-medium wp-image-63\" style=\"font-size: 1rem\" src=\"http:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image18-300x158.png\" alt=\"\" width=\"300\" height=\"158\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image18-300x158.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image18-768x404.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image18.png 857w\" sizes=\"auto, (max-width: 300px) 100vw, 300px\" \/><\/p>\n<p>Here is an example of a reconstructed mesh and the fitted mesh.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-medium wp-image-65\" src=\"http:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image15-1-117x300.png\" alt=\"\" width=\"117\" height=\"300\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image15-1-117x300.png 117w, https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image15-1-400x1024.png 400w, https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image15-1.png 440w\" sizes=\"auto, (max-width: 117px) 100vw, 117px\" \/><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-medium wp-image-64\" style=\"font-size: 1rem\" src=\"http:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image13-1-111x300.png\" alt=\"\" width=\"111\" height=\"300\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image13-1-111x300.png 111w, https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image13-1-378x1024.png 378w, https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image13-1.png 416w\" sizes=\"auto, (max-width: 111px) 100vw, 111px\" \/><\/p>\n<p>&nbsp;<\/p>\n<ul>\n<li>Further Refinements<\/li>\n<\/ul>\n<p>There are two additional refinement steps after fitting the parametrized body mesh. The first one is called local blendshape model. The body mesh is divided into a large number of small patches, each of which has its own blendshape model and parameters. The second one is per-vertex deformation, where each vertex will have a 3-vector assigned to it to further model the finest surface deformation. Here we show the comparison with and without these refinements.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-medium wp-image-67\" src=\"http:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image13-2-111x300.png\" alt=\"\" width=\"111\" height=\"300\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image13-2-111x300.png 111w, https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image13-2-378x1024.png 378w, https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image13-2.png 416w\" sizes=\"auto, (max-width: 111px) 100vw, 111px\" \/><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-medium wp-image-66\" style=\"font-size: 1rem\" src=\"http:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image5-1-109x300.png\" alt=\"\" width=\"109\" height=\"300\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image5-1-109x300.png 109w, https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image5-1.png 416w\" sizes=\"auto, (max-width: 109px) 100vw, 109px\" \/><\/p>\n<p>&nbsp;<\/p>\n<ul>\n<li>Results<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-medium wp-image-69\" src=\"http:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image6-2-247x300.png\" alt=\"\" width=\"247\" height=\"300\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image6-2-247x300.png 247w, https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image6-2-768x932.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image6-2-844x1024.png 844w, https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image6-2.png 944w\" sizes=\"auto, (max-width: 247px) 100vw, 247px\" \/> <img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-medium wp-image-70\" src=\"http:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image7-2-126x300.png\" alt=\"\" width=\"126\" height=\"300\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image7-2-126x300.png 126w, https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image7-2-431x1024.png 431w, https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image7-2.png 458w\" sizes=\"auto, (max-width: 126px) 100vw, 126px\" \/><\/p>\n<p>A video example:<\/p>\n<p><a href=\"https:\/\/drive.google.com\/file\/d\/1DRDD-aDxc1NHQz9e09BxA6yzq_s0F0H1\/view?usp=sharing\">https:\/\/drive.google.com\/file\/d\/1DRDD-aDxc1NHQz9e09BxA6yzq_s0F0H1\/view?usp=sharing<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Introduction We\u2019re trying to build realistic human models for virtual reality. The goal is to build human body models from multi-view RGB images given camera parameters, with highest possible level of detail. The high quality human we reconstruct may help overcome the uncanny valley problem, and eventually enable the next generation of gaming and social &hellip; <\/p>\n<p class=\"link-more\"><a href=\"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/2019\/12\/06\/detailed-description\/\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;Detailed Description&#8221;<\/span><\/a><\/p>\n","protected":false},"author":40,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"image","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-34","post","type-post","status-publish","format-image","hentry","category-uncategorized","post_format-post-format-image"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.4 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Detailed Description - Realistic Human Modeling for Virtual Reality<\/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\/2019teamd\/2019\/12\/06\/detailed-description\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Detailed Description - Realistic Human Modeling for Virtual Reality\" \/>\n<meta property=\"og:description\" content=\"Introduction We\u2019re trying to build realistic human models for virtual reality. The goal is to build human body models from multi-view RGB images given camera parameters, with highest possible level of detail. The high quality human we reconstruct may help overcome the uncanny valley problem, and eventually enable the next generation of gaming and social &hellip; Continue reading &quot;Detailed Description&quot;\" \/>\n<meta property=\"og:url\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/2019\/12\/06\/detailed-description\/\" \/>\n<meta property=\"og:site_name\" content=\"Realistic Human Modeling for Virtual Reality\" \/>\n<meta property=\"article:published_time\" content=\"2019-12-06T01:51:58+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2019-12-11T04:00:57+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image9.png\" \/>\n\t<meta property=\"og:image:width\" content=\"325\" \/>\n\t<meta property=\"og:image:height\" content=\"499\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"chetang\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"chetang\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teamd\\\/2019\\\/12\\\/06\\\/detailed-description\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teamd\\\/2019\\\/12\\\/06\\\/detailed-description\\\/\"},\"author\":{\"name\":\"chetang\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teamd\\\/#\\\/schema\\\/person\\\/0676da1c9351c1553d4fcd623dacca64\"},\"headline\":\"Detailed Description\",\"datePublished\":\"2019-12-06T01:51:58+00:00\",\"dateModified\":\"2019-12-11T04:00:57+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teamd\\\/2019\\\/12\\\/06\\\/detailed-description\\\/\"},\"wordCount\":549,\"image\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teamd\\\/2019\\\/12\\\/06\\\/detailed-description\\\/#primaryimage\"},\"thumbnailUrl\":\"http:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teamd\\\/wp-content\\\/uploads\\\/sites\\\/19\\\/2019\\\/12\\\/image9-195x300.png\",\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teamd\\\/2019\\\/12\\\/06\\\/detailed-description\\\/\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teamd\\\/2019\\\/12\\\/06\\\/detailed-description\\\/\",\"name\":\"Detailed Description - Realistic Human Modeling for Virtual Reality\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teamd\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teamd\\\/2019\\\/12\\\/06\\\/detailed-description\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teamd\\\/2019\\\/12\\\/06\\\/detailed-description\\\/#primaryimage\"},\"thumbnailUrl\":\"http:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teamd\\\/wp-content\\\/uploads\\\/sites\\\/19\\\/2019\\\/12\\\/image9-195x300.png\",\"datePublished\":\"2019-12-06T01:51:58+00:00\",\"dateModified\":\"2019-12-11T04:00:57+00:00\",\"author\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teamd\\\/#\\\/schema\\\/person\\\/0676da1c9351c1553d4fcd623dacca64\"},\"breadcrumb\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teamd\\\/2019\\\/12\\\/06\\\/detailed-description\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teamd\\\/2019\\\/12\\\/06\\\/detailed-description\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teamd\\\/2019\\\/12\\\/06\\\/detailed-description\\\/#primaryimage\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teamd\\\/wp-content\\\/uploads\\\/sites\\\/19\\\/2019\\\/12\\\/image9.png\",\"contentUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teamd\\\/wp-content\\\/uploads\\\/sites\\\/19\\\/2019\\\/12\\\/image9.png\",\"width\":325,\"height\":499},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teamd\\\/2019\\\/12\\\/06\\\/detailed-description\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teamd\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Detailed Description\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teamd\\\/#website\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teamd\\\/\",\"name\":\"Realistic Human Modeling for Virtual Reality\",\"description\":\"MSCV Capstone Project Site\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teamd\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teamd\\\/#\\\/schema\\\/person\\\/0676da1c9351c1553d4fcd623dacca64\",\"name\":\"chetang\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/173f000a2ec72d049493e96f8eeb3d98d3004a0d430ba1f1cb31fdf802c39d74?s=96&d=mm&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/173f000a2ec72d049493e96f8eeb3d98d3004a0d430ba1f1cb31fdf802c39d74?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/173f000a2ec72d049493e96f8eeb3d98d3004a0d430ba1f1cb31fdf802c39d74?s=96&d=mm&r=g\",\"caption\":\"chetang\"},\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teamd\\\/author\\\/chetang\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Detailed Description - Realistic Human Modeling for Virtual Reality","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\/2019teamd\/2019\/12\/06\/detailed-description\/","og_locale":"en_US","og_type":"article","og_title":"Detailed Description - Realistic Human Modeling for Virtual Reality","og_description":"Introduction We\u2019re trying to build realistic human models for virtual reality. The goal is to build human body models from multi-view RGB images given camera parameters, with highest possible level of detail. The high quality human we reconstruct may help overcome the uncanny valley problem, and eventually enable the next generation of gaming and social &hellip; Continue reading \"Detailed Description\"","og_url":"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/2019\/12\/06\/detailed-description\/","og_site_name":"Realistic Human Modeling for Virtual Reality","article_published_time":"2019-12-06T01:51:58+00:00","article_modified_time":"2019-12-11T04:00:57+00:00","og_image":[{"width":325,"height":499,"url":"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image9.png","type":"image\/png"}],"author":"chetang","twitter_card":"summary_large_image","twitter_misc":{"Written by":"chetang","Est. reading time":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/2019\/12\/06\/detailed-description\/#article","isPartOf":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/2019\/12\/06\/detailed-description\/"},"author":{"name":"chetang","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/#\/schema\/person\/0676da1c9351c1553d4fcd623dacca64"},"headline":"Detailed Description","datePublished":"2019-12-06T01:51:58+00:00","dateModified":"2019-12-11T04:00:57+00:00","mainEntityOfPage":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/2019\/12\/06\/detailed-description\/"},"wordCount":549,"image":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/2019\/12\/06\/detailed-description\/#primaryimage"},"thumbnailUrl":"http:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image9-195x300.png","inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/2019\/12\/06\/detailed-description\/","url":"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/2019\/12\/06\/detailed-description\/","name":"Detailed Description - Realistic Human Modeling for Virtual Reality","isPartOf":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/#website"},"primaryImageOfPage":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/2019\/12\/06\/detailed-description\/#primaryimage"},"image":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/2019\/12\/06\/detailed-description\/#primaryimage"},"thumbnailUrl":"http:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image9-195x300.png","datePublished":"2019-12-06T01:51:58+00:00","dateModified":"2019-12-11T04:00:57+00:00","author":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/#\/schema\/person\/0676da1c9351c1553d4fcd623dacca64"},"breadcrumb":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/2019\/12\/06\/detailed-description\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/2019\/12\/06\/detailed-description\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/2019\/12\/06\/detailed-description\/#primaryimage","url":"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image9.png","contentUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-content\/uploads\/sites\/19\/2019\/12\/image9.png","width":325,"height":499},{"@type":"BreadcrumbList","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/2019\/12\/06\/detailed-description\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/"},{"@type":"ListItem","position":2,"name":"Detailed Description"}]},{"@type":"WebSite","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/#website","url":"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/","name":"Realistic Human Modeling for Virtual Reality","description":"MSCV Capstone Project Site","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/#\/schema\/person\/0676da1c9351c1553d4fcd623dacca64","name":"chetang","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/173f000a2ec72d049493e96f8eeb3d98d3004a0d430ba1f1cb31fdf802c39d74?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/173f000a2ec72d049493e96f8eeb3d98d3004a0d430ba1f1cb31fdf802c39d74?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/173f000a2ec72d049493e96f8eeb3d98d3004a0d430ba1f1cb31fdf802c39d74?s=96&d=mm&r=g","caption":"chetang"},"url":"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/author\/chetang\/"}]}},"jetpack_featured_media_url":"","_links":{"self":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-json\/wp\/v2\/posts\/34","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-json\/wp\/v2\/users\/40"}],"replies":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-json\/wp\/v2\/comments?post=34"}],"version-history":[{"count":5,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-json\/wp\/v2\/posts\/34\/revisions"}],"predecessor-version":[{"id":71,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-json\/wp\/v2\/posts\/34\/revisions\/71"}],"wp:attachment":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-json\/wp\/v2\/media?parent=34"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-json\/wp\/v2\/categories?post=34"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2019teamd\/wp-json\/wp\/v2\/tags?post=34"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}