{"id":19,"date":"2024-04-29T22:50:02","date_gmt":"2024-04-29T22:50:02","guid":{"rendered":"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/?page_id=19"},"modified":"2024-12-15T05:09:27","modified_gmt":"2024-12-15T05:09:27","slug":"experiments","status":"publish","type":"page","link":"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/experiments\/","title":{"rendered":"Experiments"},"content":{"rendered":"\n<h2 class=\"wp-block-heading\">Feature Extraction and Matching Algorithms<\/h2>\n\n\n\n<p><strong>Learning-based <\/strong>feature extraction and matching algorithms like <strong>SuperPoint<\/strong> and <strong>SuperGlue<\/strong> outperform traditional methods such as SIFT and NN.<\/p>\n\n\n\n<figure class=\"wp-block-image size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"108\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/05\/iShot_2024-05-04_23.03.18-1024x108.png\" alt=\"\" class=\"wp-image-112\" style=\"width:674px;height:auto\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/05\/iShot_2024-05-04_23.03.18-1024x108.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/05\/iShot_2024-05-04_23.03.18-300x32.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/05\/iShot_2024-05-04_23.03.18-768x81.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/05\/iShot_2024-05-04_23.03.18-1536x162.png 1536w, https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/05\/iShot_2024-05-04_23.03.18-2048x216.png 2048w\" sizes=\"auto, (max-width: 706px) 89vw, (max-width: 767px) 82vw, 740px\" \/><\/figure>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-full is-resized\"><img loading=\"lazy\" decoding=\"async\" width=\"716\" height=\"302\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/05\/iShot_2024-05-04_23.03.25.png\" alt=\"\" class=\"wp-image-113\" style=\"width:220px;height:auto\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/05\/iShot_2024-05-04_23.03.25.png 716w, https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/05\/iShot_2024-05-04_23.03.25-300x127.png 300w\" sizes=\"auto, (max-width: 716px) 100vw, 716px\" \/><\/figure>\n<\/div>\n\n\n<ul class=\"wp-block-list\">\n<li>Both qualitative and quantitative experiments demonstrate the superior performance of <strong>learning-based methods<\/strong>, such as SuperPoint and SuperGlue (<strong>SP&amp;SG<\/strong>), compared to traditional approaches like SIFT, adalma, and NN.<\/li>\n\n\n\n<li>Besides the number of keypoints and matches, SP&amp;SG is faster than SIFT&amp;NN.<\/li>\n<\/ul>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"457\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/05\/iShot_2024-05-04_23.06.55-1024x457.png\" alt=\"\" class=\"wp-image-115\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/05\/iShot_2024-05-04_23.06.55-1024x457.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/05\/iShot_2024-05-04_23.06.55-300x134.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/05\/iShot_2024-05-04_23.06.55-768x343.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/05\/iShot_2024-05-04_23.06.55-1536x685.png 1536w, https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/05\/iShot_2024-05-04_23.06.55-2048x913.png 2048w\" sizes=\"auto, (max-width: 706px) 89vw, (max-width: 767px) 82vw, 740px\" \/><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\">Intrinsics Refinement<\/h2>\n\n\n\n<p>We tested our intrinsics refinement on both COLMAP and Pixel-Perfect pipelines.<\/p>\n\n\n\n<p>The following table shows intrinsics errors <strong>before<\/strong> refinement with ground-truth extrinsics:<\/p>\n\n\n\n<div class=\"wp-block-group is-content-justification-center is-nowrap is-layout-flex wp-container-core-group-is-layout-94bc23d7 wp-block-group-is-layout-flex\"><div class=\"wp-block-image\">\n<figure class=\"aligncenter size-full is-resized\"><img loading=\"lazy\" decoding=\"async\" width=\"347\" height=\"139\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/12\/image.png\" alt=\"\" class=\"wp-image-173\" style=\"width:293px;height:auto\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/12\/image.png 347w, https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/12\/image-300x120.png 300w\" sizes=\"auto, (max-width: 347px) 100vw, 347px\" \/><\/figure>\n<\/div>\n\n\n<figure class=\"wp-block-image size-full is-resized\"><img loading=\"lazy\" decoding=\"async\" width=\"306\" height=\"197\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/12\/image-1.png\" alt=\"\" class=\"wp-image-176\" style=\"width:233px;height:auto\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/12\/image-1.png 306w, https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/12\/image-1-300x193.png 300w\" sizes=\"auto, (max-width: 306px) 100vw, 306px\" \/><\/figure>\n<\/div>\n\n\n\n<p>The following table shows intrinsics errors <strong>after<\/strong> refinement with ground-truth extrinsics:<\/p>\n\n\n\n<div class=\"wp-block-group is-content-justification-center is-nowrap is-layout-flex wp-container-core-group-is-layout-94bc23d7 wp-block-group-is-layout-flex\">\n<figure class=\"wp-block-image size-full is-resized\"><img loading=\"lazy\" decoding=\"async\" width=\"349\" height=\"139\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/12\/image-2.png\" alt=\"\" class=\"wp-image-177\" style=\"width:290px;height:auto\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/12\/image-2.png 349w, https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/12\/image-2-300x119.png 300w\" sizes=\"auto, (max-width: 349px) 100vw, 349px\" \/><\/figure>\n\n\n\n<figure class=\"wp-block-image size-full is-resized\"><img loading=\"lazy\" decoding=\"async\" width=\"306\" height=\"197\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/12\/image-3.png\" alt=\"\" class=\"wp-image-178\" style=\"width:234px;height:auto\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/12\/image-3.png 306w, https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/12\/image-3-300x193.png 300w\" sizes=\"auto, (max-width: 306px) 100vw, 306px\" \/><\/figure>\n<\/div>\n\n\n\n<p>The following table shows intrinsics errors of <strong>PixelSfM<\/strong> before and after refinement with ground-truth extrinsics:<\/p>\n\n\n\n<div class=\"wp-block-group is-content-justification-center is-nowrap is-layout-flex wp-container-core-group-is-layout-94bc23d7 wp-block-group-is-layout-flex\">\n<figure class=\"wp-block-image size-full is-resized\"><img loading=\"lazy\" decoding=\"async\" width=\"347\" height=\"137\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/12\/image-4.png\" alt=\"\" class=\"wp-image-179\" style=\"width:289px;height:auto\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/12\/image-4.png 347w, https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/12\/image-4-300x118.png 300w\" sizes=\"auto, (max-width: 347px) 100vw, 347px\" \/><\/figure>\n\n\n\n<figure class=\"wp-block-image size-full is-resized\"><img loading=\"lazy\" decoding=\"async\" width=\"306\" height=\"197\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/12\/image-5.png\" alt=\"\" class=\"wp-image-180\" style=\"width:235px;height:auto\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/12\/image-5.png 306w, https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/12\/image-5-300x193.png 300w\" sizes=\"auto, (max-width: 306px) 100vw, 306px\" \/><\/figure>\n<\/div>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Before intrinsics refinement, PixelSfM yields much lower focal error and slightly higher principal point error than COLMAP. This is because <strong>featuremetric<\/strong> <strong>refinements<\/strong> improves the precision of keypoints.<\/li>\n<\/ul>\n\n\n\n<ul class=\"wp-block-list\">\n<li>After <strong>intrinsics refinement<\/strong> with GT extrinsics, our method yields much <strong>lower focal error and principal point error <\/strong>on both COLMAP and PixelSfM pipeline.\n<ul class=\"wp-block-list\">\n<li>~30% improvement on focal error.<\/li>\n\n\n\n<li>&gt;90% improvement on principal point error.<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n\n\n\n<p>The following picture shows the L1 erro curve during optimization:<\/p>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"439\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/12\/image-6-1024x439.png\" alt=\"\" class=\"wp-image-181\" style=\"width:397px;height:auto\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/12\/image-6-1024x439.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/12\/image-6-300x129.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/12\/image-6-768x329.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/12\/image-6.png 1211w\" sizes=\"auto, (max-width: 706px) 89vw, (max-width: 767px) 82vw, 740px\" \/><\/figure>\n<\/div>\n\n\n<p>The principal point error continues decreasing during optimization, while the focal error slightly increases in the last several epoches. This is because the inherent noise contained in the keypoints. One method to mitigate it is to add featuremetric loss term in the object function, similar to Pixel-Perfect refinement, to reduce keypoint error.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Feature Extraction and Matching Algorithms Learning-based feature extraction and matching algorithms like SuperPoint and SuperGlue outperform traditional methods such as SIFT and NN. Intrinsics Refinement We tested our intrinsics refinement on both COLMAP and Pixel-Perfect pipelines. The following table shows intrinsics errors before refinement with ground-truth extrinsics: The following table shows intrinsics errors after refinement &hellip; <\/p>\n<p class=\"link-more\"><a href=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/experiments\/\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;Experiments&#8221;<\/span><\/a><\/p>\n","protected":false},"author":200,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-19","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>Experiments - Large Scale Camera Array Calibration via SfM<\/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\/2024team4\/experiments\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Experiments - Large Scale Camera Array Calibration via SfM\" \/>\n<meta property=\"og:description\" content=\"Feature Extraction and Matching Algorithms Learning-based feature extraction and matching algorithms like SuperPoint and SuperGlue outperform traditional methods such as SIFT and NN. Intrinsics Refinement We tested our intrinsics refinement on both COLMAP and Pixel-Perfect pipelines. The following table shows intrinsics errors before refinement with ground-truth extrinsics: The following table shows intrinsics errors after refinement &hellip; Continue reading &quot;Experiments&quot;\" \/>\n<meta property=\"og:url\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/experiments\/\" \/>\n<meta property=\"og:site_name\" content=\"Large Scale Camera Array Calibration via SfM\" \/>\n<meta property=\"article:modified_time\" content=\"2024-12-15T05:09:27+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/05\/iShot_2024-05-04_23.03.18-1024x108.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=\"4 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team4\\\/experiments\\\/\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team4\\\/experiments\\\/\",\"name\":\"Experiments - Large Scale Camera Array Calibration via SfM\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team4\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team4\\\/experiments\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team4\\\/experiments\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team4\\\/wp-content\\\/uploads\\\/sites\\\/102\\\/2024\\\/05\\\/iShot_2024-05-04_23.03.18-1024x108.png\",\"datePublished\":\"2024-04-29T22:50:02+00:00\",\"dateModified\":\"2024-12-15T05:09:27+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team4\\\/experiments\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team4\\\/experiments\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team4\\\/experiments\\\/#primaryimage\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team4\\\/wp-content\\\/uploads\\\/sites\\\/102\\\/2024\\\/05\\\/iShot_2024-05-04_23.03.18.png\",\"contentUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team4\\\/wp-content\\\/uploads\\\/sites\\\/102\\\/2024\\\/05\\\/iShot_2024-05-04_23.03.18.png\",\"width\":2918,\"height\":308},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team4\\\/experiments\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team4\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Experiments\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team4\\\/#website\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team4\\\/\",\"name\":\"Large Scale Camera Array Calibration via SfM\",\"description\":\"Students: Long V\u00e2n Tran Ha, Hewei Wang, Jinjiang You | Advisors: Ioannis Gkioulekas (CMU), Shubham Garg (Meta Reality Labs), Wei Pu (Meta Reality Labs)\",\"publisher\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team4\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team4\\\/?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\\\/2024team4\\\/#organization\",\"name\":\"Large Scale Camera Array Calibration via SfM\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team4\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team4\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team4\\\/wp-content\\\/uploads\\\/sites\\\/102\\\/2024\\\/12\\\/Meta-CMU-Logo.png\",\"contentUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team4\\\/wp-content\\\/uploads\\\/sites\\\/102\\\/2024\\\/12\\\/Meta-CMU-Logo.png\",\"width\":1053,\"height\":250,\"caption\":\"Large Scale Camera Array Calibration via SfM\"},\"image\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team4\\\/#\\\/schema\\\/logo\\\/image\\\/\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Experiments - Large Scale Camera Array Calibration via SfM","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\/2024team4\/experiments\/","og_locale":"en_US","og_type":"article","og_title":"Experiments - Large Scale Camera Array Calibration via SfM","og_description":"Feature Extraction and Matching Algorithms Learning-based feature extraction and matching algorithms like SuperPoint and SuperGlue outperform traditional methods such as SIFT and NN. Intrinsics Refinement We tested our intrinsics refinement on both COLMAP and Pixel-Perfect pipelines. The following table shows intrinsics errors before refinement with ground-truth extrinsics: The following table shows intrinsics errors after refinement &hellip; Continue reading \"Experiments\"","og_url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/experiments\/","og_site_name":"Large Scale Camera Array Calibration via SfM","article_modified_time":"2024-12-15T05:09:27+00:00","og_image":[{"url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/05\/iShot_2024-05-04_23.03.18-1024x108.png","type":"","width":"","height":""}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/experiments\/","url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/experiments\/","name":"Experiments - Large Scale Camera Array Calibration via SfM","isPartOf":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/#website"},"primaryImageOfPage":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/experiments\/#primaryimage"},"image":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/experiments\/#primaryimage"},"thumbnailUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/05\/iShot_2024-05-04_23.03.18-1024x108.png","datePublished":"2024-04-29T22:50:02+00:00","dateModified":"2024-12-15T05:09:27+00:00","breadcrumb":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/experiments\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/experiments\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/experiments\/#primaryimage","url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/05\/iShot_2024-05-04_23.03.18.png","contentUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/05\/iShot_2024-05-04_23.03.18.png","width":2918,"height":308},{"@type":"BreadcrumbList","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/experiments\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/"},{"@type":"ListItem","position":2,"name":"Experiments"}]},{"@type":"WebSite","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/#website","url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/","name":"Large Scale Camera Array Calibration via SfM","description":"Students: Long V\u00e2n Tran Ha, Hewei Wang, Jinjiang You | Advisors: Ioannis Gkioulekas (CMU), Shubham Garg (Meta Reality Labs), Wei Pu (Meta Reality Labs)","publisher":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/?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\/2024team4\/#organization","name":"Large Scale Camera Array Calibration via SfM","url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/#\/schema\/logo\/image\/","url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/12\/Meta-CMU-Logo.png","contentUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-content\/uploads\/sites\/102\/2024\/12\/Meta-CMU-Logo.png","width":1053,"height":250,"caption":"Large Scale Camera Array Calibration via SfM"},"image":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/#\/schema\/logo\/image\/"}}]}},"_links":{"self":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-json\/wp\/v2\/pages\/19","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-json\/wp\/v2\/users\/200"}],"replies":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-json\/wp\/v2\/comments?post=19"}],"version-history":[{"count":5,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-json\/wp\/v2\/pages\/19\/revisions"}],"predecessor-version":[{"id":182,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-json\/wp\/v2\/pages\/19\/revisions\/182"}],"wp:attachment":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team4\/wp-json\/wp\/v2\/media?parent=19"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}