{"id":91,"date":"2022-12-21T01:05:48","date_gmt":"2022-12-21T01:05:48","guid":{"rendered":"https:\/\/mscvprojects.ri.cmu.edu\/2023team5\/?page_id=91"},"modified":"2022-12-21T02:39:11","modified_gmt":"2022-12-21T02:39:11","slug":"experimental-setup","status":"publish","type":"page","link":"https:\/\/mscvprojects.ri.cmu.edu\/2023team5\/experimental-setup\/","title":{"rendered":"EXPERIMENTAL SETUP"},"content":{"rendered":"\n

Data-Driven SfM pipeline<\/strong><\/p>\n\n\n\n

As mentioned in the introduction, we want to solve SfM using data-driving priors. We created a driver which utilizes different learning feature extractions and learning feature matching methods to see how the data-driven priors can help with sets of few Images. <\/p>\n\n\n\n

Datasets<\/strong><\/p>\n\n\n\n

Custom Daily Common Objects<\/span><\/strong><\/p>\n\n\n\n

We created our own dataset which consists of 360-degree images of 11 objects that are found in our day-to-day activities. Each category consists of multi-view images with 10-23 viewpoints. To establish a baseline we first tested the data-driven SfM pipeline on our own datasets. Link to the dataset<\/a>.<\/p>\n\n\n\n

\"\"
Example of our own dataset<\/figcaption><\/figure>\n\n\n\n

Results <\/strong><\/p>\n\n\n\n

\"\"
This is the visualization of the camera pose (pyramids) and 3D point clouds (red-points) estimated using hloc <\/figcaption><\/figure>\n\n\n\n

Co3D v2<\/strong><\/a><\/p>\n\n\n\n

We tested the data-driven SfM pipeline on the Co3D v2 dataset. The Co3D V2 dataset is designed for learning category-specific 3D reconstruction and new-view synthesis using multi-view images of common object categories.<\/p>\n\n\n\n

The dataset contains a total of 1.5 million frames from nearly 19,000 videos capturing objects from 50 MS-COCO categories, and, as such, it is significantly larger than alternatives both in terms of the number of categories and objects.<\/p>\n\n\n\n

\"\"
Co3D v2 dataset categories<\/figcaption><\/figure>\n\n\n\n

We chose one of the hydrant categories from the Co3D v2 dataset and ran the data-driven SfM pipeline on it. We randomly sampled different numbers of images from the dataset with the provided ground-truth cameras and compared the average rotation error and the number of estimated poses with different inputs. <\/p>\n\n\n\n

Results<\/strong><\/p>\n\n\n\n

Number of images<\/td>Average rotation error<\/td>Number of poses estimated<\/td><\/tr>
50<\/td>0.056<\/td>50<\/td><\/tr>
20<\/td>0.665<\/td>14<\/td><\/tr>
10<\/td>Not Converged<\/td>0<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n
\"\"
Visualize results
the blue cameras are the ground truth cameras provided in the dataset, and the red ones are predictions from the SfM pipeline.<\/figcaption><\/figure>\n\n\n\n

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

Data-Driven SfM pipeline As mentioned in the introduction, we want to solve SfM using data-driving priors. We created a driver which utilizes different learning feature extractions and learning feature matching methods to see how the data-driven priors can help with sets of few Images. Datasets Custom Daily Common Objects We created our own dataset which … <\/p>\n

Continue reading “EXPERIMENTAL SETUP”<\/span><\/a><\/p>\n","protected":false},"author":153,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-91","page","type-page","status-publish","hentry"],"yoast_head":"\nEXPERIMENTAL SETUP - 2023 Team 5<\/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\/2023team5\/experimental-setup\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"EXPERIMENTAL SETUP - 2023 Team 5\" \/>\n<meta property=\"og:description\" content=\"Data-Driven SfM pipeline As mentioned in the introduction, we want to solve SfM using data-driving priors. We created a driver which utilizes different learning feature extractions and learning feature matching methods to see how the data-driven priors can help with sets of few Images. Datasets Custom Daily Common Objects We created our own dataset which … Continue reading "EXPERIMENTAL SETUP"\" \/>\n<meta property=\"og:url\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2023team5\/experimental-setup\/\" \/>\n<meta property=\"og:site_name\" content=\"2023 Team 5\" \/>\n<meta property=\"article:modified_time\" content=\"2022-12-21T02:39:11+00:00\" \/>\n<meta property=\"og:image\" content=\"http:\/\/mscvprojects.ri.cmu.edu\/2023team5\/wp-content\/uploads\/sites\/76\/2022\/12\/Screen-Shot-2022-12-21-at-9.49.02-AM.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\\\/2023team5\\\/experimental-setup\\\/\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2023team5\\\/experimental-setup\\\/\",\"name\":\"EXPERIMENTAL SETUP - 2023 Team 5\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2023team5\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2023team5\\\/experimental-setup\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2023team5\\\/experimental-setup\\\/#primaryimage\"},\"thumbnailUrl\":\"http:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2023team5\\\/wp-content\\\/uploads\\\/sites\\\/76\\\/2022\\\/12\\\/Screen-Shot-2022-12-21-at-9.49.02-AM.png\",\"datePublished\":\"2022-12-21T01:05:48+00:00\",\"dateModified\":\"2022-12-21T02:39:11+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2023team5\\\/experimental-setup\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2023team5\\\/experimental-setup\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2023team5\\\/experimental-setup\\\/#primaryimage\",\"url\":\"http:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2023team5\\\/wp-content\\\/uploads\\\/sites\\\/76\\\/2022\\\/12\\\/Screen-Shot-2022-12-21-at-9.49.02-AM.png\",\"contentUrl\":\"http:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2023team5\\\/wp-content\\\/uploads\\\/sites\\\/76\\\/2022\\\/12\\\/Screen-Shot-2022-12-21-at-9.49.02-AM.png\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2023team5\\\/experimental-setup\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2023team5\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"EXPERIMENTAL SETUP\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2023team5\\\/#website\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2023team5\\\/\",\"name\":\"2023 Team 5\",\"description\":\"LEARN FOR STRUCTURE FROM MOTION\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2023team5\\\/?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":"EXPERIMENTAL SETUP - 2023 Team 5","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\/2023team5\/experimental-setup\/","og_locale":"en_US","og_type":"article","og_title":"EXPERIMENTAL SETUP - 2023 Team 5","og_description":"Data-Driven SfM pipeline As mentioned in the introduction, we want to solve SfM using data-driving priors. We created a driver which utilizes different learning feature extractions and learning feature matching methods to see how the data-driven priors can help with sets of few Images. Datasets Custom Daily Common Objects We created our own dataset which … Continue reading \"EXPERIMENTAL SETUP\"","og_url":"https:\/\/mscvprojects.ri.cmu.edu\/2023team5\/experimental-setup\/","og_site_name":"2023 Team 5","article_modified_time":"2022-12-21T02:39:11+00:00","og_image":[{"url":"http:\/\/mscvprojects.ri.cmu.edu\/2023team5\/wp-content\/uploads\/sites\/76\/2022\/12\/Screen-Shot-2022-12-21-at-9.49.02-AM.png","type":"","width":"","height":""}],"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\/2023team5\/experimental-setup\/","url":"https:\/\/mscvprojects.ri.cmu.edu\/2023team5\/experimental-setup\/","name":"EXPERIMENTAL SETUP - 2023 Team 5","isPartOf":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2023team5\/#website"},"primaryImageOfPage":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2023team5\/experimental-setup\/#primaryimage"},"image":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2023team5\/experimental-setup\/#primaryimage"},"thumbnailUrl":"http:\/\/mscvprojects.ri.cmu.edu\/2023team5\/wp-content\/uploads\/sites\/76\/2022\/12\/Screen-Shot-2022-12-21-at-9.49.02-AM.png","datePublished":"2022-12-21T01:05:48+00:00","dateModified":"2022-12-21T02:39:11+00:00","breadcrumb":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2023team5\/experimental-setup\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/mscvprojects.ri.cmu.edu\/2023team5\/experimental-setup\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2023team5\/experimental-setup\/#primaryimage","url":"http:\/\/mscvprojects.ri.cmu.edu\/2023team5\/wp-content\/uploads\/sites\/76\/2022\/12\/Screen-Shot-2022-12-21-at-9.49.02-AM.png","contentUrl":"http:\/\/mscvprojects.ri.cmu.edu\/2023team5\/wp-content\/uploads\/sites\/76\/2022\/12\/Screen-Shot-2022-12-21-at-9.49.02-AM.png"},{"@type":"BreadcrumbList","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2023team5\/experimental-setup\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/mscvprojects.ri.cmu.edu\/2023team5\/"},{"@type":"ListItem","position":2,"name":"EXPERIMENTAL SETUP"}]},{"@type":"WebSite","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2023team5\/#website","url":"https:\/\/mscvprojects.ri.cmu.edu\/2023team5\/","name":"2023 Team 5","description":"LEARN FOR STRUCTURE FROM MOTION","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/mscvprojects.ri.cmu.edu\/2023team5\/?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\/2023team5\/wp-json\/wp\/v2\/pages\/91","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2023team5\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2023team5\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2023team5\/wp-json\/wp\/v2\/users\/153"}],"replies":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2023team5\/wp-json\/wp\/v2\/comments?post=91"}],"version-history":[{"count":9,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2023team5\/wp-json\/wp\/v2\/pages\/91\/revisions"}],"predecessor-version":[{"id":121,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2023team5\/wp-json\/wp\/v2\/pages\/91\/revisions\/121"}],"wp:attachment":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2023team5\/wp-json\/wp\/v2\/media?parent=91"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}