{"id":14,"date":"2025-05-08T03:12:45","date_gmt":"2025-05-08T03:12:45","guid":{"rendered":"https:\/\/mscvprojects.ri.cmu.edu\/2025team4\/?page_id=14"},"modified":"2025-12-12T23:56:05","modified_gmt":"2025-12-12T23:56:05","slug":"openvslam","status":"publish","type":"page","link":"https:\/\/mscvprojects.ri.cmu.edu\/2025team4\/openvslam\/","title":{"rendered":"Pipeline Overview"},"content":{"rendered":"\n<p>Our project develops an adaptive data-collection and reconstruction pipeline that uses a single 360\u00b0 video stream to produce high-fidelity 3D Gaussian Splatting (3DGS) models. By leveraging the full omnidirectional coverage of 360\u00b0 cameras, we enable easier capture, more stable Structure-from-Motion (SfM), and improved robustness in challenging environments with distractors, lighting variations, or scene changes.<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"668\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2025team4\/wp-content\/uploads\/sites\/120\/2025\/12\/Fujitsu_CurrentPipeline-II-1-1024x668.jpeg\" alt=\"\" class=\"wp-image-187\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2025team4\/wp-content\/uploads\/sites\/120\/2025\/12\/Fujitsu_CurrentPipeline-II-1-1024x668.jpeg 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2025team4\/wp-content\/uploads\/sites\/120\/2025\/12\/Fujitsu_CurrentPipeline-II-1-300x196.jpeg 300w, https:\/\/mscvprojects.ri.cmu.edu\/2025team4\/wp-content\/uploads\/sites\/120\/2025\/12\/Fujitsu_CurrentPipeline-II-1-768x501.jpeg 768w, https:\/\/mscvprojects.ri.cmu.edu\/2025team4\/wp-content\/uploads\/sites\/120\/2025\/12\/Fujitsu_CurrentPipeline-II-1-1536x1002.jpeg 1536w, https:\/\/mscvprojects.ri.cmu.edu\/2025team4\/wp-content\/uploads\/sites\/120\/2025\/12\/Fujitsu_CurrentPipeline-II-1-2048x1336.jpeg 2048w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><\/figure>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\" \/>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>SuperPoint &amp; SuperGlue<\/strong><\/h2>\n\n\n\n<p>The first two steps of bundle adjustment are feature detection and matching. We enhance accuracy by using SuperPoint for feature detection and description, and LightGlue\u2014an attention-based improvement of SuperGlue\u2014for matching. Equirectangular images are decomposed into six perspective views, and the matched features are then fed into rig-based bundle adjustment.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Rig-Based SfM<\/strong><\/h2>\n\n\n\n<p>An equirectangular image can be decomposed into a cubemap, producing six perspective images compatible with existing bundle adjustment and SfM pipelines. While this increases the number of images by sixfold, the six views are physically constrained to one another, allowing them to be treated as a single rig. With known camera-to-rig extrinsics, the optimization only needs to track the rig\u2019s position and orientation over time. Bundle adjustment minimizes the squared re-projection error of 3D points onto each camera.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Monocular Depth Estimation with Scale Alignment<\/strong><\/h2>\n\n\n\n<p>This module predicts dense depth maps from single images and aligns them to a global scale using known reference points or camera poses. It enables detailed scene understanding even with limited multi-view data.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>GS for Unconstrained Photo Collections<\/strong><\/h2>\n\n\n\n<p>The final module applies Gaussian Splatting (GS) to reconstruct high-fidelity 3D geometry from unstructured and unconstrained photo collections. It fuses information from multiple views while handling noise, lighting variation, and sparse viewpoints to produce a coherent 3D model.<\/p>\n\n\n\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Our project develops an adaptive data-collection and reconstruction pipeline that uses a single 360\u00b0 video stream to produce high-fidelity 3D Gaussian Splatting (3DGS) models. By leveraging the full omnidirectional coverage of 360\u00b0 cameras, we enable easier capture, more stable Structure-from-Motion (SfM), and improved robustness in challenging environments with distractors, lighting variations, or scene changes. SuperPoint &hellip; <\/p>\n<p class=\"link-more\"><a href=\"https:\/\/mscvprojects.ri.cmu.edu\/2025team4\/openvslam\/\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;Pipeline Overview&#8221;<\/span><\/a><\/p>\n","protected":false},"author":233,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-14","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>Pipeline Overview - Adaptive Data Collection For High Fidelity Gaussian Splatting<\/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\/2025team4\/openvslam\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Pipeline Overview - Adaptive Data Collection For High Fidelity Gaussian Splatting\" \/>\n<meta property=\"og:description\" content=\"Our project develops an adaptive data-collection and reconstruction pipeline that uses a single 360\u00b0 video stream to produce high-fidelity 3D Gaussian Splatting (3DGS) models. By leveraging the full omnidirectional coverage of 360\u00b0 cameras, we enable easier capture, more stable Structure-from-Motion (SfM), and improved robustness in challenging environments with distractors, lighting variations, or scene changes. SuperPoint &hellip; Continue reading &quot;Pipeline Overview&quot;\" \/>\n<meta property=\"og:url\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2025team4\/openvslam\/\" \/>\n<meta property=\"og:site_name\" content=\"Adaptive Data Collection For High Fidelity Gaussian Splatting\" \/>\n<meta property=\"article:modified_time\" content=\"2025-12-12T23:56:05+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2025team4\/wp-content\/uploads\/sites\/120\/2025\/12\/Fujitsu_CurrentPipeline-II-1-scaled.jpeg\" \/>\n\t<meta property=\"og:image:width\" content=\"2560\" \/>\n\t<meta property=\"og:image:height\" content=\"1670\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\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\\\/2025team4\\\/openvslam\\\/\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team4\\\/openvslam\\\/\",\"name\":\"Pipeline Overview - Adaptive Data Collection For High Fidelity Gaussian Splatting\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team4\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team4\\\/openvslam\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team4\\\/openvslam\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team4\\\/wp-content\\\/uploads\\\/sites\\\/120\\\/2025\\\/12\\\/Fujitsu_CurrentPipeline-II-1-1024x668.jpeg\",\"datePublished\":\"2025-05-08T03:12:45+00:00\",\"dateModified\":\"2025-12-12T23:56:05+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team4\\\/openvslam\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team4\\\/openvslam\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team4\\\/openvslam\\\/#primaryimage\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team4\\\/wp-content\\\/uploads\\\/sites\\\/120\\\/2025\\\/12\\\/Fujitsu_CurrentPipeline-II-1-scaled.jpeg\",\"contentUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team4\\\/wp-content\\\/uploads\\\/sites\\\/120\\\/2025\\\/12\\\/Fujitsu_CurrentPipeline-II-1-scaled.jpeg\",\"width\":2560,\"height\":1670},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team4\\\/openvslam\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team4\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Pipeline Overview\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team4\\\/#website\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team4\\\/\",\"name\":\"Adaptive Data Collection For High Fidelity Gaussian Splatting\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team4\\\/?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":"Pipeline Overview - Adaptive Data Collection For High Fidelity Gaussian Splatting","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\/2025team4\/openvslam\/","og_locale":"en_US","og_type":"article","og_title":"Pipeline Overview - Adaptive Data Collection For High Fidelity Gaussian Splatting","og_description":"Our project develops an adaptive data-collection and reconstruction pipeline that uses a single 360\u00b0 video stream to produce high-fidelity 3D Gaussian Splatting (3DGS) models. By leveraging the full omnidirectional coverage of 360\u00b0 cameras, we enable easier capture, more stable Structure-from-Motion (SfM), and improved robustness in challenging environments with distractors, lighting variations, or scene changes. SuperPoint &hellip; Continue reading \"Pipeline Overview\"","og_url":"https:\/\/mscvprojects.ri.cmu.edu\/2025team4\/openvslam\/","og_site_name":"Adaptive Data Collection For High Fidelity Gaussian Splatting","article_modified_time":"2025-12-12T23:56:05+00:00","og_image":[{"width":2560,"height":1670,"url":"https:\/\/mscvprojects.ri.cmu.edu\/2025team4\/wp-content\/uploads\/sites\/120\/2025\/12\/Fujitsu_CurrentPipeline-II-1-scaled.jpeg","type":"image\/jpeg"}],"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\/2025team4\/openvslam\/","url":"https:\/\/mscvprojects.ri.cmu.edu\/2025team4\/openvslam\/","name":"Pipeline Overview - Adaptive Data Collection For High Fidelity Gaussian Splatting","isPartOf":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team4\/#website"},"primaryImageOfPage":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team4\/openvslam\/#primaryimage"},"image":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team4\/openvslam\/#primaryimage"},"thumbnailUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2025team4\/wp-content\/uploads\/sites\/120\/2025\/12\/Fujitsu_CurrentPipeline-II-1-1024x668.jpeg","datePublished":"2025-05-08T03:12:45+00:00","dateModified":"2025-12-12T23:56:05+00:00","breadcrumb":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team4\/openvslam\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/mscvprojects.ri.cmu.edu\/2025team4\/openvslam\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team4\/openvslam\/#primaryimage","url":"https:\/\/mscvprojects.ri.cmu.edu\/2025team4\/wp-content\/uploads\/sites\/120\/2025\/12\/Fujitsu_CurrentPipeline-II-1-scaled.jpeg","contentUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2025team4\/wp-content\/uploads\/sites\/120\/2025\/12\/Fujitsu_CurrentPipeline-II-1-scaled.jpeg","width":2560,"height":1670},{"@type":"BreadcrumbList","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team4\/openvslam\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/mscvprojects.ri.cmu.edu\/2025team4\/"},{"@type":"ListItem","position":2,"name":"Pipeline Overview"}]},{"@type":"WebSite","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team4\/#website","url":"https:\/\/mscvprojects.ri.cmu.edu\/2025team4\/","name":"Adaptive Data Collection For High Fidelity Gaussian Splatting","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/mscvprojects.ri.cmu.edu\/2025team4\/?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\/2025team4\/wp-json\/wp\/v2\/pages\/14","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team4\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team4\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team4\/wp-json\/wp\/v2\/users\/233"}],"replies":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team4\/wp-json\/wp\/v2\/comments?post=14"}],"version-history":[{"count":4,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team4\/wp-json\/wp\/v2\/pages\/14\/revisions"}],"predecessor-version":[{"id":190,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team4\/wp-json\/wp\/v2\/pages\/14\/revisions\/190"}],"wp:attachment":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team4\/wp-json\/wp\/v2\/media?parent=14"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}