{"id":68,"date":"2024-05-10T04:55:27","date_gmt":"2024-05-10T04:55:27","guid":{"rendered":"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/?page_id=68"},"modified":"2024-12-10T06:10:50","modified_gmt":"2024-12-10T06:10:50","slug":"related-work","status":"publish","type":"page","link":"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/related-work\/","title":{"rendered":"Related Works"},"content":{"rendered":"\n<div class=\"wp-block-group is-vertical is-layout-flex wp-container-core-group-is-layout-8cf370e7 wp-block-group-is-layout-flex\">\n<p>1. <strong>SplaTAM: Splat, Track &amp; Map 3D Gaussians for Dense RGB-D SLAM<\/strong><\/p>\n\n\n\n<div class=\"wp-block-group is-vertical is-layout-flex wp-container-core-group-is-layout-8cf370e7 wp-block-group-is-layout-flex\">\n<p style=\"line-height:2\">\u00b7 Proof that 3D Gaussians are useful representations for Dense SLAM<br>\u00b7 Limitations: Low Speed; Needs accurate depth; Memory and compute requirements grow fastly with scene size<\/p>\n<\/div>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"179\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/wp-content\/uploads\/sites\/113\/2024\/05\/aed0f31ca6eaa0f41bdc3f3bd337b09d-1024x179.jpg\" alt=\"\" class=\"wp-image-64\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/wp-content\/uploads\/sites\/113\/2024\/05\/aed0f31ca6eaa0f41bdc3f3bd337b09d-1024x179.jpg 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/wp-content\/uploads\/sites\/113\/2024\/05\/aed0f31ca6eaa0f41bdc3f3bd337b09d-300x52.jpg 300w, https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/wp-content\/uploads\/sites\/113\/2024\/05\/aed0f31ca6eaa0f41bdc3f3bd337b09d-768x134.jpg 768w, https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/wp-content\/uploads\/sites\/113\/2024\/05\/aed0f31ca6eaa0f41bdc3f3bd337b09d-1536x268.jpg 1536w, https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/wp-content\/uploads\/sites\/113\/2024\/05\/aed0f31ca6eaa0f41bdc3f3bd337b09d-2048x357.jpg 2048w\" sizes=\"auto, (max-width: 706px) 89vw, (max-width: 767px) 82vw, 740px\" \/><\/figure>\n<\/div>\n\n\n\n<div class=\"wp-block-group is-vertical is-layout-flex wp-container-core-group-is-layout-8cf370e7 wp-block-group-is-layout-flex\">\n<p style=\"line-height:2\">2. <strong>AnyLoc: Towards Universal Visual Place Recognition<\/strong><\/p>\n\n\n\n<p style=\"line-height:2\">\u00b7 Self-supervised Visual Features for Zero-shot Localization<br>\u00b7 Showcases the Semantic Consistency of DINOv2 features<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"346\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/wp-content\/uploads\/sites\/113\/2024\/05\/image-1.png\" alt=\"This image has an empty alt attribute; its file name is 2-1-1024x346.png\" class=\"wp-image-167\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/wp-content\/uploads\/sites\/113\/2024\/05\/image-1.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/wp-content\/uploads\/sites\/113\/2024\/05\/image-1-300x101.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/wp-content\/uploads\/sites\/113\/2024\/05\/image-1-768x260.png 768w\" sizes=\"auto, (max-width: 706px) 89vw, (max-width: 767px) 82vw, 740px\" \/><\/figure>\n<\/div>\n\n\n\n<div class=\"wp-block-group is-vertical is-layout-flex wp-container-core-group-is-layout-8cf370e7 wp-block-group-is-layout-flex\">\n<p style=\"line-height:2\">3. <strong>DUSt3R: Geometric 3D Vision Made Easy<\/strong><\/p>\n\n\n\n<p style=\"line-height:2\">\u00b7 Strong utilization of priors in geometric vision<br>\u00b7 Beats SOTA on sparse two view registration<br>\u00b7 Limitations: Out of distribution data; Can\u2019t handle long term sequences<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"239\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/wp-content\/uploads\/sites\/113\/2024\/05\/3-1-1024x239.png\" alt=\"\" class=\"wp-image-63\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/wp-content\/uploads\/sites\/113\/2024\/05\/3-1-1024x239.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/wp-content\/uploads\/sites\/113\/2024\/05\/3-1-300x70.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/wp-content\/uploads\/sites\/113\/2024\/05\/3-1-768x179.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/wp-content\/uploads\/sites\/113\/2024\/05\/3-1.png 1350w\" sizes=\"auto, (max-width: 706px) 89vw, (max-width: 767px) 82vw, 740px\" \/><\/figure>\n\n\n\n<p><br><\/p>\n\n\n\n<p style=\"line-height:2\"><strong>4. Mast3R: Masked 3D Region-based Pretraining for Robust Representations<\/strong><\/p>\n\n\n\n<p style=\"line-height:2\">\u00b7 Employs masked pretraining to learn robust 3D region-based representations<br>\u00b7 Achieves high performance in object recognition and 3D segmentation tasks<br>\u00b7 Limitations: Struggles with fine-grained details; Requires large-scale pretraining datasets<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"207\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/wp-content\/uploads\/sites\/113\/2024\/12\/3-1024x207.png\" alt=\"\" class=\"wp-image-244\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/wp-content\/uploads\/sites\/113\/2024\/12\/3-1024x207.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/wp-content\/uploads\/sites\/113\/2024\/12\/3-300x61.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/wp-content\/uploads\/sites\/113\/2024\/12\/3-768x155.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/wp-content\/uploads\/sites\/113\/2024\/12\/3-1536x310.png 1536w, https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/wp-content\/uploads\/sites\/113\/2024\/12\/3.png 1962w\" sizes=\"auto, (max-width: 706px) 89vw, (max-width: 767px) 82vw, 740px\" \/><\/figure>\n<\/div>\n\n\n\n<div class=\"wp-block-group is-vertical is-layout-flex wp-container-core-group-is-layout-8cf370e7 wp-block-group-is-layout-flex\">\n<p style=\"line-height:2\">5. <strong>DINOv2: Learning Robust Visual Features without Supervision<\/strong><\/p>\n\n\n\n<p style=\"line-height:2\">\u00b7 Introduce a discriminative self-supervised method for robust visual feature learning<br>\u00b7 Maintain high performance in various scenarios and does not require fine-tuning<br>\u00b7 Slow runtime may not fulfill the real-time requirements needed for SLAM system<\/p>\n<\/div>\n\n\n\n<div class=\"wp-block-columns is-layout-flex wp-container-core-columns-is-layout-9d6595d7 wp-block-columns-is-layout-flex\">\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\">\n<div class=\"wp-block-group is-vertical is-layout-flex wp-container-core-group-is-layout-8cf370e7 wp-block-group-is-layout-flex\">\n<p style=\"line-height:2\">6. <strong>EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Prediction<\/strong><\/p>\n\n\n\n<p style=\"line-height:2\">\u00b7 Multi-scale linear attention mechanism for high-resolution dense prediction tasks<br>\u00b7 Improve computational efficiency significantly<\/p>\n\n\n\n<div class=\"wp-block-columns is-layout-flex wp-container-core-columns-is-layout-9d6595d7 wp-block-columns-is-layout-flex\"><\/div>\n<\/div>\n<\/div>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>1. SplaTAM: Splat, Track &amp; Map 3D Gaussians for Dense RGB-D SLAM \u00b7 Proof that 3D Gaussians are useful representations for Dense SLAM\u00b7 Limitations: Low Speed; Needs accurate depth; Memory and compute requirements grow fastly with scene size 2. AnyLoc: Towards Universal Visual Place Recognition \u00b7 Self-supervised Visual Features for Zero-shot Localization\u00b7 Showcases the Semantic &hellip; <\/p>\n<p class=\"link-more\"><a href=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/related-work\/\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;Related Works&#8221;<\/span><\/a><\/p>\n","protected":false},"author":221,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-68","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 - Towards Universal State Estimation and Reconstruction in the Wild<\/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\/2024team15\/related-work\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Related Works - Towards Universal State Estimation and Reconstruction in the Wild\" \/>\n<meta property=\"og:description\" content=\"1. SplaTAM: Splat, Track &amp; Map 3D Gaussians for Dense RGB-D SLAM \u00b7 Proof that 3D Gaussians are useful representations for Dense SLAM\u00b7 Limitations: Low Speed; Needs accurate depth; Memory and compute requirements grow fastly with scene size 2. AnyLoc: Towards Universal Visual Place Recognition \u00b7 Self-supervised Visual Features for Zero-shot Localization\u00b7 Showcases the Semantic &hellip; Continue reading &quot;Related Works&quot;\" \/>\n<meta property=\"og:url\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/related-work\/\" \/>\n<meta property=\"og:site_name\" content=\"Towards Universal State Estimation and Reconstruction in the Wild\" \/>\n<meta property=\"article:modified_time\" content=\"2024-12-10T06:10:50+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/wp-content\/uploads\/sites\/113\/2024\/05\/aed0f31ca6eaa0f41bdc3f3bd337b09d-1024x179.jpg\" \/>\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\\\/2024team15\\\/related-work\\\/\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team15\\\/related-work\\\/\",\"name\":\"Related Works - Towards Universal State Estimation and Reconstruction in the Wild\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team15\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team15\\\/related-work\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team15\\\/related-work\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team15\\\/wp-content\\\/uploads\\\/sites\\\/113\\\/2024\\\/05\\\/aed0f31ca6eaa0f41bdc3f3bd337b09d-1024x179.jpg\",\"datePublished\":\"2024-05-10T04:55:27+00:00\",\"dateModified\":\"2024-12-10T06:10:50+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team15\\\/related-work\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team15\\\/related-work\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team15\\\/related-work\\\/#primaryimage\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team15\\\/wp-content\\\/uploads\\\/sites\\\/113\\\/2024\\\/05\\\/aed0f31ca6eaa0f41bdc3f3bd337b09d-scaled.jpg\",\"contentUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team15\\\/wp-content\\\/uploads\\\/sites\\\/113\\\/2024\\\/05\\\/aed0f31ca6eaa0f41bdc3f3bd337b09d-scaled.jpg\",\"width\":2560,\"height\":447},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team15\\\/related-work\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team15\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Related Works\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team15\\\/#website\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team15\\\/\",\"name\":\"Towards Universal State Estimation and Reconstruction in the Wild\",\"description\":\"Student:Bhuvan Jhamb, Chenwei Lyu | Advisors: Nikhil Keetha, Yuchen Zhang, Dr. Sebastian Scherer\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team15\\\/?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 - Towards Universal State Estimation and Reconstruction in the Wild","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\/2024team15\/related-work\/","og_locale":"en_US","og_type":"article","og_title":"Related Works - Towards Universal State Estimation and Reconstruction in the Wild","og_description":"1. SplaTAM: Splat, Track &amp; Map 3D Gaussians for Dense RGB-D SLAM \u00b7 Proof that 3D Gaussians are useful representations for Dense SLAM\u00b7 Limitations: Low Speed; Needs accurate depth; Memory and compute requirements grow fastly with scene size 2. AnyLoc: Towards Universal Visual Place Recognition \u00b7 Self-supervised Visual Features for Zero-shot Localization\u00b7 Showcases the Semantic &hellip; Continue reading \"Related Works\"","og_url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/related-work\/","og_site_name":"Towards Universal State Estimation and Reconstruction in the Wild","article_modified_time":"2024-12-10T06:10:50+00:00","og_image":[{"url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/wp-content\/uploads\/sites\/113\/2024\/05\/aed0f31ca6eaa0f41bdc3f3bd337b09d-1024x179.jpg","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\/2024team15\/related-work\/","url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/related-work\/","name":"Related Works - Towards Universal State Estimation and Reconstruction in the Wild","isPartOf":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/#website"},"primaryImageOfPage":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/related-work\/#primaryimage"},"image":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/related-work\/#primaryimage"},"thumbnailUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/wp-content\/uploads\/sites\/113\/2024\/05\/aed0f31ca6eaa0f41bdc3f3bd337b09d-1024x179.jpg","datePublished":"2024-05-10T04:55:27+00:00","dateModified":"2024-12-10T06:10:50+00:00","breadcrumb":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/related-work\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/related-work\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/related-work\/#primaryimage","url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/wp-content\/uploads\/sites\/113\/2024\/05\/aed0f31ca6eaa0f41bdc3f3bd337b09d-scaled.jpg","contentUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/wp-content\/uploads\/sites\/113\/2024\/05\/aed0f31ca6eaa0f41bdc3f3bd337b09d-scaled.jpg","width":2560,"height":447},{"@type":"BreadcrumbList","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/related-work\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/"},{"@type":"ListItem","position":2,"name":"Related Works"}]},{"@type":"WebSite","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/#website","url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/","name":"Towards Universal State Estimation and Reconstruction in the Wild","description":"Student:Bhuvan Jhamb, Chenwei Lyu | Advisors: Nikhil Keetha, Yuchen Zhang, Dr. Sebastian Scherer","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/?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\/2024team15\/wp-json\/wp\/v2\/pages\/68","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/wp-json\/wp\/v2\/users\/221"}],"replies":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/wp-json\/wp\/v2\/comments?post=68"}],"version-history":[{"count":14,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/wp-json\/wp\/v2\/pages\/68\/revisions"}],"predecessor-version":[{"id":301,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/wp-json\/wp\/v2\/pages\/68\/revisions\/301"}],"wp:attachment":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team15\/wp-json\/wp\/v2\/media?parent=68"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}