{"id":95,"date":"2024-05-12T19:21:37","date_gmt":"2024-05-12T19:21:37","guid":{"rendered":"https:\/\/mscvprojects.ri.cmu.edu\/2024team18\/?page_id=95"},"modified":"2024-12-09T02:39:58","modified_gmt":"2024-12-09T02:39:58","slug":"experiments","status":"publish","type":"page","link":"https:\/\/mscvprojects.ri.cmu.edu\/2024team18\/experiments\/","title":{"rendered":"Experiments"},"content":{"rendered":"\n

Experimental Setup<\/strong><\/h3>\n\n\n\n

Datasets.<\/strong> We primarily evaluate our method on a real-world multi-view
object-centric dataset NAVI. This dataset includes high-quality foreground
masks, precise camera poses, and 3D meshes. For each of the 35 objects in
NAVI, we randomly select 5 multi-view sequences for pose estimation and reconstruction.
Baselines.<\/strong> To evaluate camera pose accuracy, we select three sparse-view pose
estimation baseline methods: RelPose++, Ray Diffusion, and DUSt3R. The first two are trained exclusively on CO3D, while DUSt3R is trained on a mixture of eight datasets, representing different levels of precision in initial camera poses. Our method initializes and improves the pose estimates from these
baselines, and we also compare with SPARF, a sparse-view pose-NeRF co-optimization method. To evaluate novel view synthesis, we mainly compare our method with unposed sparse-view reconstruction approaches, LEAP and UpFusion. We conduct experiments with varying numbers of input images (N = 6, 8, 10, 16).<\/p>\n\n\n\n

Evaluation<\/strong><\/p>\n\n\n\n

Qualitative Comparison of Camera Pose Accuracy<\/h4>\n\n\n\n

We compare DiffusionSfM on pose accuracy with SPARF. Our method can deal with initial camera poses with large errors.<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

Qualitative Comparison of Novel View Synthesis<\/h4>\n\n\n\n

We compare DiffusionSfM on novel view synthesis with LEAP. Our method can preserve high-quality details from input images. Please refer to our paper for more comparisons with SPARF and UpFusion.<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

Ablation Study<\/h4>\n\n\n\n
\"\"<\/figure>\n","protected":false},"excerpt":{"rendered":"

Experimental Setup Datasets. We primarily evaluate our method on a real-world multi-viewobject-centric dataset NAVI. This dataset includes high-quality foregroundmasks, precise camera poses, and 3D meshes. For each of the 35 objects inNAVI, we randomly select 5 multi-view sequences for pose estimation and reconstruction.Baselines. To evaluate camera pose accuracy, we select three sparse-view poseestimation baseline methods: […]<\/p>\n","protected":false},"author":224,"featured_media":0,"parent":0,"menu_order":2,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-95","page","type-page","status-publish","hentry"],"yoast_head":"\nExperiments - Sparse-view Pose Estimation via Analysis-by-synthesis<\/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\/2024team18\/experiments\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Experiments - Sparse-view Pose Estimation via Analysis-by-synthesis\" \/>\n<meta property=\"og:description\" content=\"Experimental Setup Datasets. We primarily evaluate our method on a real-world multi-viewobject-centric dataset NAVI. This dataset includes high-quality foregroundmasks, precise camera poses, and 3D meshes. For each of the 35 objects inNAVI, we randomly select 5 multi-view sequences for pose estimation and reconstruction.Baselines. To evaluate camera pose accuracy, we select three sparse-view poseestimation baseline methods: […]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team18\/experiments\/\" \/>\n<meta property=\"og:site_name\" content=\"Sparse-view Pose Estimation via Analysis-by-synthesis\" \/>\n<meta property=\"article:modified_time\" content=\"2024-12-09T02:39:58+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team18\/wp-content\/uploads\/sites\/116\/2024\/12\/vis_compare_sparf_cr-1024x542.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\\\/2024team18\\\/experiments\\\/\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team18\\\/experiments\\\/\",\"name\":\"Experiments - Sparse-view Pose Estimation via Analysis-by-synthesis\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team18\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team18\\\/experiments\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team18\\\/experiments\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team18\\\/wp-content\\\/uploads\\\/sites\\\/116\\\/2024\\\/12\\\/vis_compare_sparf_cr-1024x542.jpg\",\"datePublished\":\"2024-05-12T19:21:37+00:00\",\"dateModified\":\"2024-12-09T02:39:58+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team18\\\/experiments\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team18\\\/experiments\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team18\\\/experiments\\\/#primaryimage\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team18\\\/wp-content\\\/uploads\\\/sites\\\/116\\\/2024\\\/12\\\/vis_compare_sparf_cr-scaled.jpg\",\"contentUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team18\\\/wp-content\\\/uploads\\\/sites\\\/116\\\/2024\\\/12\\\/vis_compare_sparf_cr-scaled.jpg\",\"width\":2560,\"height\":1356},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team18\\\/experiments\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team18\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Experiments\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team18\\\/#website\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team18\\\/\",\"name\":\"Sparse-view Pose Estimation via Analysis-by-synthesis\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team18\\\/?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":"Experiments - Sparse-view Pose Estimation via Analysis-by-synthesis","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\/2024team18\/experiments\/","og_locale":"en_US","og_type":"article","og_title":"Experiments - Sparse-view Pose Estimation via Analysis-by-synthesis","og_description":"Experimental Setup Datasets. We primarily evaluate our method on a real-world multi-viewobject-centric dataset NAVI. This dataset includes high-quality foregroundmasks, precise camera poses, and 3D meshes. For each of the 35 objects inNAVI, we randomly select 5 multi-view sequences for pose estimation and reconstruction.Baselines. To evaluate camera pose accuracy, we select three sparse-view poseestimation baseline methods: […]","og_url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team18\/experiments\/","og_site_name":"Sparse-view Pose Estimation via Analysis-by-synthesis","article_modified_time":"2024-12-09T02:39:58+00:00","og_image":[{"url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team18\/wp-content\/uploads\/sites\/116\/2024\/12\/vis_compare_sparf_cr-1024x542.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\/2024team18\/experiments\/","url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team18\/experiments\/","name":"Experiments - Sparse-view Pose Estimation via Analysis-by-synthesis","isPartOf":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team18\/#website"},"primaryImageOfPage":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team18\/experiments\/#primaryimage"},"image":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team18\/experiments\/#primaryimage"},"thumbnailUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2024team18\/wp-content\/uploads\/sites\/116\/2024\/12\/vis_compare_sparf_cr-1024x542.jpg","datePublished":"2024-05-12T19:21:37+00:00","dateModified":"2024-12-09T02:39:58+00:00","breadcrumb":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team18\/experiments\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/mscvprojects.ri.cmu.edu\/2024team18\/experiments\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team18\/experiments\/#primaryimage","url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team18\/wp-content\/uploads\/sites\/116\/2024\/12\/vis_compare_sparf_cr-scaled.jpg","contentUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2024team18\/wp-content\/uploads\/sites\/116\/2024\/12\/vis_compare_sparf_cr-scaled.jpg","width":2560,"height":1356},{"@type":"BreadcrumbList","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team18\/experiments\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/mscvprojects.ri.cmu.edu\/2024team18\/"},{"@type":"ListItem","position":2,"name":"Experiments"}]},{"@type":"WebSite","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team18\/#website","url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team18\/","name":"Sparse-view Pose Estimation via Analysis-by-synthesis","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/mscvprojects.ri.cmu.edu\/2024team18\/?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\/2024team18\/wp-json\/wp\/v2\/pages\/95","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team18\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team18\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team18\/wp-json\/wp\/v2\/users\/224"}],"replies":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team18\/wp-json\/wp\/v2\/comments?post=95"}],"version-history":[{"count":12,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team18\/wp-json\/wp\/v2\/pages\/95\/revisions"}],"predecessor-version":[{"id":159,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team18\/wp-json\/wp\/v2\/pages\/95\/revisions\/159"}],"wp:attachment":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team18\/wp-json\/wp\/v2\/media?parent=95"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}