{"id":41866,"date":"2025-12-17T15:38:00","date_gmt":"2025-12-17T08:38:00","guid":{"rendered":"https:\/\/thaipropertynews.com\/feeds\/?p=41866"},"modified":"2025-12-17T15:38:00","modified_gmt":"2025-12-17T08:38:00","slug":"the-largest-scale-globally-realsee-open-sources-indoor-3d-dataset-realsee3d","status":"publish","type":"post","link":"https:\/\/thaipropertynews.com\/feeds\/?p=41866","title":{"rendered":"The Largest-Scale Globally: Realsee Open-Sources Indoor 3D Dataset Realsee3D"},"content":{"rendered":"<p><span class=\"legendSpanClass\"><span class=\"xn-location\">BEIJING<\/span><\/span>, <span class=\"legendSpanClass\"><span class=\"xn-chron\">Dec. 17, 2025<\/span><\/span> \/PRNewswire\/ &#8212; Realsee announced the official opening of Realsee3D, a dataset of 10,000 indoor 3D scenes, for academic research and non-commercial purposes.<\/p>\n<div class=\"PRN_ImbeddedAssetReference\">\n<p><a href=\"https:\/\/mma.prnasia.com\/media2\/2847511\/Realsee3D.html\" target=\"_blank\" rel=\"nofollow\"><img decoding=\"async\" src=\"https:\/\/mma.prnasia.com\/media2\/2847511\/Realsee3D.jpg?p=medium600\" title=\"Realsee3D\" alt=\"Realsee3D\" \/><\/a><br \/><span>Realsee3D<\/span><\/p>\n<\/div>\n<p>This is potentially the world&#8217;s largest spatial 3D dataset to date, aiming to provide a high-quality data foundation for researchers and developers in the field of spatial intelligence, and accelerate the technological iteration and application implementation of the entire industry.\u00a0<\/p>\n<p>Prior to this, Realsee released Argus 1.0, a large model for spatial depth estimation. As the first large model for spatial depth estimation that supports panoramic image input, Argus 1.0 was trained based on the 10-million-level 3D spatial database accumulated by Realsee. The Realsee3D 3D dataset opened this time is precisely a selection of high-quality samples from this massive database.\u00a0<\/p>\n<p><b>Overview<\/b><\/p>\n<p>Realsee3D is a large-scale multi-view\u00a0RGB-D dataset designed to advance research in indoor 3D perception, reconstruction, and scene understanding.<\/p>\n<p><b>Features<\/b><\/p>\n<ul type=\"disc\">\n<li>Large Scale: 10,000 unique indoor scenes, comprising 95,962 rooms and 299,073 viewpoints\/RGB-D pairs.<\/li>\n<li>Rich Data: Panoramic RGB-D captures with complete room-level coverage.<\/li>\n<li>Comprehensive Annotations: Includes CAD drawings, floor plans, semantic segmentation, 3D detection labels and more (forthcoming).<\/li>\n<li>Diverse Scenes: Comprising 1,000 real-world scenes with varied layouts and decoration styles, and 9,000 procedurally generated scenes utilizing over 100 designer-curated style templates, ensuring diverse furniture models and styles for robust training and testing.<\/li>\n<\/ul>\n<p><b>Data Types<\/b><\/p>\n<ul type=\"disc\">\n<li>HDR RGB Panoramic<\/li>\n<li>Depth Map<\/li>\n<li>Poses<\/li>\n<li>CAD Drawings<\/li>\n<li>Floorplans<\/li>\n<li>Segmentation<\/li>\n<li>3D object detection information<\/li>\n<\/ul>\n<p><b>Applicable Research Directions<\/b><\/p>\n<p>For a long time, research and applications in the field of spatial intelligence have faced a bottleneck challenge: there has always been a huge gap in high-quality spatial data. Relying on its technological accumulation and resource reserves in the field of 3D spatial data, Realsee is filling this gap.\u00a0<\/p>\n<p>This dataset is suitable for core research directions in spatial intelligence such as geometric reconstruction, multi-modal learning, and embodied AI. Researchers and developers worldwide are welcome to download and use the Realsee3D 3D dataset to jointly explore the future boundaries of spatial intelligence research.\u00a0<\/p>\n<p><b>Data Organization &amp; Access<\/b><\/p>\n<p>Currently, the Realsee3D dataset is open for application through official channels. Visit the <a href=\"https:\/\/github.com\/realsee-developer\/RealSee3D\" target=\"_blank\" rel=\"nofollow\">Realsee GitHub<\/a> repository to access it:\u00a0<\/p>\n<p><a href=\"https:\/\/github.com\/realsee-developer\/RealSee3D\" target=\"_blank\" rel=\"nofollow\">https:\/\/github.com\/realsee-developer\/RealSee3D<\/a><\/p>\n<div class=\"PRN_ImbeddedAssetReference\">  <\/div>","protected":false},"excerpt":{"rendered":"<p><!-- wp:html --><\/p>\n<p><span class=\"legendSpanClass\"><span class=\"xn-location\">BEIJING<\/span><\/span>, <span class=\"legendSpanClass\"><span class=\"xn-chron\">Dec. 17, 2025<\/span><\/span> \/PRNewswire\/ &#8212; Realsee announced the official opening of Realsee3D, a dataset of 10,000 indoor 3D scenes, for academic research and non-commercial purposes.<\/p>\n<div class=\"PRN_ImbeddedAssetReference\">\n<p><a href=\"https:\/\/mma.prnasia.com\/media2\/2847511\/Realsee3D.html\" target=\"_blank\" rel=\"nofollow\"><img decoding=\"async\" src=\"https:\/\/mma.prnasia.com\/media2\/2847511\/Realsee3D.jpg?p=medium600\" title=\"Realsee3D\" alt=\"Realsee3D\" \/><\/a><br \/><span>Realsee3D<\/span><\/p>\n<\/div>\n<p>This is potentially the world&#8217;s largest spatial 3D dataset to date, aiming to provide a high-quality data foundation for researchers and developers in the field of spatial intelligence, and accelerate the technological iteration and application implementation of the entire industry.\u00a0<\/p>\n<p>Prior to this, Realsee released Argus 1.0, a large model for spatial depth estimation. As the first large model for spatial depth estimation that supports panoramic image input, Argus 1.0 was trained based on the 10-million-level 3D spatial database accumulated by Realsee. The Realsee3D 3D dataset opened this time is precisely a selection of high-quality samples from this massive database.\u00a0<\/p>\n<p><b>Overview<\/b><\/p>\n<p>Realsee3D is a large-scale multi-view\u00a0RGB-D dataset designed to advance research in indoor 3D perception, reconstruction, and scene understanding.<\/p>\n<p><b>Features<\/b><\/p>\n<ul type=\"disc\">\n<li>Large Scale: 10,000 unique indoor scenes, comprising 95,962 rooms and 299,073 viewpoints\/RGB-D pairs.<\/li>\n<li>Rich Data: Panoramic RGB-D captures with complete room-level coverage.<\/li>\n<li>Comprehensive Annotations: Includes CAD drawings, floor plans, semantic segmentation, 3D detection labels and more (forthcoming).<\/li>\n<li>Diverse Scenes: Comprising 1,000 real-world scenes with varied layouts and decoration styles, and 9,000 procedurally generated scenes utilizing over 100 designer-curated style templates, ensuring diverse furniture models and styles for robust training and testing.<\/li>\n<\/ul>\n<p><b>Data Types<\/b><\/p>\n<ul type=\"disc\">\n<li>HDR RGB Panoramic<\/li>\n<li>Depth Map<\/li>\n<li>Poses<\/li>\n<li>CAD Drawings<\/li>\n<li>Floorplans<\/li>\n<li>Segmentation<\/li>\n<li>3D object detection information<\/li>\n<\/ul>\n<p><b>Applicable Research Directions<\/b><\/p>\n<p>For a long time, research and applications in the field of spatial intelligence have faced a bottleneck challenge: there has always been a huge gap in high-quality spatial data. Relying on its technological accumulation and resource reserves in the field of 3D spatial data, Realsee is filling this gap.\u00a0<\/p>\n<p>This dataset is suitable for core research directions in spatial intelligence such as geometric reconstruction, multi-modal learning, and embodied AI. Researchers and developers worldwide are welcome to download and use the Realsee3D 3D dataset to jointly explore the future boundaries of spatial intelligence research.\u00a0<\/p>\n<p><b>Data Organization &amp; Access<\/b><\/p>\n<p>Currently, the Realsee3D dataset is open for application through official channels. Visit the <a href=\"https:\/\/github.com\/realsee-developer\/RealSee3D\" target=\"_blank\" rel=\"nofollow\">Realsee GitHub<\/a> repository to access it:\u00a0<\/p>\n<p><a href=\"https:\/\/github.com\/realsee-developer\/RealSee3D\" target=\"_blank\" rel=\"nofollow\">https:\/\/github.com\/realsee-developer\/RealSee3D<\/a><\/p>\n<div class=\"PRN_ImbeddedAssetReference\">  <\/div>\n<p><!-- \/wp:html --><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"rop_custom_images_group":[],"rop_custom_messages_group":[],"rop_publish_now":"initial","rop_publish_now_accounts":[],"rop_publish_now_history":[],"rop_publish_now_status":"pending","footnotes":""},"categories":[1],"tags":[],"class_list":["post-41866","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-uncategorized"],"_links":{"self":[{"href":"https:\/\/thaipropertynews.com\/feeds\/index.php?rest_route=\/wp\/v2\/posts\/41866","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/thaipropertynews.com\/feeds\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/thaipropertynews.com\/feeds\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/thaipropertynews.com\/feeds\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/thaipropertynews.com\/feeds\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=41866"}],"version-history":[{"count":0,"href":"https:\/\/thaipropertynews.com\/feeds\/index.php?rest_route=\/wp\/v2\/posts\/41866\/revisions"}],"wp:attachment":[{"href":"https:\/\/thaipropertynews.com\/feeds\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=41866"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/thaipropertynews.com\/feeds\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=41866"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/thaipropertynews.com\/feeds\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=41866"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}