{"id":6247,"date":"2024-03-26T09:15:03","date_gmt":"2024-03-26T01:15:03","guid":{"rendered":"https:\/\/www.1ai.net\/?p=6247"},"modified":"2024-03-26T09:15:03","modified_gmt":"2024-03-26T01:15:03","slug":"meta-%e6%8e%a8%e5%87%ba-scenescript-ai-%e8%a7%86%e8%a7%89%e6%a8%a1%e5%9e%8b%ef%bc%8c%e5%88%a9%e7%94%a8%e5%8f%af%e7%bc%96%e7%a8%8b%e8%af%ad%e8%a8%80%e5%ae%9e%e6%97%b6%e9%a2%84%e6%b5%8b%e5%bb%ba","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/6247.html","title":{"rendered":"Meta launches SceneScript AI visual model, using programmable language to predict and build 3D scenes in real time"},"content":{"rendered":"<p data-vmark=\"a975\">according to <a href=\"https:\/\/www.1ai.net\/en\/tag\/meta\" title=\"[View articles tagged with [Meta]]\" target=\"_blank\" >Meta<\/a> The company&#039;s official press release said that it has developed a software called &quot;SceneScript&quot;<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e8%a7%86%e8%a7%89%e6%a8%a1%e5%9e%8b\" title=\"[Sees articles with [visual model] labels]\" target=\"_blank\" >Visual Model<\/a>, which claims to be able to use a programmable language to quickly &quot;build&quot; scenes, infer room geometry in real time, and convert related data into architectural approximations.<\/p>\n<p data-vmark=\"1e1a\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-6248\" title=\"76129f1b-5363-4eda-9330-aab1d1533a04\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/03\/76129f1b-5363-4eda-9330-aab1d1533a04.png\" alt=\"76129f1b-5363-4eda-9330-aab1d1533a04\" width=\"1176\" height=\"652\" \/><\/p>\n<p>Image source: Meta company official press release<\/p>\n<p data-vmark=\"da33\">Meta claims that the method can efficiently and lightly build indoor 3D models.<span class=\"accentTextColor\">It claims that &quot;only a few KB of memory are needed to generate clear and complete geometric shapes&quot;<\/span>, and the related shape data is &quot;interpretable&quot; and users can easily read and edit these data representations.<\/p>\n<p data-vmark=\"b3dc\">Developers borrowed the &quot;word prediction&quot; method of large language models to develop SceneScript. Take the Llama model as an example. The model can predict the next word of a sentence based on the previous words. For example, if the input sentence is &quot;The cat sat on the...&quot;, the model will predict that the next word may be &quot;mat&quot; or &quot;floor&quot;. SceneScript uses the same concept.<span class=\"accentTextColor\">That is, the subsequent content is derived from the previous input content, and these architectural descriptions are used to reconstruct the complex indoor 3D environment<\/span>.<\/p>","protected":false},"excerpt":{"rendered":"<p>According to an official Meta press release, the company has developed a visual model called \"SceneScript,\" which claims to be able to use a programmable language to quickly \"build\" a scene, infer room geometry in real time, and convert relevant data into architectural-level approximations. data into architectural-level approximations. Meta claims that the method is efficient and lightweight for building 3D models of interiors, claiming that it \"requires only a few KBs of memory to generate clear and complete geometries\" and that the shape data is \"interpretable\" and can be easily read by users. The associated shape data is \"interpretable\" and users can easily read and edit these representations. The developers drew on the \"predictive word\" approach of large language models to develop SceneScript, using the Llama model as the basis.<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[297,1865],"collection":[],"class_list":["post-6247","post","type-post","status-publish","format-standard","hentry","category-news","tag-meta","tag-1865"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/6247","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/comments?post=6247"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/6247\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=6247"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=6247"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=6247"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=6247"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}