{"id":385181,"date":"2017-08-18T09:16:00","date_gmt":"2017-08-18T01:16:00","guid":{"rendered":"https:\/\/www.engadget.com\/2017\/08\/17\/ai-creates-fictional-scenes-out-of-real-life-photos\/21|23116730"},"modified":"2017-08-18T09:16:00","modified_gmt":"2017-08-18T01:16:00","slug":"ai-creates-fictional-scenes-out-of-real-life-photos","status":"publish","type":"post","link":"https:\/\/people.utm.my\/asmawisham\/ai-creates-fictional-scenes-out-of-real-life-photos\/","title":{"rendered":"AI creates fictional scenes out of real-life photos"},"content":{"rendered":"<p>Researcher Qifeng Chen of <a href=\"https:\/\/arxiv.org\/abs\/1707.09405\">Stanford<\/a> and Intel fed his AI system 5,000 photos from German streets. Then, with some human help it can build slightly blurry made-up scenes. The image at the top of this article is a example of the network&#8217;s output.<\/p>\n<p>To create an image a human needs to tell the AI system what goes where. Put a car here, put a building there, place a tree right there. It&#8217;s paint by numbers and the system generates a wholly unique scene based on that input.<\/p>\n<p><iframe loading=\"lazy\" allowfullscreen=\"\" frameborder=\"0\" height=\"354\" src=\"https:\/\/www.youtube.com\/embed\/0fhUJT21-bs\" width=\"630\">[embedded content]<\/iframe><\/p>\n<p>Chen&#8217;s AI isn&#8217;t quite good enough to create photorealistic scenes just yet. It doesn&#8217;t know enough to fill in all those tiny pixels. It&#8217;s not going to replace the high-end special effects houses that spend months building a world. But, it could be used to create video game and VR worlds where not everything needs to look perfect in the near future.<\/p>\n<p>Intel plans on showing off the tech at the International Conference on Computer Vision in October.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Researcher Qifeng Chen of Stanford and Intel fed his AI system 5,000 photos from German streets. Then, with some human help it can build slightly blurry made-up scenes. The image at the top of this article is a example of the network&#8217;s output. To create an image a human needs to tell the AI system [&hellip;]<\/p>\n","protected":false},"author":5817,"featured_media":385182,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_et_pb_use_builder":"","_et_pb_old_content":"","_et_gb_content_width":"","footnotes":""},"categories":[23],"tags":[27,59,26],"class_list":["post-385181","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-media","tag-engadget","tag-media","tag-technology"],"_links":{"self":[{"href":"https:\/\/people.utm.my\/asmawisham\/wp-json\/wp\/v2\/posts\/385181","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/people.utm.my\/asmawisham\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/people.utm.my\/asmawisham\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/people.utm.my\/asmawisham\/wp-json\/wp\/v2\/users\/5817"}],"replies":[{"embeddable":true,"href":"https:\/\/people.utm.my\/asmawisham\/wp-json\/wp\/v2\/comments?post=385181"}],"version-history":[{"count":0,"href":"https:\/\/people.utm.my\/asmawisham\/wp-json\/wp\/v2\/posts\/385181\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/people.utm.my\/asmawisham\/wp-json\/wp\/v2\/media\/385182"}],"wp:attachment":[{"href":"https:\/\/people.utm.my\/asmawisham\/wp-json\/wp\/v2\/media?parent=385181"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/people.utm.my\/asmawisham\/wp-json\/wp\/v2\/categories?post=385181"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/people.utm.my\/asmawisham\/wp-json\/wp\/v2\/tags?post=385181"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}