{"id":8648,"date":"2019-05-03T11:36:08","date_gmt":"2019-05-03T18:36:08","guid":{"rendered":"http:\/\/jnack.com\/blog\/?p=8648"},"modified":"2024-10-24T15:13:25","modified_gmt":"2024-10-24T22:13:25","slug":"awesome-new-portrait-lighting-tech-from-google","status":"publish","type":"post","link":"https:\/\/jnack.com\/blog\/2019\/05\/03\/awesome-new-portrait-lighting-tech-from-google\/","title":{"rendered":"Awesome new portrait lighting tech from Google"},"content":{"rendered":"<p>The rockstar crew behind Night Sight have created&nbsp;<a href=\"https:\/\/arxiv.org\/abs\/1905.00824\">a neural network<\/a> that takes a standard RGB image from a cellphone &amp; produces a&nbsp;relit image, displaying the subject as though s\/he were illuminated via a different environment map. Check out the results:<\/p>\n<p><iframe loading=\"lazy\" width=\"604\" height=\"340\" src=\"https:\/\/www.youtube.com\/embed\/yxhGWds_g4I?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; encrypted-media; gyroscope; picture-in-picture\" allowfullscreen><\/iframe><\/p>\n<p>I spent <em><a href=\"http:\/\/blogs.adobe.com\/jnack\/2007\/01\/more_fascinating_3d_face_bits.html\">years<\/a><\/em> wanting &amp; trying to get capabilities like this into Photoshop\u2014and now it\u2019s close to running in realtime on your telephone (!). Days of miracles and\u2026 well, you know.<\/p>\n<blockquote><p>Our method is trained on a small database of 18 individuals captured under different directional light sources in a controlled light stage setup consisting of a densely sampled sphere of lights. Our proposed technique produces quantitatively superior results on our dataset&#8217;s validation set compared to prior works, and produces convincing qualitative relighting results on a dataset of hundreds of real-world cellphone portraits. Because our technique can produce a 640 \u00d7 640 image in only 160 milliseconds, it may enable interactive user-facing photographic applications in the future.<\/p><\/blockquote>\n<p>[<a href=\"https:\/\/youtu.be\/yxhGWds_g4I\">YouTube<\/a>]<\/p>\n","protected":false},"excerpt":{"rendered":"<p>The rockstar crew behind Night Sight have created&nbsp;a neural network that takes a standard RGB image from a cellphone &amp; produces a&nbsp;relit image, displaying the subject as though s\/he were illuminated via a different environment map. Check out the results: I spent years wanting &amp; trying to get capabilities like this into Photoshop\u2014and now it\u2019s [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[13,3,75],"tags":[],"_links":{"self":[{"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/8648"}],"collection":[{"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/comments?post=8648"}],"version-history":[{"count":2,"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/8648\/revisions"}],"predecessor-version":[{"id":8651,"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/8648\/revisions\/8651"}],"wp:attachment":[{"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/media?parent=8648"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/categories?post=8648"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/tags?post=8648"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}