{"id":15127,"date":"2021-07-19T06:31:31","date_gmt":"2021-07-19T13:31:31","guid":{"rendered":"http:\/\/jnack.com\/blog\/?p=15127"},"modified":"2021-07-19T06:31:33","modified_gmt":"2021-07-19T13:31:33","slug":"disney-research-shows-off-new-style-transfer-tech","status":"publish","type":"post","link":"https:\/\/jnack.com\/blog\/2021\/07\/19\/disney-research-shows-off-new-style-transfer-tech\/","title":{"rendered":"Disney Research shows off new style-transfer tech"},"content":{"rendered":"\n<p>Okay, this one is a little &#8220;inside baseball,&#8221; but I&#8217;m glad to see more progress using GANs to transfer visual styles among images. <a href=\"https:\/\/studios.disneyresearch.com\/2021\/06\/19\/adaptive-convolutions-for-structure-aware-style-transfer\/\">Check it out<\/a>:<\/p>\n\n\n\n<figure class=\"wp-block-embed is-type-video is-provider-youtube wp-block-embed-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"wp-block-embed__wrapper\">\n<iframe loading=\"lazy\" title=\"Adaptive Convolutions for Structure-Aware Style Transfer\" width=\"604\" height=\"340\" src=\"https:\/\/www.youtube.com\/embed\/GPZ1oDIoG44?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture\" allowfullscreen><\/iframe>\n<\/div><\/figure>\n\n\n\n<blockquote class=\"wp-block-quote\"><p>The current state-of-the-art in neural style transfer uses a technique called Adaptive Instance Normalization (AdaIN), which transfers the statistical properties of style features to a content image, and can transfer an infinite number of styles in real time. However, AdaIN is a global operation, and thus local geometric structures in the style image are often ignored during the transfer. We propose Adaptive convolutions; a generic extension of AdaIN, which allows for the simultaneous transfer of both statistical and structural styles in real time.<\/p><\/blockquote>\n","protected":false},"excerpt":{"rendered":"<p>Okay, this one is a little &#8220;inside baseball,&#8221; but I&#8217;m glad to see more progress using GANs to transfer visual styles among images. Check it out: The current state-of-the-art in neural style transfer uses a technique called Adaptive Instance Normalization (AdaIN), which transfers the statistical properties of style features to a content image, and can [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[66],"tags":[],"_links":{"self":[{"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/15127"}],"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=15127"}],"version-history":[{"count":3,"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/15127\/revisions"}],"predecessor-version":[{"id":15143,"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/15127\/revisions\/15143"}],"wp:attachment":[{"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/media?parent=15127"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/categories?post=15127"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/tags?post=15127"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}