{"id":758,"date":"2014-06-02T06:58:11","date_gmt":"2014-06-02T13:58:11","guid":{"rendered":"http:\/\/jnack.com\/blog\/?p=758"},"modified":"2014-06-02T06:58:11","modified_gmt":"2014-06-02T13:58:11","slug":"demo-transferring-photographic-style-among-faces","status":"publish","type":"post","link":"https:\/\/jnack.com\/blog\/2014\/06\/02\/demo-transferring-photographic-style-among-faces\/","title":{"rendered":"Demo: Transferring photographic style among faces"},"content":{"rendered":"<p>My old Adobe colleague Sylvain Paris &amp; a team at MIT have long worked on enabling style transfer among images (see demos from <a href=\"http:\/\/blogs.adobe.com\/jnack\/2010\/11\/sneak-peeks-new-adobe-digital-imaging-tech.html\">2010<\/a> &amp; <a href=\"http:\/\/blogs.adobe.com\/jnack\/2013\/05\/sneak-peek-playing-with-lighting-in-photoshop-and-after-effects.html\">last year<\/a>), and now they\u2019re demonstrating new progress in <a href=\"http:\/\/newsoffice.mit.edu\/2014\/spruce-your-selfie\">a new SIGGRAPH paper<\/a>:<\/p>\n<blockquote>\n<p>Using off-the-shelf face recognition software, they first identify a portrait, in the desired style, that has characteristics similar to those of the photo to be modified. \u201cWe then find a dense correspondence \u2014 like eyes to eyes, beard to beard, skin to skin \u2014 and do this local transfer,\u201d Shih explains.<\/p>\n<\/blockquote>\n<p><img decoding=\"async\" loading=\"lazy\" title=\"Headshots.png\" src=\"http:\/\/jnack.com\/blog\/wp-content\/uploads\/2014\/06\/Headshots.png\" alt=\"NewImage\" width=\"600\" height=\"400\" border=\"0\" \/><\/p>\n<p>Check out this quick demo, including the ability to apply style to video (provided it\u2019s a headshot):<\/p>\n<p><iframe loading=\"lazy\" width=\"604\" height=\"340\" src=\"https:\/\/www.youtube.com\/embed\/ixCxK75jl9M?feature=oembed\" frameborder=\"0\" allow=\"autoplay; encrypted-media\" allowfullscreen><\/iframe><\/p>\n<p>Neat stuff. [<a href=\"http:\/\/youtu.be\/ixCxK75jl9M\">YouTube<\/a>]<\/p>\n<p>\u00a0<\/p>\n","protected":false},"excerpt":{"rendered":"<p>My old Adobe colleague Sylvain Paris &amp; a team at MIT have long worked on enabling style transfer among images (see demos from 2010 &amp; last year), and now they\u2019re demonstrating new progress in a new SIGGRAPH paper: Using off-the-shelf face recognition software, they first identify a portrait, in the desired style, that has characteristics [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[3],"tags":[],"_links":{"self":[{"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/758"}],"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=758"}],"version-history":[{"count":1,"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/758\/revisions"}],"predecessor-version":[{"id":759,"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/758\/revisions\/759"}],"wp:attachment":[{"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/media?parent=758"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/categories?post=758"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/tags?post=758"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}