{"id":7031,"date":"2018-05-29T16:29:14","date_gmt":"2018-05-29T23:29:14","guid":{"rendered":"http:\/\/jnack.com\/blog\/?p=7031"},"modified":"2018-05-29T17:07:42","modified_gmt":"2018-05-30T00:07:42","slug":"demo-generating-realistic-3d-faces-skin-from-ordinary-photos","status":"publish","type":"post","link":"https:\/\/jnack.com\/blog\/2018\/05\/29\/demo-generating-realistic-3d-faces-skin-from-ordinary-photos\/","title":{"rendered":"Demo: Generating realistic 3D faces &#038; skin from ordinary photos"},"content":{"rendered":"<p><a href=\"http:\/\/blogs.adobe.com\/jnack\/2007\/01\/more_fascinating_3d_face_bits.html\">10+ years ago<\/a>, I really hoped we\u2019d get Photoshop to <a href=\"https:\/\/www.youtube.com\/watch?v=nice6NYb_WA&amp;eurl=\">understand a human face as a 3D structure<\/a>\u00a0that one could relight, re-pose, etc. We never got there, sadly. <a href=\"http:\/\/jnack.com\/blog\/2017\/03\/21\/snapseed-gains-double-exposure-face-pose-and-more\/\">Last year<\/a> we gave Snapseed the ability to change the orientation of a face (see <a href=\"https:\/\/www.androidpolice.com\/wp-content\/uploads\/2017\/03\/nexus2cee_Snapseed_Face_Pose_Animated_cropped_thumb.gif\">GIF<\/a>)\u2014another small step in the right direction. Progress marches forward, and now USC prof. Hao Li &amp; team have demonstrated a <a href=\"http:\/\/www.hao-li.com\/publications\/papers\/siggraph2018HFFRGIFUI.pdf\">method<\/a>\u00a0for generating models with realistic skin from just ordinary input images. It\u2019ll be fun to see where this leads (e.g. see <a href=\"http:\/\/jnack.com\/blog\/2018\/05\/24\/apollo-portrait-lighting-app-threatens-to-be-good\/\">previous<\/a>).<\/p>\n<p><a href=\"https:\/\/youtu.be\/khNWYKfZwjQ%5D\">https:\/\/youtu.be\/khNWYKfZwjQ]<\/a><\/p>\n<p><img decoding=\"async\" loading=\"lazy\" title=\"NewImage.png\" src=\"http:\/\/jnack.com\/blog\/wp-content\/uploads\/2018\/05\/NewImage-35.png\" alt=\"NewImage\" width=\"598\" height=\"332\" border=\"0\" \/><\/p>\n<p>\u00a0[<a href=\"https:\/\/youtu.be\/khNWYKfZwjQ\">YouTube<\/a>]<\/p>\n","protected":false},"excerpt":{"rendered":"<p>10+ years ago, I really hoped we\u2019d get Photoshop to understand a human face as a 3D structure\u00a0that one could relight, re-pose, etc. We never got there, sadly. Last year we gave Snapseed the ability to change the orientation of a face (see GIF)\u2014another small step in the right direction. Progress marches forward, and now [&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],"tags":[],"_links":{"self":[{"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/7031"}],"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=7031"}],"version-history":[{"count":3,"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/7031\/revisions"}],"predecessor-version":[{"id":7034,"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/7031\/revisions\/7034"}],"wp:attachment":[{"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/media?parent=7031"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/categories?post=7031"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/tags?post=7031"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}