{"id":6860,"date":"2018-04-25T08:02:35","date_gmt":"2018-04-25T15:02:35","guid":{"rendered":"http:\/\/jnack.com\/blog\/?p=6860"},"modified":"2018-04-24T22:36:27","modified_gmt":"2018-04-25T05:36:27","slug":"nvidias-giving-me-the-content-aware-feels","status":"publish","type":"post","link":"http:\/\/jnack.com\/blog\/2018\/04\/25\/nvidias-giving-me-the-content-aware-feels\/","title":{"rendered":"NVIDIA&#8217;s giving me the Content-Aware Feels"},"content":{"rendered":"<p>Crazy to think that it\u2019s been <a href=\"https:\/\/www.youtube.com\/watch?v=NH0aEp1oDOI\">8+ years<\/a> since Photoshop added Content-Aware Fill\u2014itself derived from earlier <a href=\"http:\/\/gfx.cs.princeton.edu\/pubs\/Barnes_2009_PAR\/patchmatch.mp4\">PatchMatch<\/a> technology. Time &amp; tech march onward, and new NVIDIA research promises to raise the game. As PetaPixel <a href=\"https:\/\/petapixel.com\/2018\/04\/23\/nvidias-ai-powered-content-aware-fill-is-mind-blowing\/\">notes<\/a>,<\/p>\n<blockquote>\n<p>What\u2019s amazing about NVIDIA\u2019s system and the current \u201cContent-Aware Fill\u201d in Photoshop is that NVIDIA\u2019s tool doesn\u2019t just glean information from surrounding pixels to figure out what to fill holes with \u2014 it understands what the subject should look like.<\/p>\n<\/blockquote>\n<p>Check it out:<\/p>\n<p><iframe loading=\"lazy\" width=\"604\" height=\"340\" src=\"https:\/\/www.youtube.com\/embed\/gg0F5JjKmhA?feature=oembed\" frameborder=\"0\" allow=\"autoplay; encrypted-media\" allowfullscreen><\/iframe><\/p>\n<blockquote>\n<p>Researchers from NVIDIA, led by Guilin Liu, introduced a state-of-the-art deep learning method that can edit images or reconstruct a corrupted image, one that has holes or is missing pixels. The method can also be used to edit images by removing content and filling in the resulting holes. Learn more about their research paper \u201c<a href=\"https:\/\/nvda.ws\/2K1G243\">Image Inpainting for Irregular Holes Using Partial Convolutions<\/a>.\u201d<\/p>\n<\/blockquote>\n<p><img decoding=\"async\" loading=\"lazy\" title=\"NewImage.png\" src=\"http:\/\/jnack.com\/blog\/wp-content\/uploads\/2018\/04\/NewImage-26.png\" alt=\"NewImage\" width=\"600\" height=\"300\" border=\"0\" \/><\/p>\n<p>[<a href=\"https:\/\/youtu.be\/gg0F5JjKmhA\">YouTube<\/a>] [Via John Lin]<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Crazy to think that it\u2019s been 8+ years since Photoshop added Content-Aware Fill\u2014itself derived from earlier PatchMatch technology. Time &amp; tech march onward, and new NVIDIA research promises to raise the game. As PetaPixel notes, What\u2019s amazing about NVIDIA\u2019s system and the current \u201cContent-Aware Fill\u201d in Photoshop is that NVIDIA\u2019s tool doesn\u2019t just glean information [&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":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/6860"}],"collection":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/comments?post=6860"}],"version-history":[{"count":3,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/6860\/revisions"}],"predecessor-version":[{"id":6865,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/6860\/revisions\/6865"}],"wp:attachment":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/media?parent=6860"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/categories?post=6860"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/tags?post=6860"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}