{"id":4683,"date":"2016-11-14T11:43:17","date_gmt":"2016-11-14T19:43:17","guid":{"rendered":"http:\/\/jnack.com\/blog\/?p=4683"},"modified":"2016-11-14T11:51:36","modified_gmt":"2016-11-14T19:51:36","slug":"check-out-google-raisr-sharp-images-with-machine-learning","status":"publish","type":"post","link":"http:\/\/jnack.com\/blog\/2016\/11\/14\/check-out-google-raisr-sharp-images-with-machine-learning\/","title":{"rendered":"Check out Google RAISR: Sharp images with machine learning"},"content":{"rendered":"

If you share a picture of a tree in a forest, but no one can see it, did you really share it?<\/p>\n

Working at Google, where teams aspire to \u201cthree-comma moments” (i.e. reaching 1,000,000,000 users), it\u2019s become overwhelmingly clear to me that all the fancy features in the world don\u2019t mean squat if people can\u2019t access them. And traveling in Nepal, I got a taste of just how slow & expensive connectivity can be. Anything that helps deliver content faster & more cheaply means more democratic access to ideas & inspiration.<\/p>\n

That\u2019s why I\u2019ve been really excited about RAISR<\/a> (“Rapid and Accurate Image Super-Resolution\u201d). The Google Research team writes<\/a>,<\/p>\n

\n

[It\u2019s] a technique that incorporates machine learning in order to produce high-quality versions of low-resolution images<\/strong>. RAISR produces results that are comparable to or better than the currently available super-resolution methods, and does so roughly 10 to 100 times faster<\/strong>, allowing it to be run on a typical mobile device in real-time.<\/p>\n<\/blockquote>\n

\"NewImage\"<\/p>\n

I\u2019ve been championing this tech within the company and\u2014because the research paper is public\u2014encouraging friends at Facebook, Adobe, Apple, and elsewhere to check it out. Fast, affordable access is good for everyone.<\/p>\n

It\u2019s funny: I came here to \u201cteach Google Photoshop\u201d (i.e. to make computers see & create like artists), yet if I do my job right here, you\u2019ll never spot a thing. I\u2019ve come to prioritize access<\/em> far ahead of synthesis<\/em>. Funny ol’ world.<\/p>\n

PS\u2014Obligatory (?) Old Man Nack remark: \u201cIn my<\/em> day, Genuine Fractals, blah blah\u2026\u201d<\/p>\n","protected":false},"excerpt":{"rendered":"

If you share a picture of a tree in a forest, but no one can see it, did you really share it? Working at Google, where teams aspire to \u201cthree-comma moments” (i.e. reaching 1,000,000,000 users), it\u2019s become overwhelmingly clear to me that all the fancy features in the world don\u2019t mean squat if people can\u2019t […]<\/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\/4683"}],"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=4683"}],"version-history":[{"count":2,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/4683\/revisions"}],"predecessor-version":[{"id":4685,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/4683\/revisions\/4685"}],"wp:attachment":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/media?parent=4683"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/categories?post=4683"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/tags?post=4683"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}