{"id":28313,"date":"2018-01-09T22:15:12","date_gmt":"2018-01-09T20:15:12","guid":{"rendered":"https:\/\/mamchenkov.net\/wordpress\/?p=28313"},"modified":"2018-01-09T22:15:12","modified_gmt":"2018-01-09T20:15:12","slug":"how-an-a-i-cat-and-mouse-game-generates-believable-fake-photos","status":"publish","type":"post","link":"https:\/\/mamchenkov.net\/wordpress\/2018\/01\/09\/how-an-a-i-cat-and-mouse-game-generates-believable-fake-photos\/","title":{"rendered":"How an A.I. \u2018Cat-and-Mouse Game\u2019 Generates Believable Fake Photos"},"content":{"rendered":"\n

\"\"<\/a><\/p>\n

The New York Times<\/a> is running a very fascinating article on the progress of the artificial intelligence and machine learning in both identifying and generating fake photos –\u00a0How an A.I. \u2018Cat-and-Mouse Game\u2019 Generates Believable Fake Photos<\/a>.\u00a0 \u00a0The above image shows the progress of the AI working against itself and learning from its own results – one part is trying to identify if the photo is fake or not, and the other part is trying to generate a fake photo which will pass the test.\u00a0 When the test fails, the system learns, improves, and tries again.\u00a0 Look at the last row of photos, which are super realistic and took the system between 10 to 18 days to learn how to generate.<\/p>\n

But that’s not all.\u00a0 It gets better, and I quote:<\/p>\n

A second team of Nvidia researchers recently\u00a0<\/a>built a system<\/a>\u00a0that can automatically alter a street photo taken on a summer\u2019s day so that it looks like a snowy winter scene. Researchers at the University of California, Berkeley, have\u00a0<\/a>designed another<\/a>\u00a0that learns to convert horses into zebras and Monets into Van Goghs. DeepMind, a London-based A.I. lab owned by Google, is\u00a0<\/a>exploring technology that can generate its own videos<\/a>. And Adobe is fashioning similar machine learning techniques with an eye toward pushing them into products like Photoshop, its popular image design tool.<\/p><\/blockquote>\n

Here are a few more photos that were generated:<\/p>\n

\"\"<\/a><\/p>\n

This is remarkable.\u00a0 But if you keep reading the article, you’ll quickly discover that there is even more to it.\u00a0 What’s next in line after pictures?\u00a0 You are correct: videos.\u00a0 You better sit down before you watch this video<\/a>, showing Obama’s lip sync:<\/p>\n