{"id":13913,"date":"2020-12-01T07:42:08","date_gmt":"2020-12-01T15:42:08","guid":{"rendered":"http:\/\/jnack.com\/blog\/?p=13913"},"modified":"2020-12-01T09:58:47","modified_gmt":"2020-12-01T17:58:47","slug":"new-google-research-witchcraft-retimes-humans-in-video","status":"publish","type":"post","link":"http:\/\/jnack.com\/blog\/2020\/12\/01\/new-google-research-witchcraft-retimes-humans-in-video\/","title":{"rendered":"New Google Research witchcraft retimes humans in video"},"content":{"rendered":"\n<p>There&#8217;s no way the title can do this one justice, so just watch as this ML-based technique identifies moving humans (including their reflections!), then segments them out to enable individual manipulation\u2014including syncing up their motions and even removing people wholesale:<\/p>\n\n\n\n<figure class=\"wp-block-embed-youtube wp-block-embed is-type-video is-provider-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"wp-block-embed__wrapper\">\nhttps:\/\/youtu.be\/2pWK0arWAmU\n<\/div><\/figure>\n\n\n\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" src=\"https:\/\/retiming.github.io\/assets\/teaser1.gif\" alt=\"\"\/><\/figure>\n\n\n\n<p>Here&#8217;s the vid directly from <a href=\"https:\/\/retiming.github.io\/\">the research team<\/a>, which includes longtime Adobe vet David Salesin:<\/p>\n\n\n\n<figure class=\"wp-block-embed-youtube wp-block-embed is-type-video is-provider-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"wp-block-embed__wrapper\">\n<iframe loading=\"lazy\" title=\"Layered Neural Rendering for Retiming People in Video (SIGGRAPH Asia 2020)\" width=\"604\" height=\"340\" src=\"https:\/\/www.youtube.com\/embed\/KAVCHR1mucw?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture\" allowfullscreen><\/iframe>\n<\/div><\/figure>\n\n\n\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" src=\"https:\/\/retiming.github.io\/assets\/teaser2.gif\" alt=\"\"\/><\/figure>\n","protected":false},"excerpt":{"rendered":"<p>There&#8217;s no way the title can do this one justice, so just watch as this ML-based technique identifies moving humans (including their reflections!), then segments them out to enable individual manipulation\u2014including syncing up their motions and even removing people wholesale: Here&#8217;s the vid directly from the research team, which includes longtime Adobe vet David Salesin:<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[17],"tags":[],"_links":{"self":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/13913"}],"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=13913"}],"version-history":[{"count":4,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/13913\/revisions"}],"predecessor-version":[{"id":13919,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/13913\/revisions\/13919"}],"wp:attachment":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/media?parent=13913"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/categories?post=13913"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/tags?post=13913"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}