{"id":13371,"date":"2020-10-04T09:57:17","date_gmt":"2020-10-04T16:57:17","guid":{"rendered":"http:\/\/jnack.com\/blog\/?p=13371"},"modified":"2024-10-24T15:13:25","modified_gmt":"2024-10-24T22:13:25","slug":"google-researchers-demo-ai-powered-shadow-removal","status":"publish","type":"post","link":"http:\/\/jnack.com\/blog\/2020\/10\/04\/google-researchers-demo-ai-powered-shadow-removal\/","title":{"rendered":"Google &#038; researchers demo AI-powered shadow removal"},"content":{"rendered":"\n<p>Speaking of Google photography research (see <a href=\"http:\/\/jnack.com\/blog\/2020\/10\/02\/interactive-portrait-light-comes-to-google-photos-on-pixel-editor-gets-upgraded\/\">previous post about portrait relighting<\/a>), I&#8217;ve been meaning to point to the team&#8217;s collaboration with MIT &amp; Berkeley. As PetaPixel <a href=\"https:\/\/petapixel.com\/2020\/08\/24\/this-ai-automatically-removes-harsh-shadows-from-your-portraits\/\">writes<\/a>,<\/p>\n\n\n\n<blockquote class=\"wp-block-quote\"><p>The tech itself relies on not one, but two neural networks: one to remove \u201cforeign\u201d shadows that are cast by unwanted objects like a hat or a hand held up to block the sun in your eyes, and the other to soften natural facial shadows and add \u201ca synthetic fill light\u201d to improve the lighting ratio once the unwanted shadows have been removed.<\/p><\/blockquote>\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=\"Portrait Shadow Manipulation\" width=\"604\" height=\"340\" src=\"https:\/\/www.youtube.com\/embed\/M_qYTXhzyac?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; 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\" loading=\"lazy\" width=\"1024\" height=\"538\" src=\"http:\/\/jnack.com\/blog\/wp-content\/uploads\/2020\/08\/shadows-1024x538.jpg\" alt=\"\" class=\"wp-image-13373\" srcset=\"http:\/\/jnack.com\/blog\/wp-content\/uploads\/2020\/08\/shadows-1024x538.jpg 1024w, http:\/\/jnack.com\/blog\/wp-content\/uploads\/2020\/08\/shadows-300x158.jpg 300w, http:\/\/jnack.com\/blog\/wp-content\/uploads\/2020\/08\/shadows-768x403.jpg 768w, http:\/\/jnack.com\/blog\/wp-content\/uploads\/2020\/08\/shadows.jpg 1200w\" sizes=\"(max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n\n<p>Here&#8217;s a nice summary from Two-Minute Papers:<\/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\/qeZMKgKJLX4\n<\/div><\/figure>\n","protected":false},"excerpt":{"rendered":"<p>Speaking of Google photography research (see previous post about portrait relighting), I&#8217;ve been meaning to point to the team&#8217;s collaboration with MIT &amp; Berkeley. As PetaPixel writes, The tech itself relies on not one, but two neural networks: one to remove \u201cforeign\u201d shadows that are cast by unwanted objects like a hat or a hand [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[35,3,75],"tags":[],"_links":{"self":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/13371"}],"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=13371"}],"version-history":[{"count":6,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/13371\/revisions"}],"predecessor-version":[{"id":13565,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/13371\/revisions\/13565"}],"wp:attachment":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/media?parent=13371"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/categories?post=13371"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/tags?post=13371"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}