{"id":1202,"date":"2016-03-09T10:47:10","date_gmt":"2016-03-09T02:47:10","guid":{"rendered":"http:\/\/magicalbits.net\/?p=1202"},"modified":"2016-03-09T10:47:10","modified_gmt":"2016-03-09T02:47:10","slug":"awentzonlineimage-analogies-generate-image-analogies-using-neural-matching-and-blending","status":"publish","type":"post","link":"https:\/\/magicalbits.net\/?p=1202","title":{"rendered":"awentzonline\/image-analogies: Generate image analogies using neural matching and blending."},"content":{"rendered":"<blockquote><p><a href=\"https:\/\/github.com\/awentzonline\/image-analogies\"><img decoding=\"async\" class=\"alignnone size-full\" src=\"http:\/\/magicalbits.net\/wp-content\/uploads\/2016\/03\/image-analogy-explanation.jpg\" alt=\"\" \/><\/a><a href=\"https:\/\/github.com\/awentzonline\/image-analogies\"><img decoding=\"async\" class=\"alignnone size-full\" src=\"http:\/\/magicalbits.net\/wp-content\/uploads\/2016\/03\/trump-image-analogy.jpg\" alt=\"\" \/><\/a><a href=\"https:\/\/github.com\/awentzonline\/image-analogies\"><img decoding=\"async\" class=\"alignnone size-full\" src=\"http:\/\/magicalbits.net\/wp-content\/uploads\/2016\/03\/sugarskull-analogy.jpg\" alt=\"\" \/><\/a>This is basically an implementation of this &#8220;Image Analogies&#8221; paper http:\/\/www.mrl.nyu.edu\/projects\/image-analogies\/index.html In our case, we use feature maps from VGG16. The patch matching and blending is done with a method described in &#8220;Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis&#8221; http:\/\/arxiv.org\/abs\/1601.04589 Effects similar to that paper can be achieved by turning off the analogy loss (or leave it on!) and turning on the B\/B&#8217; content weighting via the &#8211;b-cont<\/p><\/blockquote>\n<p>Source: <em><a href=\"https:\/\/github.com\/awentzonline\/image-analogies\">awentzonline\/image-analogies: Generate image analogies using neural matching and blending.<\/a><\/em><\/p>\n","protected":false},"excerpt":{"rendered":"<p>This is basically an implementation of this &#8220;Image Analogies&#8221; paper http:\/\/www.mrl.nyu.edu\/projects\/image-analogies\/index.html In our case, we use feature maps from VGG16. The patch matching and blending is done with a method described in &#8220;Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis&#8221; http:\/\/arxiv.org\/abs\/1601.04589 Effects similar to that paper can be achieved by turning off [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"ep_exclude_from_search":false,"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[1],"tags":[],"class_list":["post-1202","post","type-post","status-publish","format-standard","hentry","category-uncategorised"],"jetpack_featured_media_url":"","jetpack-related-posts":[],"jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/magicalbits.net\/index.php?rest_route=\/wp\/v2\/posts\/1202","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/magicalbits.net\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/magicalbits.net\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/magicalbits.net\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/magicalbits.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1202"}],"version-history":[{"count":1,"href":"https:\/\/magicalbits.net\/index.php?rest_route=\/wp\/v2\/posts\/1202\/revisions"}],"predecessor-version":[{"id":1206,"href":"https:\/\/magicalbits.net\/index.php?rest_route=\/wp\/v2\/posts\/1202\/revisions\/1206"}],"wp:attachment":[{"href":"https:\/\/magicalbits.net\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1202"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/magicalbits.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1202"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/magicalbits.net\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1202"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}