{"id":35,"date":"2022-04-28T04:11:11","date_gmt":"2022-04-28T04:11:11","guid":{"rendered":"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/?page_id=35"},"modified":"2022-05-02T05:04:04","modified_gmt":"2022-05-02T05:04:04","slug":"experiments","status":"publish","type":"page","link":"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/experiments\/","title":{"rendered":"Interactive Face Editing in 2D"},"content":{"rendered":"\n<p class=\"has-text-align-center\"><img decoding=\"async\" width=\"794px;\" height=\"340px;\" src=\"https:\/\/lh5.googleusercontent.com\/L9DrTSNfbTcKZFaJqLkYQM9R9EhBVWkdpGKny5soRHDyHpqh2Vrk3l0IKap2oQQzL6u_wXgvcfdQWmdMk1js1ZNOU48FWx1VrZpIYcMRSFqf1vZl37IgTZsluuzMpvhgQmT4Ho7agAF2n48i2lRN\"><em>High-quality facial attributes editing results from  InterFaceGAN.<\/em><\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>GAN Inversion<\/strong><\/h2>\n\n\n\n<p>GAN inversion aims to invert a given image back into the latent space of a pre-trained GAN model, for the image to be faithfully reconstructed from the inverted code by the generator. This allows us to manipulate the latent vectors to control facial attributes like age, smile, etc by traversing along the corresponding dimensions. The following figure explains the high-level concept of GAN inversion and its use for face manipulation.<\/p>\n\n\n\n<p><img decoding=\"async\" width=\"583px;\" height=\"376px;\" src=\"https:\/\/lh5.googleusercontent.com\/Zq0m7BUYAyw1iGaetLT6NrYGpGSOAwWjb_r4LeaPy6sGyr3hY5NH4VrD_uuNyas4l0YPMIUlPA03Ck4UusTI56kSa01WjtNcqxH8FwKRDy4kYjB0emvKK9qGKPpOlJPhwD6Ppg2ZzVHvVCzUOJB6\"><\/p>\n\n\n\n<p class=\"has-text-align-center\"><em>GAN Inversion Overview<\/em><\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>GAN inversion for face manipulation:<\/strong><\/h3>\n\n\n\n<p>We applied some of the state of art approaches in GAN inversion literature to invert an image to a latent code that supports high-fidelity controllable edits and realistic image generation. We ran the following approaches that gave us the following results:<\/p>\n\n\n\n<ol class=\"wp-block-list\"><li>HyperStyle:<\/li><\/ol>\n\n\n\n<figure class=\"wp-block-image size-full is-resized\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/wp-content\/uploads\/sites\/58\/2022\/04\/image.png\" alt=\"\" class=\"wp-image-115\" width=\"527\" height=\"294\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/wp-content\/uploads\/sites\/58\/2022\/04\/image.png 463w, https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/wp-content\/uploads\/sites\/58\/2022\/04\/image-300x167.png 300w\" sizes=\"auto, (max-width: 527px) 100vw, 527px\" \/><\/figure>\n\n\n\n<figure class=\"wp-block-image size-full is-resized\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/wp-content\/uploads\/sites\/58\/2022\/04\/image-1.png\" alt=\"\" class=\"wp-image-116\" width=\"524\" height=\"285\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/wp-content\/uploads\/sites\/58\/2022\/04\/image-1.png 494w, https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/wp-content\/uploads\/sites\/58\/2022\/04\/image-1-300x163.png 300w\" sizes=\"auto, (max-width: 524px) 100vw, 524px\" \/><\/figure>\n\n\n\n<figure class=\"wp-block-image size-full is-resized\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/wp-content\/uploads\/sites\/58\/2022\/04\/image-2.png\" alt=\"\" class=\"wp-image-118\" width=\"522\" height=\"280\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/wp-content\/uploads\/sites\/58\/2022\/04\/image-2.png 490w, https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/wp-content\/uploads\/sites\/58\/2022\/04\/image-2-300x161.png 300w\" sizes=\"auto, (max-width: 522px) 100vw, 522px\" \/><\/figure>\n\n\n\n<p>2. <em>Pivotal Tuning Inversion<\/em>:<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"580\" height=\"306\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/wp-content\/uploads\/sites\/58\/2022\/04\/image-3.png\" alt=\"\" class=\"wp-image-122\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/wp-content\/uploads\/sites\/58\/2022\/04\/image-3.png 580w, https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/wp-content\/uploads\/sites\/58\/2022\/04\/image-3-300x158.png 300w\" sizes=\"auto, (max-width: 580px) 100vw, 580px\" \/><\/figure>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"590\" height=\"289\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/wp-content\/uploads\/sites\/58\/2022\/04\/image-4.png\" alt=\"\" class=\"wp-image-123\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/wp-content\/uploads\/sites\/58\/2022\/04\/image-4.png 590w, https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/wp-content\/uploads\/sites\/58\/2022\/04\/image-4-300x147.png 300w\" sizes=\"auto, (max-width: 590px) 100vw, 590px\" \/><\/figure>\n\n\n\n<p>3. StyleCLIP:<\/p>\n\n\n\n<figure class=\"wp-block-image size-full is-resized\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/wp-content\/uploads\/sites\/58\/2022\/04\/image-6.png\" alt=\"\" class=\"wp-image-140\" width=\"637\" height=\"349\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/wp-content\/uploads\/sites\/58\/2022\/04\/image-6.png 572w, https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/wp-content\/uploads\/sites\/58\/2022\/04\/image-6-300x164.png 300w\" sizes=\"auto, (max-width: 637px) 100vw, 637px\" \/><figcaption>Text Driven Image Manipulation of StyleGAN Imagery<\/figcaption><\/figure>\n\n\n\n<figure class=\"wp-block-image size-full is-resized\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/wp-content\/uploads\/sites\/58\/2022\/04\/image-8.png\" alt=\"\" class=\"wp-image-143\" width=\"633\" height=\"335\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/wp-content\/uploads\/sites\/58\/2022\/04\/image-8.png 580w, https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/wp-content\/uploads\/sites\/58\/2022\/04\/image-8-300x159.png 300w\" sizes=\"auto, (max-width: 633px) 100vw, 633px\" \/><figcaption>Text Driven Image Manipulation of StyleGAN Imagery<\/figcaption><\/figure>\n","protected":false},"excerpt":{"rendered":"<p>High-quality facial attributes editing results from InterFaceGAN. GAN Inversion GAN inversion aims to invert a given image back into the latent space of a pre-trained GAN model, for the image to be faithfully reconstructed from the inverted code by the generator. This allows us to manipulate the latent vectors to control facial attributes like age, &hellip; <\/p>\n<p class=\"link-more\"><a href=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/experiments\/\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;Interactive Face Editing in 2D&#8221;<\/span><\/a><\/p>\n","protected":false},"author":122,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-35","page","type-page","status-publish","hentry"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v28.1 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Interactive Face Editing in 2D -<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/experiments\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Interactive Face Editing in 2D -\" \/>\n<meta property=\"og:description\" content=\"High-quality facial attributes editing results from InterFaceGAN. GAN Inversion GAN inversion aims to invert a given image back into the latent space of a pre-trained GAN model, for the image to be faithfully reconstructed from the inverted code by the generator. This allows us to manipulate the latent vectors to control facial attributes like age, &hellip; Continue reading &quot;Interactive Face Editing in 2D&quot;\" \/>\n<meta property=\"og:url\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/experiments\/\" \/>\n<meta property=\"article:modified_time\" content=\"2022-05-02T05:04:04+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/lh5.googleusercontent.com\/L9DrTSNfbTcKZFaJqLkYQM9R9EhBVWkdpGKny5soRHDyHpqh2Vrk3l0IKap2oQQzL6u_wXgvcfdQWmdMk1js1ZNOU48FWx1VrZpIYcMRSFqf1vZl37IgTZsluuzMpvhgQmT4Ho7agAF2n48i2lRN\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"3 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team3\\\/experiments\\\/\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team3\\\/experiments\\\/\",\"name\":\"Interactive Face Editing in 2D -\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team3\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team3\\\/experiments\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team3\\\/experiments\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/lh5.googleusercontent.com\\\/L9DrTSNfbTcKZFaJqLkYQM9R9EhBVWkdpGKny5soRHDyHpqh2Vrk3l0IKap2oQQzL6u_wXgvcfdQWmdMk1js1ZNOU48FWx1VrZpIYcMRSFqf1vZl37IgTZsluuzMpvhgQmT4Ho7agAF2n48i2lRN\",\"datePublished\":\"2022-04-28T04:11:11+00:00\",\"dateModified\":\"2022-05-02T05:04:04+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team3\\\/experiments\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team3\\\/experiments\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team3\\\/experiments\\\/#primaryimage\",\"url\":\"https:\\\/\\\/lh5.googleusercontent.com\\\/L9DrTSNfbTcKZFaJqLkYQM9R9EhBVWkdpGKny5soRHDyHpqh2Vrk3l0IKap2oQQzL6u_wXgvcfdQWmdMk1js1ZNOU48FWx1VrZpIYcMRSFqf1vZl37IgTZsluuzMpvhgQmT4Ho7agAF2n48i2lRN\",\"contentUrl\":\"https:\\\/\\\/lh5.googleusercontent.com\\\/L9DrTSNfbTcKZFaJqLkYQM9R9EhBVWkdpGKny5soRHDyHpqh2Vrk3l0IKap2oQQzL6u_wXgvcfdQWmdMk1js1ZNOU48FWx1VrZpIYcMRSFqf1vZl37IgTZsluuzMpvhgQmT4Ho7agAF2n48i2lRN\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team3\\\/experiments\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team3\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Interactive Face Editing in 2D\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team3\\\/#website\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team3\\\/\",\"name\":\"\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team3\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Interactive Face Editing in 2D -","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/experiments\/","og_locale":"en_US","og_type":"article","og_title":"Interactive Face Editing in 2D -","og_description":"High-quality facial attributes editing results from InterFaceGAN. GAN Inversion GAN inversion aims to invert a given image back into the latent space of a pre-trained GAN model, for the image to be faithfully reconstructed from the inverted code by the generator. This allows us to manipulate the latent vectors to control facial attributes like age, &hellip; Continue reading \"Interactive Face Editing in 2D\"","og_url":"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/experiments\/","article_modified_time":"2022-05-02T05:04:04+00:00","og_image":[{"url":"https:\/\/lh5.googleusercontent.com\/L9DrTSNfbTcKZFaJqLkYQM9R9EhBVWkdpGKny5soRHDyHpqh2Vrk3l0IKap2oQQzL6u_wXgvcfdQWmdMk1js1ZNOU48FWx1VrZpIYcMRSFqf1vZl37IgTZsluuzMpvhgQmT4Ho7agAF2n48i2lRN","type":"","width":"","height":""}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/experiments\/","url":"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/experiments\/","name":"Interactive Face Editing in 2D -","isPartOf":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/#website"},"primaryImageOfPage":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/experiments\/#primaryimage"},"image":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/experiments\/#primaryimage"},"thumbnailUrl":"https:\/\/lh5.googleusercontent.com\/L9DrTSNfbTcKZFaJqLkYQM9R9EhBVWkdpGKny5soRHDyHpqh2Vrk3l0IKap2oQQzL6u_wXgvcfdQWmdMk1js1ZNOU48FWx1VrZpIYcMRSFqf1vZl37IgTZsluuzMpvhgQmT4Ho7agAF2n48i2lRN","datePublished":"2022-04-28T04:11:11+00:00","dateModified":"2022-05-02T05:04:04+00:00","breadcrumb":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/experiments\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/experiments\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/experiments\/#primaryimage","url":"https:\/\/lh5.googleusercontent.com\/L9DrTSNfbTcKZFaJqLkYQM9R9EhBVWkdpGKny5soRHDyHpqh2Vrk3l0IKap2oQQzL6u_wXgvcfdQWmdMk1js1ZNOU48FWx1VrZpIYcMRSFqf1vZl37IgTZsluuzMpvhgQmT4Ho7agAF2n48i2lRN","contentUrl":"https:\/\/lh5.googleusercontent.com\/L9DrTSNfbTcKZFaJqLkYQM9R9EhBVWkdpGKny5soRHDyHpqh2Vrk3l0IKap2oQQzL6u_wXgvcfdQWmdMk1js1ZNOU48FWx1VrZpIYcMRSFqf1vZl37IgTZsluuzMpvhgQmT4Ho7agAF2n48i2lRN"},{"@type":"BreadcrumbList","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/experiments\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/"},{"@type":"ListItem","position":2,"name":"Interactive Face Editing in 2D"}]},{"@type":"WebSite","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/#website","url":"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/","name":"","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"}]}},"_links":{"self":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/wp-json\/wp\/v2\/pages\/35","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/wp-json\/wp\/v2\/users\/122"}],"replies":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/wp-json\/wp\/v2\/comments?post=35"}],"version-history":[{"count":4,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/wp-json\/wp\/v2\/pages\/35\/revisions"}],"predecessor-version":[{"id":211,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/wp-json\/wp\/v2\/pages\/35\/revisions\/211"}],"wp:attachment":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2022team3\/wp-json\/wp\/v2\/media?parent=35"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}