{"id":65160,"date":"2022-08-01T12:28:30","date_gmt":"2022-08-01T09:28:30","guid":{"rendered":"https:\/\/forklog.com\/en\/?p=65160"},"modified":"2025-09-06T18:26:43","modified_gmt":"2025-09-06T15:26:43","slug":"tencent-trains-ai-to-restore-old-photographs","status":"publish","type":"post","link":"https:\/\/forklog.com\/en\/tencent-trains-ai-to-restore-old-photographs\/","title":{"rendered":"Tencent trains AI to restore old photographs"},"content":{"rendered":"<p>Researchers from Tencent have developed the GFP-GAN algorithm that restores damaged photos and low-resolution portraits. As reported by <a href=\"https:\/\/petapixel.com\/2022\/07\/28\/gfpgan-is-a-new-free-ai-tool-that-can-fix-most-old-photos-instantly\/\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">PetaPixel<\/a>.<\/p>\n<figure class=\"wp-block-image size-full is-style-default\"><img loading=\"lazy\" decoding=\"async\" width=\"675\" height=\"380\" src=\"https:\/\/forklog.com\/wp-content\/uploads\/3750ddf0-0f6a-11ed-b164-ac38016725f8.png\" alt=\"Tencent teaches AI to restore old photographs\" class=\"wp-image-180487\" srcset=\"https:\/\/forklog.com\/wp-content\/uploads\/3750ddf0-0f6a-11ed-b164-ac38016725f8.png 675w, https:\/\/forklog.com\/wp-content\/uploads\/3750ddf0-0f6a-11ed-b164-ac38016725f8-300x169.png 300w\" sizes=\"auto, (max-width: 675px) 100vw, 675px\" \/><figcaption>A photograph restored with GFP-GAN. Source: YouTube channel <a href=\"https:\/\/www.youtube.com\/watch?v=nLDVtzcSeqM\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">What\u2019s AI<\/a>.<\/figcaption><\/figure>\n<p>The technology combines information from two AI models to fill in missing details of photographs in a few seconds, preserving high accuracy and quality.<\/p>\n<p>According to the scientists, conventional methods for restoring images require meticulous tuning of the existing AI model by measuring differences between generated and real images. This often leads to low-quality results, they added.<\/p>\n<p>The new approach uses a pre-trained version of Nvidia&#8217;s StyleGAN-2 algorithm to inform the group&#8217;s own model at several stages of the image creation process. This helps preserve the &#8216;identity&#8217; of people in the photograph, with particular emphasis on facial features such as the eyes and mouth.<\/p>\n<figure class=\"wp-block-embed is-type-video is-provider-youtube wp-block-embed-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\">\n<div class=\"wp-block-embed__wrapper\">\n<iframe loading=\"lazy\" title=\"Impressive AI Restoration of Pictures!\" width=\"500\" height=\"281\" src=\"https:\/\/www.youtube.com\/embed\/nLDVtzcSeqM?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" allowfullscreen><\/iframe>\n<\/div>\n<\/figure>\n<p>The GFP-GAN demo <a href=\"https:\/\/app.baseten.co\/apps\/QPp4nPE\/operator_views\/RqgOnqV\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">is free<\/a>. Researchers also published the <a href=\"https:\/\/github.com\/TencentARC\/GFPGAN\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">source code<\/a> of the model, enabling any developer to implement restoration technology in their projects.<\/p>\n<p>However, the creators of GFP-GAN warned that the algorithm may distort some facial details and output the result at a lower resolution.<\/p>\n<p>In June, Adobe unveiled a tool for restoring old photographs in Photoshop.<\/p>\n<p>In October 2021, the Israeli startup D-ID developed a tool that makes people on portraits speak.<\/p>\n<p>In April, Deep Nostalgia <a href=\"https:\/\/forklog.com\/en\/news\/deep-nostalgia-lets-live-photos-dance-and-send-an-air-kiss\">taught &#8216;live&#8217; photos<\/a> to dance and send a virtual kiss.<\/p>\n<p>Subscribe to ForkLog&#8217;s news on Telegram: <a href=\"https:\/\/t.me\/forklogAI\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">ForkLog AI<\/a> \u2014 all the news from the world of AI!<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Researchers from Tencent have developed the GFP-GAN algorithm that restores damaged photos and low-resolution portraits.<\/p>\n","protected":false},"author":1,"featured_media":26216,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"select":"1","news_style_id":"1","cryptorium_level":"","_short_excerpt_text":"","creation_source":"","_metatest_mainpost_news_update":false,"footnotes":""},"categories":[3],"tags":[438,1771],"class_list":["post-65160","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news-and-analysis","tag-artificial-intelligence","tag-tencent"],"aioseo_notices":[],"amp_enabled":true,"views":"47","promo_type":"1","layout_type":"1","short_excerpt":"","is_update":"","_links":{"self":[{"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/posts\/65160","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/comments?post=65160"}],"version-history":[{"count":1,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/posts\/65160\/revisions"}],"predecessor-version":[{"id":65161,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/posts\/65160\/revisions\/65161"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/media\/26216"}],"wp:attachment":[{"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/media?parent=65160"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/categories?post=65160"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/tags?post=65160"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}