{"id":38674,"date":"2019-10-31T22:25:15","date_gmt":"2019-10-31T19:25:15","guid":{"rendered":"https:\/\/prohoster.info\/blog\/otkryt-kod-dlya-sinteza-animatsii-s-pomoshhyu-nejrosetej\/"},"modified":"2019-10-31T22:25:15","modified_gmt":"2019-10-31T19:25:15","slug":"otkryt-kod-dlya-sinteza-animatsii-s-pomoshhyu-nejrosetej","status":"publish","type":"post","link":"https:\/\/prohoster.info\/ro\/blog\/news\/otkryt-kod-dlya-sinteza-animatsii-s-pomoshhyu-nejrosetej","title":{"rendered":"Codul pentru sinteza anima\u021biilor prin re\u021bele neuronale a fost deschis","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"

Un grup de cercet\u0103tori de la Universitatea Tehnic\u0103 din Shanghai a publicat<\/a><\/noindex> un instrumentar Impersonator<\/a><\/noindex>, care permite, folosind metode de \u00eenv\u0103\u021bare automat\u0103, simularea mi\u0219c\u0103rilor umane pe imagini statice, precum \u0219i schimbarea hainelor, mutarea \u00een alte medii \u0219i schimbarea unghiului din care obiectul este vizibil. Codul este scris \u00een limbajul Python
\nprin utilizarea framework-ului PyTorch<\/a><\/noindex>. De asemenea, este necesar torchvision<\/a><\/noindex> \u0219i CUDA Toolkit. <\/p>\n

\"Codul<\/center><\/p>\n

Instrumentul prime\u0219te ca input o imagine bidimensional\u0103 \u0219i sintetizeaz\u0103 un rezultat modificat pe baza modelului selectat. Sunt sus\u021binute trei tipuri de transform\u0103ri:
\nCrearea unui obiect \u00een mi\u0219care, care repet\u0103 mi\u0219c\u0103rile pe care modelul a fost antrenat. Transferul elementelor de aspect din model \u00een obiect (de exemplu, schimbarea hainelor). Generarea unei noi perspective (de exemplu, sinteza unei imagini de profil pe baza unei fotografii din fa\u021b\u0103). Toate cele trei metode pot fi combinate; de exemplu, se poate genera un videoclip dintr-o fotografie, imit\u00e2nd execu\u021bia unei acroba\u021bii complexe \u00een alte haine. <\/p>\n

\r\n \"Reda\u021bi\r\n
<\/div>\r\n <\/div><\/center><\/p>\n

\u00cen procesul de sintez\u0103, se realizeaz\u0103 \u00een paralel opera\u021bii de extragere a obiectului din fotografie \u0219i formarea elementelor lips\u0103 din fundal atunci c\u00e2nd acesta se mut\u0103. Modelul pentru re\u021beaua neural\u0103 poate fi antrenat o singur\u0103 dat\u0103 \u0219i utilizat pentru diverse transform\u0103ri. Pentru desc\u0103rcarea sunt disponibile<\/a><\/noindex> modelurilor preg\u0103tite, care permit utilizarea imediat\u0103 a instrumentului f\u0103r\u0103 a necesita antrenamente prealabile. Este necesar un GPU cu o dimensiune a memoriei de cel pu\u021bin 8GB.<\/p>\n

Spre deosebire de metodele de transformare bazate pe transformarea prin puncte cheie, care descriu pozi\u021bia corpului \u00een spa\u021biul bidimensional, Impersonator face o \u00eencercare de sintez\u0103 a unei re\u021bele 3D (mesh) cu o descriere a corpului, folosind metode de \u00eenv\u0103\u021bare automat\u0103.
\nMetoda propus\u0103 permite manevrarea cu luarea \u00een considerare a formei personalizate a corpului \u0219i a pozi\u021biei actuale, model\u00e2nd mi\u0219c\u0103rile naturale ale membrelor. <\/p>\n

\"Codul<\/a><\/noindex><\/center><\/p>\n

Pentru a p\u0103stra informa\u021biile originale, cum ar fi texturile, stilul, culorile \u0219i recunoa\u0219terea fe\u021bei, \u00een procesul de transformare se aplic\u0103 o re\u021bea neural\u0103 generativ\u0103 adversarial\u0103<\/a><\/noindex> (Liquid Warping GAN<\/a><\/noindex>). Informa\u021biile despre obiectul original \u0219i parametrii pentru identificarea sa precis\u0103 sunt extrase prin aplicarea unei re\u021bele neuronale convolu\u021bionale<\/a><\/noindex>.<\/p>\n

\r\n \"Reda\u021bi\r\n
<\/div>\r\n <\/div>
\n<\/center><\/p>\n

<\/a><\/noindex><\/p>\n

Sursa: opennet.ro<\/a><\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"

\u0413\u0440\u0443\u043f\u043f\u0430 \u0438\u0441\u0441\u043b\u0435\u0434\u043e\u0432\u0430\u0442\u0435\u043b\u0435\u0439 \u0438\u0437 \u0448\u0430\u043d\u0445\u0430\u0439\u0441\u043a\u043e\u0433\u043e \u0442\u0435\u0445\u043d\u0438\u0447\u0435\u0441\u043a\u043e\u0433\u043e \u0443\u043d\u0438\u0432\u0435\u0440\u0441\u0438\u0442\u0435\u0442\u0430 \u043e\u043f\u0443\u0431\u043b\u0438\u043a\u043e\u0432\u0430\u043b\u0430 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0430\u0440\u0438\u0439 Impersonator, \u043f\u043e\u0437\u0432\u043e\u043b\u044f\u044e\u0449\u0438\u0439 \u043f\u0440\u0438 \u043f\u043e\u043c\u043e\u0449\u0438 \u043c\u0435\u0442\u043e\u0434\u043e\u0432 \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u0441\u0438\u043c\u0443\u043b\u0438\u0440\u043e\u0432\u0430\u0442\u044c \u0434\u0432\u0438\u0436\u0435\u043d\u0438\u044f \u043b\u044e\u0434\u0435\u0439 \u043f\u043e \u0441\u0442\u0430\u0442\u0438\u0447\u0435\u0441\u043a\u0438\u043c \u0438\u0437\u043e\u0431\u0440\u0430\u0436\u0435\u043d\u0438\u044f\u043c, \u0430 \u0442\u0430\u043a\u0436\u0435 \u0437\u0430\u043c\u0435\u043d\u044f\u0442\u044c \u043e\u0434\u0435\u0436\u0434\u0443, \u043f\u0435\u0440\u0435\u043d\u043e\u0441\u0438\u0442\u044c \u0432 \u0434\u0440\u0443\u0433\u043e\u0435 \u043e\u043a\u0440\u0443\u0436\u0435\u043d\u0438\u0435 \u0438 \u043c\u0435\u043d\u044f\u0442\u044c \u0440\u0430\u043a\u0443\u0440\u0441 \u0441 \u043a\u043e\u0442\u043e\u0440\u043e\u0433\u043e \u0432\u0438\u0434\u0435\u043d \u043e\u0431\u044a\u0435\u043a\u0442. \u041a\u043e\u0434 \u043d\u0430\u043f\u0438\u0441\u0430\u043d \u043d\u0430 \u044f\u0437\u044b\u043a\u0435 Python \u0441 \u043f\u0440\u0438\u043c\u0435\u043d\u0435\u043d\u0438\u0435\u043c \u0444\u0440\u0435\u0439\u043c\u0432\u043e\u0440\u043a\u0430 PyTorch. \u0414\u043b\u044f \u0441\u0431\u043e\u0440\u043a\u0438 \u0442\u0430\u043a\u0436\u0435 \u0442\u0440\u0435\u0431\u0443\u0435\u0442\u0441\u044f torchvision \u0438 CUDA Toolkit. \u0418\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0430\u0440\u0438\u0439 \u043f\u043e\u043b\u0443\u0447\u0430\u0435\u0442 […]<\/p>\n","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"author":1,"featured_media":29010,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[702],"tags":[],"class_list":["post-38674","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news"],"aioseo_notices":[],"aioseo_head":"\n\t\t\n\t\n\t\n\t\n\t\n\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\n","aioseo_head_json":{"title":"\ud83e\udd47Cod deschis pentru sinteza anima\u021biei cu ajutorul re\u021belelor neuronale | ProHoster","description":"Un grup de cercet\u0103tori de la Universitatea Tehnic\u0103 din Shanghai a publicat un instrument de lucru","canonical_url":"https:\/\/prohoster.info\/ro\/blog\/news\/otkryt-kod-dlya-sinteza-animatsii-s-pomoshhyu-nejrosetej","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":null,"og:locale":"ro_RO","og:site_name":"ProHoster | \u041a\u0443\u043f\u0438\u0442\u044c \u043d\u0430\u0434\u0435\u0436\u043d\u044b\u0439 \u0445\u043e\u0441\u0442\u0438\u043d\u0433 \u0434\u043b\u044f \u0441\u0430\u0439\u0442\u043e\u0432 \u0441 \u0437\u0430\u0449\u0438\u0442\u043e\u0439 \u043e\u0442 DDoS, VPS VDS \u0441\u0435\u0440\u0432\u0435\u0440\u044b","og:type":"article","og:title":"\ud83e\udd47\u041e\u0442\u043a\u0440\u044b\u0442 \u043a\u043e\u0434 \u0434\u043b\u044f \u0441\u0438\u043d\u0442\u0435\u0437\u0430 \u0430\u043d\u0438\u043c\u0430\u0446\u0438\u0438 \u0441 \u043f\u043e\u043c\u043e\u0449\u044c\u044e \u043d\u0435\u0439\u0440\u043e\u0441\u0435\u0442\u0435\u0439 | ProHoster","og:description":"\u0413\u0440\u0443\u043f\u043f\u0430 \u0438\u0441\u0441\u043b\u0435\u0434\u043e\u0432\u0430\u0442\u0435\u043b\u0435\u0439 \u0438\u0437 \u0448\u0430\u043d\u0445\u0430\u0439\u0441\u043a\u043e\u0433\u043e \u0442\u0435\u0445\u043d\u0438\u0447\u0435\u0441\u043a\u043e\u0433\u043e \u0443\u043d\u0438\u0432\u0435\u0440\u0441\u0438\u0442\u0435\u0442\u0430 \u043e\u043f\u0443\u0431\u043b\u0438\u043a\u043e\u0432\u0430\u043b\u0430 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0430\u0440\u0438\u0439","og:url":"https:\/\/prohoster.info\/ro\/blog\/news\/otkryt-kod-dlya-sinteza-animatsii-s-pomoshhyu-nejrosetej","og:image":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:secure_url":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:width":350,"og:image:height":350,"article:published_time":"2019-10-31T19:25:15+00:00","article:modified_time":"2019-10-31T19:25:15+00:00","article:publisher":"https:\/\/www.facebook.com\/prohoster","article:author":"https:\/\/www.facebook.com\/prohoster"},"aioseo_meta_data":{"post_id":"38674","title":null,"description":null,"keywords":null,"keyphrases":null,"primary_term":null,"canonical_url":null,"og_title":null,"og_description":null,"og_object_type":"default","og_image_type":"default","og_image_url":null,"og_image_width":null,"og_image_height":null,"og_image_custom_url":null,"og_image_custom_fields":null,"og_video":null,"og_custom_url":null,"og_article_section":null,"og_article_tags":null,"twitter_use_og":false,"twitter_card":"default","twitter_image_type":"default","twitter_image_url":null,"twitter_image_custom_url":null,"twitter_image_custom_fields":null,"twitter_title":null,"twitter_description":null,"schema":{"blockGraphs":[],"customGraphs":[],"default":{"data":{"Article":[],"Course":[],"Dataset":[],"FAQPage":[],"Movie":[],"Person":[],"Product":[],"ProductReview":[],"Car":[],"Recipe":[],"Service":[],"SoftwareApplication":[],"WebPage":[]},"graphName":"","isEnabled":true},"graphs":[]},"schema_type":null,"schema_type_options":null,"pillar_content":false,"robots_default":true,"robots_noindex":false,"robots_noarchive":false,"robots_nosnippet":false,"robots_nofollow":false,"robots_noimageindex":false,"robots_noodp":false,"robots_notranslate":false,"robots_max_snippet":null,"robots_max_videopreview":null,"robots_max_imagepreview":"large","priority":null,"frequency":null,"local_seo":null,"seo_analyzer_scan_date":"2026-01-23 22:59:19","breadcrumb_settings":null,"limit_modified_date":false,"reviewed_by":null,"ai":null,"created":"2021-02-28 22:16:09","updated":"2026-01-23 22:59:19","focus_keyword":null,"additional_keywords":null,"truseo_locale":null},"gt_translate_keys":[{"key":"link","format":"url"}],"_links":{"self":[{"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/posts\/38674","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/comments?post=38674"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/posts\/38674\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/media\/29010"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/media?parent=38674"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/categories?post=38674"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/tags?post=38674"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}