{"id":85284,"date":"2020-06-14T19:42:01","date_gmt":"2020-06-14T17:42:01","guid":{"rendered":"https:\/\/prohoster.info\/blog\/novosti-interneta\/pifu-sistema-mashinnogo-obucheniya-dlya-postroeniya-3d-modeli-cheloveka-na-osnove-2d-snimkov"},"modified":"2020-06-14T19:42:01","modified_gmt":"2020-06-14T17:42:01","slug":"pifu-sistema-mashinnogo-obucheniya-dlya-postroeniya-3d-modeli-cheloveka-na-osnove-2d-snimkov","status":"publish","type":"post","link":"https:\/\/prohoster.info\/cs\/blog\/news\/pifu-sistema-mashinnogo-obucheniya-dlya-postroeniya-3d-modeli-cheloveka-na-osnove-2d-snimkov","title":{"rendered":"PIFu \u2014 syst\u00e9m strojov\u00e9ho u\u010den\u00ed pro vytvo\u0159en\u00ed 3D modelu \u010dlov\u011bka na z\u00e1klad\u011b 2D sn\u00edmk\u016f","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"

Skupina v\u00fdzkumn\u00edk\u016f z n\u011bkolika americk\u00fdch univerzit publikovala projekt PIFu<\/a><\/noindex> (Pixel-Aligned Implicit Function), kter\u00fd umo\u017e\u0148uje pou\u017e\u00edt metody strojov\u00e9ho u\u010den\u00ed k vytvo\u0159en\u00ed 3D modelu \u010dlov\u011bka z jednoho nebo n\u011bkolika dvourozm\u011brn\u00fdch obraz\u016f. Syst\u00e9m dok\u00e1\u017ee replikovat slo\u017eit\u00e9 varianty oble\u010den\u00ed, jako jsou plisovan\u00e9 sukn\u011b a boty na vysok\u00e9m podpatku, a r\u016fzn\u00e9 \u00fa\u010desy, p\u0159i\u010dem\u017e automaticky obnovuje texturu a tvar v oblastech, kter\u00e9 jsou p\u0159i vytv\u00e1\u0159en\u00ed 3D modelu neviditeln\u00e9. Pro zv\u00fd\u0161en\u00ed kvality a detailnosti v\u00fdsledn\u00e9ho 3D modelu lze pou\u017e\u00edt v\u00edce obr\u00e1zk\u016f z r\u016fzn\u00fdch \u00fahl\u016f. K\u00f3d projektu je naps\u00e1n v jazyce Python s vyu\u017eit\u00edm frameworku PyTorch a distribuov\u00e1no<\/a><\/noindex> je licencov\u00e1n pod MIT licenc\u00ed.<\/p>\n

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

jako zdroj pro rekonstrukci objemov\u00e9ho modelu se pou\u017e\u00edv\u00e1Neuronov\u00e1 s\u00ed\u0165, kter\u00e1 umo\u017e\u0148uje vyb\u00edrat nejpravd\u011bpodobn\u011bj\u0161\u00ed tvar a dovym\u00fd\u0161let skryt\u00e9 prvky na z\u00e1klad\u011b modelu \u0161kolen\u00e9ho na r\u016fzn\u00fdch variant\u00e1ch existuj\u00edc\u00edch objekt\u016f. Sou\u010dasn\u011b projekt poskytuje algoritmus pro p\u0159i\u0159azen\u00ed z\u00edskan\u00e9ho objemov\u00e9ho modelu k textur\u00e1m na poskytnut\u00fdch dvourozm\u011brn\u00fdch obraz\u00edch, kter\u00fd vyrovn\u00e1v\u00e1 pixely 2D obr\u00e1zku podle jejich polohy na 3D objektu a generuje nejpravd\u011bpodobn\u011bj\u0161\u00ed chyb\u011bj\u00edc\u00ed textury. Pro k\u00f3dov\u00e1n\u00ed obrazu lze pou\u017e\u00edt jakoukoliv konvolu\u010dn\u00ed neur\u00e1ln\u00ed s\u00ed\u0165<\/a><\/noindex>, pro
\nrekonstrukce povrchu byla pou\u017eita architektura «Stacked hourglass<\/a><\/noindex>«, a
\n pro p\u0159i\u0159azen\u00ed textur byla nasazena neur\u00e1ln\u00ed s\u00ed\u0165 zalo\u017een\u00e1 na architektu\u0159e CycleGAN<\/a><\/noindex>.<\/p>\n

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

Pou\u017eit\u00fd p\u0159ipraven\u00fd model v\u00fdzkumn\u00edk\u016f je k dispozici<\/a><\/noindex> je k dispozici pro voln\u00e9 sta\u017een\u00ed, ale zdrojov\u00e1 data, na kter\u00fdch bylo \u0161kolen\u00ed provedeno, z\u016fst\u00e1vaj\u00ed uzav\u0159en\u00e1, proto\u017ee jsou zalo\u017eena na v\u00fdsledc\u00edch komer\u010dn\u00edho 3D skenov\u00e1n\u00ed. Jako zdroj pro samostatn\u00e9 \u0161kolen\u00ed modelu m\u016f\u017ee b\u00fdt pou\u017eita datab\u00e1ze 3D model\u016f<\/a><\/noindex> lid\u00ed od projektu Renderpeople.<\/p>\n

\r\n \"P\u0159ehr\u00e1t\r\n
<\/div>\r\n <\/div><\/center><\/p>\n

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

Zdroj: opennet.ru<\/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 \u043d\u0435\u0441\u043a\u043e\u043b\u044c\u043a\u0438\u0445 \u0430\u043c\u0435\u0440\u0438\u043a\u0430\u043d\u0441\u043a\u0438\u0445 \u0443\u043d\u0438\u0432\u0435\u0440\u0441\u0438\u0442\u0435\u0442\u043e\u0432 \u043e\u043f\u0443\u0431\u043b\u0438\u043a\u043e\u0432\u0430\u043b\u0430 \u043f\u0440\u043e\u0435\u043a\u0442 PIFu (Pixel-Aligned Implicit Function), \u043f\u043e\u0437\u0432\u043e\u043b\u044f\u044e\u0449\u0438\u0439 \u043f\u0440\u0438\u043c\u0435\u043d\u0438\u0442\u044c \u043c\u0435\u0442\u043e\u0434\u044b \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u0434\u043b\u044f \u043f\u043e\u0441\u0442\u0440\u043e\u0435\u043d\u0438\u044f 3D-\u043c\u043e\u0434\u0435\u043b\u0438 \u0447\u0435\u043b\u043e\u0432\u0435\u043a\u0430 \u043f\u043e \u043e\u0434\u043d\u043e\u043c\u0443 \u0438\u043b\u0438 \u043d\u0435\u0441\u043a\u043e\u043b\u044c\u043a\u0438\u043c \u0434\u0432\u0443\u043c\u0435\u0440\u043d\u044b\u043c \u0438\u0437\u043e\u0431\u0440\u0430\u0436\u0435\u043d\u0438\u044f\u043c. \u0421\u0438\u0441\u0442\u0435\u043c\u0430 \u043f\u043e\u0437\u0432\u043e\u043b\u044f\u0435\u0442 \u0432\u043e\u0441\u0441\u043e\u0437\u0434\u0430\u0432\u0430\u0442\u044c \u0441\u043b\u043e\u0436\u043d\u044b\u0435 \u0432\u0430\u0440\u0438\u0430\u043d\u0442\u044b \u043e\u0434\u0435\u0436\u0434\u044b, \u0442\u0430\u043a\u0438\u0435 \u043a\u0430\u043a \u044e\u0431\u043a\u0438 \u0441\u043e \u0441\u043a\u043b\u0430\u0434\u043a\u0430\u043c\u0438 \u0438 \u0442\u0443\u0444\u043b\u0438 \u043d\u0430 \u043a\u0430\u0431\u043b\u0443\u043a\u0430\u0445, \u0438 \u0440\u0430\u0437\u043b\u0438\u0447\u043d\u044b\u0435 \u043f\u0440\u0438\u0447\u0451\u0441\u043a\u0438, \u0441\u0430\u043c\u043e\u0441\u0442\u043e\u044f\u0442\u0435\u043b\u044c\u043d\u043e \u0432\u043e\u0441\u0441\u0442\u0430\u043d\u0430\u0432\u043b\u0438\u0432\u0430\u044f \u0442\u0435\u043a\u0441\u0442\u0443\u0440\u0443 \u0438 \u0444\u043e\u0440\u043c\u0443 \u0432 \u043e\u0431\u043b\u0430\u0441\u0442\u044f\u0445, \u043d\u0435\u0432\u0438\u0434\u0438\u043c\u044b\u0445 \u0432 \u043f\u0440\u043e\u0435\u043a\u0446\u0438\u0438, […]<\/p>\n","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"author":1,"featured_media":85285,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[702],"tags":[],"class_list":["post-85284","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\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\udd47PIFu \u2014 syst\u00e9m strojov\u00e9ho u\u010den\u00ed pro vytv\u00e1\u0159en\u00ed 3D modelu \u010dlov\u011bka na z\u00e1klad\u011b 2D sn\u00edmk\u016f | ProHoster","description":"Skupina v\u00fdzkumn\u00edk\u016f z n\u011bkolika americk\u00fdch univerzit publikovala projekt PIFu (Pixel-Aligned Implicit Function).","canonical_url":"https:\/\/prohoster.info\/cs\/blog\/news\/pifu-sistema-mashinnogo-obucheniya-dlya-postroeniya-3d-modeli-cheloveka-na-osnove-2d-snimkov","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":null,"og:locale":"cs_CZ","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\udd47PIFu \u2014 \u0441\u0438\u0441\u0442\u0435\u043c\u0430 \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u0434\u043b\u044f \u043f\u043e\u0441\u0442\u0440\u043e\u0435\u043d\u0438\u044f 3D-\u043c\u043e\u0434\u0435\u043b\u0438 \u0447\u0435\u043b\u043e\u0432\u0435\u043a\u0430 \u043d\u0430 \u043e\u0441\u043d\u043e\u0432\u0435 2D-\u0441\u043d\u0438\u043c\u043a\u043e\u0432 | 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 \u043d\u0435\u0441\u043a\u043e\u043b\u044c\u043a\u0438\u0445 \u0430\u043c\u0435\u0440\u0438\u043a\u0430\u043d\u0441\u043a\u0438\u0445 \u0443\u043d\u0438\u0432\u0435\u0440\u0441\u0438\u0442\u0435\u0442\u043e\u0432 \u043e\u043f\u0443\u0431\u043b\u0438\u043a\u043e\u0432\u0430\u043b\u0430 \u043f\u0440\u043e\u0435\u043a\u0442 PIFu (Pixel-Aligned Implicit Function).","og:url":"https:\/\/prohoster.info\/cs\/blog\/news\/pifu-sistema-mashinnogo-obucheniya-dlya-postroeniya-3d-modeli-cheloveka-na-osnove-2d-snimkov","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":"2020-06-14T17:42:01+00:00","article:modified_time":"2020-06-14T17:42:01+00:00","article:publisher":"https:\/\/www.facebook.com\/prohoster","article:author":"https:\/\/www.facebook.com\/prohoster"},"aioseo_meta_data":{"post_id":"85284","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":null,"breadcrumb_settings":null,"limit_modified_date":false,"reviewed_by":null,"ai":null,"created":"2021-02-28 10:35:23","updated":"2022-09-28 11:59:14","focus_keyword":null,"additional_keywords":null,"truseo_locale":null},"gt_translate_keys":[{"key":"link","format":"url"}],"_links":{"self":[{"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/posts\/85284","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/comments?post=85284"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/posts\/85284\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/media\/85285"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/media?parent=85284"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/categories?post=85284"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/tags?post=85284"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}