{"id":5892,"date":"2024-12-19T05:51:00","date_gmt":"2024-12-18T20:51:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=5892"},"modified":"2024-12-19T05:51:00","modified_gmt":"2024-12-18T20:51:00","slug":"simvs-simulating-world-inconsistencies-for-robust-view-synthesis","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=5892","title":{"rendered":"SimVS: Simulating World Inconsistencies for Robust View Synthesis\u00a0"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>SimVS: Simulating World Inconsistencies for Robust View Synthesis\u00a0<\/strong>[102.8]<br>\u672c\u7a3f\u3067\u306f\u3001\u751f\u6210\u30d3\u30c7\u30aa\u30e2\u30c7\u30eb\u3092\u5229\u7528\u3057\u3066\u3001\u30ad\u30e3\u30d7\u30c1\u30e3\u4e2d\u306b\u8d77\u3053\u308a\u3046\u308b\u4e16\u754c\u306e\u4e0d\u6574\u5408\u3092\u30b7\u30df\u30e5\u30ec\u30fc\u30c8\u3059\u308b\u624b\u6cd5\u3092\u63d0\u6848\u3059\u308b\u3002 \u6211\u3005\u306e\u4e16\u754c\u30b7\u30df\u30e5\u30ec\u30fc\u30b7\u30e7\u30f3\u6226\u7565\u306f\u3001\u73fe\u5b9f\u306e\u30b7\u30fc\u30f3\u306e\u30d0\u30ea\u30a8\u30fc\u30b7\u30e7\u30f3\u3092\u6271\u3046\u4e0a\u3067\u3001\u5f93\u6765\u306e\u62e1\u5f35\u624b\u6cd5\u3088\u308a\u3082\u5927\u5e45\u306b\u512a\u308c\u3066\u3044\u308b\u3053\u3068\u3092\u5b9f\u8a3c\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2412.07696v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2412.07696v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Tue, 10 Dec 2024 17:35:12 GMT)<\/li>\n\n\n\n<li>\u300cOur approach augments existing multiview datasets with inconsistencies simulated by a video diffusion model and trains a multiview harmonization model to sample sets of consistent views of a scene conditioned on sparse inconsistent captures. We can then use existing 3D reconstruction and view synthesis techniques to synthesize novel viewpoints from these consistent images.\u300d\u3068\u306e\u3053\u3068\u3002\u9762\u767d\u3044\u30c7\u30fc\u30bf\u62e1\u5f35\u306e\u30a2\u30d7\u30ed\u30fc\u30c1\u3067\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u30b5\u30a4\u30c8\u3092\u898b\u308b\u306b\u52b9\u679c\u3082\u9ad8\u3044\u3088\u3046\u3002<\/li>\n\n\n\n<li>\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u30b5\u30a4\u30c8\u306f<a href=\"https:\/\/alextrevithick.github.io\/simvs\/\">SimVS: Simulating World Inconsistencies for Robust View Synthesis<\/a><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[92,449,554],"class_list":["post-5892","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-data-augmentation","tag-world-model","tag-554"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5892","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=5892"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5892\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5892"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5892"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5892"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}