{"id":13186,"date":"2024-06-15T09:09:51","date_gmt":"2024-06-15T01:09:51","guid":{"rendered":"https:\/\/www.1ai.net\/?p=13186"},"modified":"2024-06-15T09:09:51","modified_gmt":"2024-06-15T01:09:51","slug":"%e6%9b%b4%e5%bf%ab%e6%9b%b4%e5%87%86%e7%a1%ae%ef%bc%81%e5%ad%97%e8%8a%82%e8%b7%b3%e5%8a%a8%e5%8f%91%e5%b8%83%e6%96%b0%e4%b8%80%e4%bb%a3depth-anything-v2%e6%b7%b1%e5%ba%a6%e6%a8%a1%e5%9e%8b","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/13186.html","title":{"rendered":"Faster and more accurate! ByteDance releases a new generation of Depth Anything V2 depth model"},"content":{"rendered":"<p><a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%ad%97%e8%8a%82%e8%b7%b3%e5%8a%a8\" title=\"\u3010\u67e5\u770b\u542b\u6709[\u5b57\u8282\u8df3\u52a8]\u6807\u7b7e\u7684\u6587\u7ae0\u3011\" target=\"_blank\" rel=\"noopener\">\u5b57\u8282\u8df3\u52a8<\/a>\u53d1\u5e03\u4e86\u65b0\u4e00\u4ee3\u7684Depth Anything V2<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e6%b7%b1%e5%ba%a6%e6%a8%a1%e5%9e%8b\" title=\"\u3010\u67e5\u770b\u542b\u6709[\u6df1\u5ea6\u6a21\u578b]\u6807\u7b7e\u7684\u6587\u7ae0\u3011\" target=\"_blank\" rel=\"noopener\">\u6df1\u5ea6\u6a21\u578b<\/a>\uff0c\u8be5\u6a21\u578b\u5728\u5355\u773c\u6df1\u5ea6\u4f30\u8ba1\u9886\u57df\u5b9e\u73b0\u4e86\u663e\u8457\u7684\u6027\u80fd\u63d0\u5347\u3002\u4e0e\u524d\u4e00\u4ee3Depth Anything V1\u76f8\u6bd4\uff0cV2\u7248\u672c\u5177\u6709\u66f4\u7cbe\u7ec6\u7684\u7ec6\u8282\u548c\u66f4\u5f3a\u7684\u9c81\u68d2\u6027\uff0c\u540c\u65f6\u5728\u6548\u7387\u4e0a\u4e5f\u6709\u4e86\u663e\u8457\u63d0\u9ad8\uff0c\u6bd4\u57fa\u4e8eStable Diffusion\u7684\u6a21\u578b\u5feb\u4e8610\u500d\u4ee5\u4e0a\u3002<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-13187\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/06\/6385397096400297274399482.jpg\" alt=\"\" width=\"1154\" height=\"876\" \/><\/p>\n<p><strong>\u5173\u952e\u7279\u70b9:<\/strong><\/p>\n<p>\u66f4\u7cbe\u7ec6\u7684\u7ec6\u8282:V2\u6a21\u578b\u5728\u7ec6\u8282\u4e0a\u8fdb\u884c\u4e86\u4f18\u5316\uff0c\u63d0\u4f9b\u4e86\u66f4\u7cbe\u7ec6\u7684\u6df1\u5ea6\u9884\u6d4b\u3002<\/p>\n<p>\u9ad8\u6548\u7387\u4e0e\u51c6\u786e\u6027:\u4e0e\u57fa\u4e8eSD\u6784\u5efa\u7684\u6a21\u578b\u76f8\u6bd4\uff0cV2\u5728\u6548\u7387\u548c\u51c6\u786e\u6027\u4e0a\u90fd\u6709\u663e\u8457\u63d0\u5347\u3002<\/p>\n<p>\u591a\u89c4\u6a21\u6a21\u578b\u652f\u6301:\u63d0\u4f9b\u4e86\u4e0d\u540c\u89c4\u6a21\u7684\u6a21\u578b\uff0c\u53c2\u6570\u4ece25M\u52301.3B\u4e0d\u7b49\uff0c\u4ee5\u9002\u5e94\u4e0d\u540c\u7684\u5e94\u7528\u573a\u666f\u3002<\/p>\n<p>\u5173\u952e\u5b9e\u8df5:\u901a\u8fc7\u4f7f\u7528\u5408\u6210\u56fe\u50cf\u66ff\u6362\u771f\u5b9e\u56fe\u50cf\u3001\u6269\u5927\u6559\u5e08\u6a21\u578b\u5bb9\u91cf\u3001\u5229\u7528\u5927\u89c4\u6a21\u4f2a\u6807\u6ce8\u56fe\u50cf\u6559\u6388\u5b66\u751f\u6a21\u578b\u7b49\u65b9\u6cd5\uff0c\u63d0\u9ad8\u4e86\u6a21\u578b\u7684\u6027\u80fd\u3002<\/p>\n<p><strong>\u63d0\u5347\u6a21\u578b\u6027\u80fd\u7684\u4e09\u4e2a\u5173\u952e\u5b9e\u8df5:<\/strong><\/p>\n<p>\u5408\u6210\u56fe\u50cf\u7684\u4f7f\u7528:\u7528\u5408\u6210\u56fe\u50cf\u53d6\u4ee3\u4e86\u6240\u6709\u6807\u6ce8\u7684\u771f\u5b9e\u56fe\u50cf\uff0c\u63d0\u9ad8\u4e86\u6a21\u578b\u7684\u8bad\u7ec3\u6548\u7387\u3002<\/p>\n<p>\u6559\u5e08\u6a21\u578b\u5bb9\u91cf\u6269\u5927:\u901a\u8fc7\u6269\u5927\u6559\u5e08\u6a21\u578b\u7684\u5bb9\u91cf\uff0c\u589e\u5f3a\u4e86\u6a21\u578b\u7684\u6cdb\u5316\u80fd\u529b\u3002<\/p>\n<p>\u4f2a\u6807\u6ce8\u56fe\u50cf\u7684\u5e94\u7528:\u4f7f\u7528\u5927\u89c4\u6a21\u4f2a\u6807\u6ce8\u7684\u771f\u5b9e\u56fe\u50cf\u4f5c\u4e3a\u6865\u6881\uff0c\u6559\u6388\u5b66\u751f\u6a21\u578b\uff0c\u63d0\u9ad8\u4e86\u6a21\u578b\u7684\u9c81\u68d2\u6027\u3002<\/p>\n<p>\u5e7f\u6cdb\u5e94\u7528\u573a\u666f\u7684\u652f\u6301:<\/p>\n<p>\u4e3a\u4e86\u6ee1\u8db3\u5e7f\u6cdb\u7684\u5e94\u7528\u9700\u6c42\uff0c\u7814\u7a76\u4eba\u5458\u63d0\u4f9b\u4e86\u4e0d\u540c\u89c4\u6a21\u7684\u6a21\u578b\uff0c\u5e76\u5229\u7528\u5176\u6cdb\u5316\u80fd\u529b\uff0c\u901a\u8fc7\u5ea6\u91cf\u6df1\u5ea6\u6807\u7b7e\u8fdb\u884c\u5fae\u8c03\u3002<\/p>\n<p>\u6784\u5efa\u4e86\u4e00\u4e2a\u591a\u6837\u5316\u7684\u8bc4\u4f30\u57fa\u51c6\uff0c\u5305\u542b\u7a00\u758f\u6df1\u5ea6\u6ce8\u91ca\uff0c\u4ee5\u4fc3\u8fdb\u672a\u6765\u7814\u7a76\u3002<\/p>\n<p>\u57fa\u4e8e\u5408\u6210\u4e0e\u771f\u5b9e\u56fe\u50cf\u7684\u8bad\u7ec3\u65b9\u6cd5:<\/p>\n<p>\u7814\u7a76\u4eba\u5458\u9996\u5148\u5728\u5408\u6210\u56fe\u50cf\u4e0a\u8bad\u7ec3\u4e86\u6700\u5927\u7684\u6559\u5e08\u6a21\u578b\uff0c\u7136\u540e\u4e3a\u5927\u89c4\u6a21\u672a\u6807\u6ce8\u7684\u771f\u5b9e\u56fe\u50cf\u751f\u6210\u4e86\u9ad8\u8d28\u91cf\u7684\u4f2a\u6807\u7b7e\uff0c\u5e76\u5728\u8fd9\u4e9b\u4f2a\u6807\u8bb0\u7684\u771f\u5b9e\u56fe\u50cf\u4e0a\u8bad\u7ec3\u4e86\u5b66\u751f\u6a21\u578b\u3002<\/p>\n<p>\u8bad\u7ec3\u8fc7\u7a0b\u4f7f\u7528\u4e86595K\u5408\u6210\u56fe\u50cf\u548c62M+\u771f\u5b9e\u4f2a\u6807\u8bb0\u56fe\u50cf\u3002<\/p>\n<p>Depth Anything V2\u6a21\u578b\u7684\u63a8\u51fa\uff0c\u5c55\u793a\u4e86\u5b57\u8282\u8df3\u52a8\u5728\u6df1\u5ea6\u5b66\u4e60\u6280\u672f\u9886\u57df\u7684\u521b\u65b0\u80fd\u529b\uff0c\u5176\u9ad8\u6548\u548c\u51c6\u786e\u7684\u6027\u80fd\u7279\u70b9\u9884\u793a\u7740\u8be5\u6a21\u578b\u5728\u8ba1\u7b97\u673a\u89c6\u89c9\u9886\u57df\u5177\u6709\u5e7f\u6cdb\u7684\u5e94\u7528\u6f5c\u529b\u3002<\/p>\n<p>\u9879\u76ee\u5730\u5740\uff1ahttps:\/\/depth-anything-v2.github.io\/<\/p>\n","protected":false},"excerpt":{"rendered":"<p>ByteDance has released the next generation of Depth Anything V2 depth model, which achieves significant performance improvements in the field of monocular depth estimation. Compared to its predecessor, Depth Anything V1, the V2 version features finer details and greater robustness, as well as significant improvements in efficiency, being more than 10x faster than the Stable Diffusion-based model. Key Features: Finer Detail: The V2 model is optimized in detail to provide finer depth prediction. High Efficiency and Accuracy:V2 provides significant improvements in efficiency and accuracy compared to models built on SD. Multi-scale model support:Provides models of different scales with parameters ranging from 25M to 1.3B to fit the<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[146],"tags":[548,3079],"collection":[],"class_list":["post-13186","post","type-post","status-publish","format-standard","hentry","category-news","tag-548","tag-3079"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/13186","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/comments?post=13186"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/13186\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=13186"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=13186"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=13186"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=13186"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}