
{"id":10034,"date":"2026-07-08T19:47:40","date_gmt":"2026-07-08T11:47:40","guid":{"rendered":"https:\/\/infernews.com\/blog\/sensenova-vision\/"},"modified":"2026-07-08T19:47:40","modified_gmt":"2026-07-08T11:47:40","slug":"sensenova-vision","status":"publish","type":"post","link":"https:\/\/infernews.com\/blog\/sensenova-vision\/","title":{"rendered":"SenseNova-Vision \u628a\u8996\u89ba\u4efb\u52d9\u6536\u9032\u540c\u4e00\u6a21\u578b"},"content":{"rendered":"\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" src=\"https:\/\/infernews.com\/blog\/wp-content\/uploads\/2026\/07\/fig2_one_case_for_all.jpg\" alt=\"SenseNova-Vision handles diverse vision tasks in a unified model\"><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">\u505a\u8996\u89ba\u9805\u76ee\u6700\u9ebb\u7169\u7684\uff0c\u5f80\u5f80\u4e0d\u662f\u55ae\u4e00\u4efb\u52d9\u505a\u4e0d\u5230\uff0c\u800c\u662f\u5075\u6e2c\u3001OCR\u3001\u5206\u5272\u3001\u6df1\u5ea6\u4f30\u8a08\u540c\u591a\u8996\u89d2\u5e7e\u4f55\u5404\u6709\u5404\u5957\u8f38\u51fa\u683c\u5f0f\u3002SenseNova-Vision\u628a\u9019\u4e9b\u5de5\u4f5c\u6536\u6582\u5230 unified multimodal model\uff08UMM\uff09\u7684\u751f\u6210\u4ecb\u9762\u4e4b\u5167\uff0c\u5c6c\u65bc<strong>\u591a\u6a21\u614b\u6a21\u578b\u9805\u76ee<\/strong>\uff0c\u91cd\u9ede\u662f\u7528\u81ea\u7136\u8a9e\u8a00\u6307\u4ee4\u52a0\u53ef\u9078\u8996\u89ba\u63d0\u793a\uff0c\u7d71\u4e00\u8655\u7406\u7d50\u69cb\u5316\u7406\u89e3\u8207\u5bc6\u96c6\u9810\u6e2c\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u5b83\u7684\u53d6\u5411\u5e7e\u660e\u78ba\uff1a\u4e0d\u518d\u70ba\u6bcf\u985e\u8996\u89ba\u4efb\u52d9\u5404\u81ea\u8a2d\u8a08\u982d\u90e8\u8207\u8f38\u51fa\u5668\uff0c\u800c\u662f\u628a boxes\u3001points\u3001OCR strings\u3001keypoints\u3001camera parameters \u4ea4\u7531\u6587\u5b57\u751f\u6210\uff0c\u628a segmentation masks\u3001depth maps\u3001surface normals\u3001multi-view point maps \u4ea4\u7531\u5f71\u50cf\u751f\u6210\uff0c\u4ea6\u652f\u63f4\u6587\u5b57\u52a0\u5f71\u50cf\u6df7\u5408\u56de\u61c9\u3002\u9019\u7a2e\u505a\u6cd5\u7684\u597d\u8655\u662f\u5de5\u4f5c\u6d41\u4e00\u81f4\uff0c\u4ee3\u50f9\u5247\u662f\u63a8\u7406\u89e3\u78bc\u8207\u8a55\u6e2c\u8f49\u63db\u8981\u505a\u5f97\u5920\u7a69\uff0c\u5426\u5247\u901a\u7528\u6027\u672a\u5fc5\u7b49\u65bc\u6bcf\u4e00\u9805\u90fd\u6700\u5f37\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u76ee\u524d\u516c\u958b\u5167\u5bb9\u5305\u62ec\u63a8\u7406\u7a0b\u5f0f\u3001\u6a21\u578b\u6b0a\u91cd SenseNova-Vision-7B-MoT\u3001\u8cc7\u6599\u96c6 SenseNova-Vision-Corpus-50M\uff0c\u4ee5\u53ca\u53ef\u8a66\u7528\u7684 Demo\u3002\u8981\u7406\u89e3\u5b83\u9ede\u6a23\u6e2c\u8a66\uff0c\u6700\u76f4\u63a5\u662f\u5148\u7528 Demo \u770b\u540c\u4e00\u5f35\u5716\u5728\u4e0d\u540c\u6307\u4ee4\u4e0b\u53ef\u5426\u8f38\u51fa\u53ef\u89e3\u78bc\u7d50\u679c\uff0c\u518d\u914d\u5408\u5009\u5eab\u7684 Evaluation Guide \u5c0d\u6a19\u6e96 benchmark \u6aa2\u67e5\u6587\u5b57\u3001\u5f71\u50cf\u6216\u6df7\u5408\u8f38\u51fa\u7684\u9084\u539f\u80fd\u529b\u3002<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>\u540c\u4e00\u6a21\u578b\u8986\u84cb<\/strong> \u7d50\u69cb\u5316\u8996\u89ba\u7406\u89e3\u3001\u5206\u5272\u3001dense geometric prediction \u8207 multi-view visual geometry<\/li>\n<li><strong>\u8f38\u51fa\u5f62\u5f0f\u7d71\u4e00<\/strong>\uff1a\u6587\u5b57\u3001\u5f71\u50cf\u3001\u6df7\u5408\u6587\u5b57\u5f71\u50cf\u90fd\u53ef\u4f5c\u70ba\u56de\u61c9<\/li>\n<li><strong>\u5df2\u516c\u958b\u8cc7\u6e90\u5b8c\u6574<\/strong>\uff1ainference code\u3001SenseNova-Vision-7B-MoT\u3001SenseNova-Vision-Corpus-50M\u3001Demo<\/li>\n<li><strong>\u9069\u5408\u5834\u666f\u660e\u78ba<\/strong>\uff1a\u7814\u7a76\u5718\u968a\u3001\u8996\u89ba\u7522\u54c1\u539f\u578b\u3001\u8981\u6574\u5408\u591a\u4efb\u52d9\u6d41\u7a0b\u7684\u5de5\u7a0b\u5de5\u4f5c<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">\u9019\u500b\u9805\u76ee\u6700\u9069\u5408\u4e0d\u60f3\u70ba\u6bcf\u500b\u4efb\u52d9\u7dad\u8b77\u4e00\u5957\u6a21\u578b\u5806\u758a\u7684\u5718\u968a\uff0c\u5c24\u5176\u662f\u540c\u6642\u8981\u505a\u5075\u6e2c\u3001\u6587\u5b57\u8fa8\u8b58\u3001\u5206\u5272\u8207\u5e7e\u4f55\u4f30\u8a08\u7684\u7d44\u5408\u578b\u6d41\u7a0b\u3002\u73fe\u6709\u8cc7\u6599\u6307\u51fa\u5b83\u5728\u591a\u985e\u8996\u89ba\u4efb\u52d9\u4e0a\u6709\u4e0d\u932f\u7d50\u679c\uff0c\u4f46\u5009\u5eab\u6458\u8981\u672a\u5217\u51fa\u5b8c\u6574\u6578\u5b57\uff1b\u73fe\u968e\u6bb5\u66f4\u503c\u5f97\u7559\u610f\u7684\uff0c\u662f\u5b83\u7528\u53ef\u89e3\u78bc\u751f\u6210\u683c\u5f0f\u7d71\u4e00 benchmark \u8f38\u51fa\u7684\u80fd\u529b\uff0c\u9019\u6bd4\u55ae\u770b\u67d0\u4e00\u9805\u5206\u6578\u66f4\u80fd\u53cd\u6620\u5176\u5b9a\u4f4d\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><a href=\"https:\/\/github.com\/OpenSenseNova\/SenseNova-Vision\" rel=\"noopener noreferrer\" target=\"_blank\"><strong>GitHub<\/strong><\/a> \u00b7 <a href=\"https:\/\/huggingface.co\/sensenova\/SenseNova-Vision-7B-MoT\" rel=\"noopener noreferrer\" target=\"_blank\"><strong>\u6a21\u578b<\/strong><\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u540c\u4e00\u500b\u6a21\u578b\u540c\u6642\u8655\u7406\u6846\u3001\u9ede\u3001OCR\u3001\u5206\u5272\u540c\u6df1\u5ea6\u5716\uff0cSenseNova-Vision\u60f3\u89e3\u6c7a\u7684\u6b63\u662f\u8996\u89ba\u6d41\u7a0b\u592a\u5206\u6563\u7684\u8001\u554f\u984c\u3002\u4f60\u53ef\u4ee5\u628a\u5b83\u7406\u89e3\u6210\u4e00\u500b\u7528\u751f\u6210\u65b9\u5f0f\u7d71\u4e00\u591a\u7a2e\u96fb\u8166\u8996\u89ba\u8f38\u51fa\u7684\u6a21\u578b\u9805\u76ee\u3002<\/p>\n","protected":false},"author":8,"featured_media":10033,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"ai_generated_summary":"","footnotes":""},"categories":[133,163,30,119,120,76,199],"tags":[],"class_list":["post-10034","post","type-post","status-publish","format-standard","hentry","category-133","category-163","category-image","category-119","category-120","category-76","category-dataset-"],"_links":{"self":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/10034","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/users\/8"}],"replies":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/comments?post=10034"}],"version-history":[{"count":0,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/10034\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/media\/10033"}],"wp:attachment":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/media?parent=10034"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/categories?post=10034"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/tags?post=10034"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}