{"id":13269,"date":"2026-10-13T01:39:01","date_gmt":"2026-10-12T17:39:01","guid":{"rendered":"https:\/\/infernews.com\/blog\/stereobind\/"},"modified":"2026-10-13T01:39:01","modified_gmt":"2026-10-12T17:39:01","slug":"stereobind","status":"publish","type":"post","link":"https:\/\/infernews.com\/blog\/stereobind\/","title":{"rendered":"StereoBind \u8b93\u751f\u6210\u8072\u97f3\u8ddf\u96a8\u756b\u9762\u79fb\u52d5"},"content":{"rendered":"\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" src=\"https:\/\/infernews.com\/blog\/wp-content\/uploads\/2026\/10\/StereoBind.jpg\" alt=\"StereoBind logo\"><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">\u7576\u756b\u9762\u4e2d\u7684\u8eca\u8f1b\u3001\u4eba\u7269\u6216\u7269\u4ef6\u79fb\u52d5\uff0c\u8072\u97f3\u4e0d\u61c9\u53ea\u5728\u6642\u9593\u4e0a\u540c\u6b65\uff0c\u9084\u8981\u8b93\u807d\u8005\u611f\u89ba\u8072\u6e90\u4f4d\u7f6e\u4e00\u540c\u6539\u8b8a\u3002StereoBind \u5c6c\u65bc\u806f\u5408\u5f71\u7247\u8207\u97f3\u8a0a\u751f\u6210\u6a21\u578b\u7684\u7814\u7a76\u9805\u76ee\uff0c\u8655\u7406\u7684\u6b63\u662f\u7acb\u9ad4\u8072\u8207\u53ef\u898b\u8072\u6e90\u4e4b\u9593\u7684\u52d5\u614b\u7a7a\u9593\u5c0d\u61c9\u554f\u984c\uff0c\u9762\u5411 AR\/VR\u3001\u4e92\u52d5\u904a\u6232\u53ca\u6c89\u6d78\u5f0f\u5167\u5bb9\u88fd\u4f5c\u8f03\u6709\u50f9\u503c\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">StereoBind \u5728\u9810\u8a13\u7df4\u7684 joint audio-video generator \u4e0a\u52a0\u5165\u8996\u89ba\u4f86\u6e90\u7684 motion tracks\uff0c\u5c07\u756b\u9762\u4e2d\u7684\u79fb\u52d5\u8ecc\u8de1\u50b3\u7d66\u97f3\u8a0a\u751f\u6210\u6d41\u7a0b\u3002Simple Summary Tokens \u58d3\u7e2e\u4f86\u6e90\u5167\u5bb9\u8207\u52d5\u614b\u8cc7\u8a0a\uff1bSpatial Track Encoder\uff08STE\uff09\u7de8\u78bc\u6bcf\u500b\u6642\u9593\u9ede\u7684\u6a19\u6e96\u5316 2D \u4f4d\u7f6e\uff1bResidualTrackRoPE \u5247\u628a\u76f8\u5c0d\u8ecc\u8de1\u8b8a\u5316\u52a0\u5165 temporal attention\uff0c\u4ee4\u6a21\u578b\u540c\u6642\u7406\u89e3\u8072\u6e90\u6240\u5728\u4f4d\u7f6e\u53ca\u79fb\u52d5\u65b9\u5411\u3002<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u4ee5\u8ecc\u8de1\u9023\u63a5\u8996\u89ba\u4f86\u6e90\u8207 stereo audio<\/li>\n<li>StereoWorld-29K \u63d0\u4f9b\u9644\u5e36 motion tracks \u7684\u7acb\u9ad4\u8072\u5f71\u97f3\u8cc7\u6599<\/li>\n<li>StereoWorldBench \u7528\u4f86\u91cf\u5ea6\u8072\u97f3\u662f\u5426\u8ddf\u96a8\u53ef\u898b\u8072\u6e90<\/li>\n<li>\u76ee\u6a19\u662f\u6539\u5584\u7a7a\u9593\u5c0d\u9f4a\uff0c\u540c\u6642\u4fdd\u7559\u6574\u9ad4\u5f71\u97f3\u54c1\u8cea<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">StereoWorld-29K \u4e0d\u53ea\u662f\u8a13\u7df4\u8cc7\u6599\uff0c\u4ea6\u5305\u542b\u7531\u771f\u5be6\u5f71\u7247\u53ca\u8ecc\u8de1\u63a7\u5236\u5408\u6210\u5834\u666f\u6574\u7406\u800c\u6210\u7684\u5e7e\u4f55\u76e3\u7763\uff1bStereoWorldBench \u5247\u91dd\u5c0d\u8072\u97f3\u8207\u756b\u9762\u4f86\u6e90\u5728\u6642\u9593\u4e0a\u7684\u7a7a\u9593\u4e00\u81f4\u6027\u4f5c\u8a55\u4f30\u3002\u9805\u76ee\u8cc7\u6599\u7a31\u5be6\u9a57\u80fd\u5927\u5e45\u6539\u5584\u7acb\u9ad4\u8072\u751f\u6210\u7684\u7a7a\u9593\u5c0d\u9f4a\uff0c\u4f46\u76ee\u524d\u63d0\u4f9b\u7684\u8cc7\u8a0a\u672a\u5217\u51fa\u5177\u9ad4\u5206\u6578\u3001\u57fa\u6e96\u6a21\u578b\u6216\u5ef6\u9072\u6578\u64da\uff0c\u56e0\u6b64\u672a\u80fd\u5224\u65b7\u5b83\u5728\u4e0d\u540c\u5834\u666f\u7684\u5be6\u969b\u512a\u52e2\u5e45\u5ea6\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">GitHub \u5132\u5b58\u5eab\u76ee\u524d\u4ecd\u5c6c\u516c\u958b\u767c\u5e03\u524d\u72c0\u614b\uff0cinference code\u3001training code\u3001\u8a2d\u5b9a\u6a94\u3001checkpoints\u3001StereoWorld-29K \u53ca\u8a55\u4f30\u5957\u4ef6\u5c1a\u672a\u63d0\u4f9b\uff0c\u4ea6\u6c92\u6709\u53ef\u7167\u505a\u7684\u5b89\u88dd\u6d41\u7a0b\u3002\u7814\u7a76\u5718\u968a\u3001\u5f71\u97f3\u751f\u6210\u6a21\u578b\u958b\u767c\u8005\uff0c\u4ee5\u53ca\u9700\u8981\u8072\u97f3\u65b9\u5411\u96a8\u756b\u9762\u79fb\u52d5\u7684 AR\/VR \u548c\u904a\u6232\u88fd\u4f5c\u6d41\u7a0b\uff0c\u53ef\u4ee5\u5148\u628a\u5b83\u7406\u89e3\u6210\u4e00\u5957\u5f85\u516c\u958b\u7684 trajectory-conditioned \u806f\u5408\u751f\u6210\u6846\u67b6\uff1b\u73fe\u968e\u6bb5\u8f03\u9069\u5408\u95b1\u8b80\u7814\u7a76\u6982\u5ff5\u53ca\u7b49\u5f85\u5f8c\u7e8c\u8cc7\u6e90\uff0c\u800c\u4e0d\u662f\u7acb\u5373\u90e8\u7f72\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><a href=\"https:\/\/vivocameraresearch.github.io\/Stereo-Bind-Project\/\" rel=\"noopener noreferrer\"><strong>\u9805\u76ee\u4e3b\u9801<\/strong><\/a> \u00b7 <a href=\"https:\/\/github.com\/vivoCameraResearch\/StereoBind\" rel=\"noopener noreferrer\"><strong>GitHub<\/strong><\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>StereoBind \u4e0d\u53ea\u540c\u6b65\u5f71\u7247\u8207\u8072\u97f3\uff0c\u9084\u5617\u8a66\u8b93\u8072\u97f3\u65b9\u5411\u8ddf\u96a8\u756b\u9762\u4e2d\u7684\u767c\u8072\u7269\u9ad4\u79fb\u52d5\uff0c\u70ba\u6c89\u6d78\u5f0f\u751f\u6210\u88dc\u4e0a\u7a7a\u9593\u611f\u3002<\/p>\n","protected":false},"author":8,"featured_media":13268,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"wpai_generated_summary":"","wpai_meta_description":"","footnotes":""},"categories":[133,162,76,119,127,31,210,29,197,150,199],"tags":[],"class_list":["post-13269","post","type-post","status-publish","format-standard","hentry","category-133","category-ai-productions","category-76","category-119","category-127","category-video","category-worldactionmodel","category-audio","category-framework","category-150","category-dataset-"],"_links":{"self":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/13269","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=13269"}],"version-history":[{"count":0,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/13269\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/media\/13268"}],"wp:attachment":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/media?parent=13269"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/categories?post=13269"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/tags?post=13269"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}