Meta发布SAM 3：突破标签限制，30毫秒分割百物，3D重建与科研应用拓新篇

ITBEAR科技资讯11-20

meta近日在人工智能领域再掀波澜，正式推出第三代图像分割模型Segment Anything Models（SAM）——SAM 3，并同步开源3D重建模型SAM 3D。这一技术组合不仅突破了传统图像分割的固有局限，更将应用场景从二维平面延伸至三维空间，为视频创作、机器人感知、野生动物保护等多个领域带来革新性工具。在核心功能层面，SAM 3首次实现通过自然语言与图像示例的双重提示，精准识别、分割及...

网页链接

免责声明：本文观点仅代表作者个人观点，不构成本平台的投资建议，本平台不对文章信息准确性、完整性和及时性做出任何保证，亦不对因使用或信赖文章信息引发的任何损失承担责任。

精彩评论

我们需要你的真知灼见来填补这片空白

发表看法

{"i18n":{"language":"zh_CN"},"isChannel":false,"data":{"share":"https://www.laohu8.com/m/news/2584185354?lang=zh_CN&edition=full","thumbnail":"","is_english":false,"pubTime":"2025-11-20 15:08","share_image_url":"https://static.laohu8.com/9a95c1376e76363c1401fee7d3717173","id":"2584185354","market":"us","top_or_hot":-1,"title":"Meta发布SAM 3：突破标签限制，30毫秒分割百物，3D重建与科研应用拓新篇","media":"ITBEAR科技资讯","content":"<div>\n<p>meta近日在人工智能领域再掀波澜，正式推出第三代图像分割模型Segment Anything Models（SAM）——SAM 3，并同步开源3D重建模型SAM 3D。这一技术组合不仅突破了传统图像分割的固有局限，更将应用场景从二维平面延伸至三维空间，为视频创作、机器人感知、野生动物保护等多个领域带来革新性工具。在核心功能层面，SAM 3首次实现通过自然语言与图像示例的双重提示，精准识别、分割及...</p>\n\n<a href=\"http://gu.qq.com/resources/shy/news/detail-v2/index.html#/?id=nesSN2025112015261097751665&s=b\">网页链接</a>\n\n</div>\n","source":"tencent","html":"<!DOCTYPE html>\n<html>\n<head>\n<meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\" />\n<meta name=\"viewport\" content=\"width=device-width,initial-scale=1.0,minimum-scale=1.0,maximum-scale=1.0,user-scalable=no\"/>\n<meta name=\"format-detection\" content=\"telephone=no,email=no,address=no\" />\n<title>Meta发布SAM 3：突破标签限制，30毫秒分割百物，3D重建与科研应用拓新篇</title>\n<style type=\"text/css\">\na,abbr,acronym,address,applet,article,aside,audio,b,big,blockquote,body,canvas,caption,center,cite,code,dd,del,details,dfn,div,dl,dt,\nem,embed,fieldset,figcaption,figure,footer,form,h1,h2,h3,h4,h5,h6,header,hgroup,html,i,iframe,img,ins,kbd,label,legend,li,mark,menu,nav,\nobject,ol,output,p,pre,q,ruby,s,samp,section,small,span,strike,strong,sub,summary,sup,table,tbody,td,tfoot,th,thead,time,tr,tt,u,ul,var,video{ font:inherit;margin:0;padding:0;vertical-align:baseline;border:0 }\nbody{ font-size:16px; line-height:1.5; color:#999; background:transparent; }\n.wrapper{ overflow:hidden;word-break:break-all;padding:10px; }\nh1,h2{ font-weight:normal; line-height:1.35; margin-bottom:.6em; }\nh3,h4,h5,h6{ line-height:1.35; margin-bottom:1em; }\nh1{ font-size:24px; }\nh2{ font-size:20px; }\nh3{ font-size:18px; }\nh4{ font-size:16px; }\nh5{ font-size:14px; }\nh6{ font-size:12px; }\np,ul,ol,blockquote,dl,table{ margin:1.2em 0; }\nul,ol{ margin-left:2em; }\nul{ list-style:disc; }\nol{ list-style:decimal; }\nli,li p{ margin:10px 0;}\nimg{ max-width:100%;display:block;margin:0 auto 1em; }\nblockquote{ color:#B5B2B1; border-left:3px solid #aaa; padding:1em; }\nstrong,b{font-weight:bold;}\nem,i{font-style:italic;}\ntable{ width:100%;border-collapse:collapse;border-spacing:1px;margin:1em 0;font-size:.9em; }\nth,td{ padding:5px;text-align:left;border:1px solid #aaa; }\nth{ font-weight:bold;background:#5d5d5d; }\n.symbol-link{font-weight:bold;}\n/* header{ border-bottom:1px solid #494756; } */\n.title{ margin:0 0 8px;line-height:1.3;color:#ddd; }\n.meta {color:#5e5c6d;font-size:13px;margin:0 0 .5em; }\na{text-decoration:none; color:#2a4b87;}\n.meta .head { display: inline-block; overflow: hidden}\n.head .h-thumb { width: 30px; height: 30px; margin: 0; padding: 0; border-radius: 50%; float: left;}\n.head .h-content { margin: 0; padding: 0 0 0 9px; float: left;}\n.head .h-name {font-size: 13px; color: #eee; margin: 0;}\n.head .h-time {font-size: 11px; color: #7E829C; margin: 0;line-height: 11px;}\n.small {font-size: 12.5px; display: inline-block; transform: scale(0.9); -webkit-transform: scale(0.9); transform-origin: left; -webkit-transform-origin: left;}\n.smaller {font-size: 12.5px; display: inline-block; transform: scale(0.8); -webkit-transform: scale(0.8); transform-origin: left; -webkit-transform-origin: left;}\n.bt-text {font-size: 12px;margin: 1.5em 0 0 0}\n.bt-text p {margin: 0}\n</style>\n</head>\n<body>\n<div class=\"wrapper\">\n<header>\n<h2 class=\"title\">\nMeta发布SAM 3：突破标签限制，30毫秒分割百物，3D重建与科研应用拓新篇\n</h2>\n\n<h4 class=\"meta\">\n\n\n2025-11-20 15:08 北京时间&nbsp;&nbsp;&nbsp;<a href=http://gu.qq.com/resources/shy/news/detail-v2/index.html#/?id=nesSN2025112015261097751665&s=b><strong>ITBEAR科技资讯</strong></a>\n\n\n</h4>\n\n</header>\n<article>\n<div>\n<p>meta近日在人工智能领域再掀波澜，正式推出第三代图像分割模型Segment Anything Models（SAM）——SAM 3，并同步开源3D重建模型SAM 3D。这一技术组合不仅突破了传统图像分割的固有局限，更将应用场景从二维平面延伸至三维空间，为视频创作、机器人感知、野生动物保护等多个领域带来革新性工具。在核心功能层面，SAM 3首次实现通过自然语言与图像示例的双重提示，精准识别、分割及...</p>\n\n<a href=\"http://gu.qq.com/resources/shy/news/detail-v2/index.html#/?id=nesSN2025112015261097751665&s=b\">网页链接</a>\n\n</div>\n\n\n</article>\n</div>\n</body>\n</html>\n","isBrief":false,"type":0,"news_type":1,"symbol":"LU0444971666.USD","symbol_name":"天利全球科技基金","start_time":0,"source_url":"http://gu.qq.com/resources/shy/news/detail-v2/index.html#/?id=nesSN2025112015261097751665&s=b","article_id":"2584185354","we_media_id":null,"thumbnails":[],"rights":{"source":"tencent","url":"http://gu.qq.com/resources/shy/news/detail-v2/index.html#/?id=nesSN2025112015261097751665&s=b","rn_cache_url":null,"customStyle":"body{padding-top:10px;}#news_title{font-weight:bold;#titleStyle#;}#news_description span{font-size:12px;#descriptionStyle#;}.footer-note{#statement#}","selectors":".mod-LoadTzbdNews, body","filters":".relate-stock, .hot-list, .recom-box, .wx-sou","directOrigin":true},"url":"https://stock-news.laohu8.com/highlight/detail?id=2584185354","pubTimestamp":1763622531,"columns":[],"sourceInfo":{"source_id":"tencent","name":"腾讯"},"weMediaInfo":null,"summary":"meta近日在人工智能领域再掀波澜，正式推出第三代图像分割模型Segment Anything Models——SAM 3，并同步开源3D重建模型SAM 3D。在核心功能层面，SAM 3首次实现通过自然语言与图像示例的双重提示，精准识别、分割及追踪视频中的任意物体。数据标注效率的飞跃是SAM 3的另一大突破。在三维重建领域，SAM 3D系列模型树立了新标杆。实际应用层面，SAM 3已渗透至科研与商业领域。尽管性能显著提升，SAM 3仍存在局限性。","collect":0,"end_time":0,"defaultTopTitle":"qq.com","property":[],"viewcount":null,"language":"zh","relate_stocks":{"LU0444971666.USD":"天利全球科技基金","LU0234570918.USD":"高盛全球核心股票组合Acc Close","BK4525":"远程办公概念","LU1267930730.SGD":"富兰克林美国机遇基金AS Acc SGD (CPF)","LU0096362180.USD":"CT (LUX) I GLOBAL FOCUS \"DU\" (USD)","BK4524":"宅经济概念","SG9999002224.SGD":"Allianz Global High Payout SGD","IE00BJJMRX11.SGD":"Janus Henderson Balanced A Acc SGD","LU0072462426.USD":"贝莱德全球配置 A2","BK4527":"明星科技股","LU2133065610.SGD":"JPMorgan Investment Funds - Global Dividend A (mth) SGD","LU0882574139.USD":"富达环球消费行业基金A ACC","IE00BJTD4N35.SGD":"Neuberger Berman US Long Short Equity A1  Acc SGD-H","LU2054465674.USD":"UBS (LUX) KEY SELEC SICAV DIGITAL TRANSFORMATION T \"P\" (USD) ACC","LU0957791311.USD":"THREADNEEDLE (LUX) GLOBAL FOCUS \"ZU\" (USD) ACC","LU0208291251.USD":"FRANKLIN MUTUAL U.S. VALUE \"A\" (USD) INC","LU0130102774.USD":"Natixis Harris Associates US Equity RA USD","LU2125154778.USD":"ALLSPRING GLOBAL EQUITY ENHANCED INCOME \"A\" (USD) INC","LU0061474705.USD":"THREADNEEDLE (LUX) GLOBAL DYNAMIC REAL RETURN \"AU\" (USD) ACC","SAM":"波斯顿啤酒","LU1670711040.USD":"M&G (LUX) GLOBAL DIVIDEND \"A\" (USD) ACC","LU2326559502.SGD":"Natixis Loomis Sayles US Growth Equity P/A SGD-H","LU0308772762.SGD":"Blackrock Global Allocation A2 SGD-H","LU2247934214.USD":"FIDELITY FUNDS SUSTAINABLE FUTURE CONNECTIVITY \"A\" (USD) ACC","IE0002270589.USD":"LEGG MASON CLEARBRIDGE VALUE \"A\" (USD) INC","LU2065171311.SGD":"M&G (LUX) GLOBAL MAXIMA \"A\" (SGD) ACC","LU0784384876.USD":"Blackrock Global Multi-Asset Income A6 USD","LU2420271590.USD":"ALLIANZ SELECT INCOME AND GROWTH \"AT\" (USD) ACC","FB":"ProShares S&P 500 Dynamic Buffer ETF","LU0823434583.USD":"BNP PARIBAS US GROWTH \"C\" (USD) ACC","LU1988902786.USD":"FULLERTON LUX FUNDS GLOBAL ABSOLUTE ALPHA \"I\" (USD) ACC","LU1074936037.SGD":"JPMorgan Funds - US Value A (acc) SGD","LU0053666078.USD":"摩根大通基金-美国股票A（离岸）美元","LU2430703178.SGD":"WELLINGTON MULTI-ASSET HIGH INCOME \"AM4H\" (SGDHDG) INC","IE00BJTD4V19.USD":"NEUBERGER BERMAN US LONG SHORT EQUITY \"A1\" (USD) ACC","LU1992135472.HKD":"ALLIANZ GLOBAL INTELLIGENT CITIES \"AT\" (HKD) ACC","LU2764263203.CNY":"BGF GLOBAL UNCONSTRAINED EQUITY \"A2\" (CNYHDG) ACC","LU1242518931.SGD":"Fullerton Lux Funds - Asia Absolute Alpha A Acc SGD","LU0127658192.USD":"EASTSPRING INVESTMENTS GLOBAL TECHNOLOGY \"A\" (USD) ACC","LU2213496289.HKD":"ALLIANZ INCOME AND GROWTH \"AT\" (HKD) ACC","LU0795875169.SGD":"JPMorgan Investment Funds - Global Income A (div) SGD-H","SG9999015986.USD":"LIONGLOBAL DISRUPTIVE INNOVATION \"I\" (USD) ACC","LU0077335932.USD":"FIDELITY AMERICAN GROWTH \"A\" INC","LU0784383803.USD":"BGF GLOBAL MULTI-ASSET INCOME FUND \"A\" (USD) INC A","LU1035775433.USD":"AB SICAV I - AMERICAN GROWTH PORTFOLIO \"AD\" (USD) INC","LU0348723411.USD":"ALLIANZ GLOBAL HI-TECH GROWTH \"A\" (USD) INC","LU0061474960.USD":"天利环球焦点基金AU Acc","LU2764262908.HKD":"BGF GLOBAL UNCONSTRAINED EQUITY \"A2\" (HKD) ACC","META":"Meta Platforms, Inc.","LU0198837287.USD":"UBS (LUX) EQUITY SICAV - USA GROWTH \"P\" (USD) ACC"},"translate_title":"Meta releases SAM 3: Breaking through label restrictions, dividing everything in 30 milliseconds, opening up a new chapter in 3D reconstruction and scientific research applications","themeId":null,"isJumpTheme":false,"ttsUrl":null,"symbols_score_info":{"FB":1.5,"META":1.5,"SAM":1.5},"content_text":"meta近日在人工智能领域再掀波澜，正式推出第三代图像分割模型Segment Anything Models（SAM）——SAM 3，并同步开源3D重建模型SAM 3D。这一技术组合不仅突破了传统图像分割的固有局限，更将应用场景从二维平面延伸至三维空间，为视频创作、机器人感知、野生动物保护等多个领域带来革新性工具。在核心功能层面，SAM 3首次实现通过自然语言与图像示例的双重提示，精准识别、分割及追踪视频中的任意物体。用户仅需输入“条纹红色雨伞”等描述性词汇，模型即可自动定位图像或视频中所有符合条件的实例，彻底摆脱传统模型对固定标签集的依赖。为验证这一能力，meta构建了SA-Co基准数据集，涵盖21.4万个独特概念、12.4万张图像及1700个视频，其概念覆盖范围达现有基准的50倍以上。测试数据显示，SAM 3在LVIS数据集的零样本分割任务中准确率达47.0，较前代提升22%；在用户偏好测试中，其输出效果以3:1的优势领先于最强基准模型OWLv2。技术架构方面，SAM 3引入“可提示概念分割”（Promptable Concept Segmentation）机制，支持短语文本、图像示例、点选、框选等多种提示方式。这种灵活性使其既能处理“坐着但没有拿礼物盒的人”等复杂推理任务，也可应对罕见或难以用文字描述的视觉概念。当与多模态大语言模型协同工作时，SAM 3在ReasonSeg和OmniLabel等需要推理的分割基准测试中表现优异，且无需针对特定数据集进行额外训练。数据标注效率的飞跃是SAM 3的另一大突破。meta开发的创新数据引擎将模型、人类标注者与AI系统结合，形成闭环反馈机制。对于图像中不存在的概念标注，该系统速度较纯人工提升5倍；在细粒度领域标注中，效率亦提高36%。通过这一系统，研究团队构建了包含超400万个独特概念的训练集，其中AI标注者基于Llama 3.2v模型，在掩码质量验证等任务中达到或超越人类水平，使整体标注吞吐量翻倍。在三维重建领域，SAM 3D系列模型树立了新标杆。其包含的SAM 3D Objects可从单张自然图像重建详细3D形状、纹理及物体布局，通过扩散捷径优化，实现几秒内完成高质量纹理重建。在人类偏好测试中，该模型以至少5:1的胜率领先其他领先方案，为机器人3D感知等实时应用提供可能。另一模型SAM 3D Body则专注于人体姿态估计，即使面对异常姿势、遮挡或多人场景，仍能通过交互式输入（如分割掩码）实现精准预测。其训练数据集涵盖800万张图像，包含罕见姿势及多样化服装场景，在多个3D基准测试中表现卓越。实际应用层面，SAM 3已渗透至科研与商业领域。meta与Conservation X Labs合作推出的SA-FARI数据集，包含超1万个相机陷阱视频，覆盖100余个物种，每帧图像均标注边界框与分割掩码，为野生动物保护提供研究工具。海洋研究方面，FathomNet数据库开放了水下图像的定制化分割掩码及实例分割基准，助力海洋探索AI工具开发。商业领域，meta与Roboflow合作，允许用户标注数据、微调模型并部署至特定场景，同时公开微调方法供社区参考。尽管性能显著提升，SAM 3仍存在局限性。例如，其在细粒度专业领域（如医学图像）的零样本泛化能力有限，需针对特定术语进行优化；视频追踪任务中，推理成本随物体数量线性增长，且缺乏物体间交互机制。这些挑战为后续研究指明了方向，也预示着图像分割技术仍有广阔进化空间。","kind":"news","is_publish_news":true,"is_publish_highlight":false,"is_publish_live":false,"is_publish_wemedia":null,"editions":null,"column":"","sentiment":"0","news_tag":"","news_rank":0,"symbols":[],"gpt_button":1,"need_auth":false,"code":"91000000","status":"200"},"commentList":[],"isCommentEnd":true,"newsSizeData":{"likeSize":0,"commentSize":0,"repostSize":0,"favoriteSize":0,"likeStatus":false,"favoriteStatus":false},"APP":{"userAgent":"Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; +claudebot@anthropic.com)","isDev":false,"isTTM":false,"deviceId":"web-server-community-laohu8-v3","version":"4.35.9","shortVersion":"4.35.9","platform":"web","vendor":"web","appName":"laohu8","isIOS":false,"isAndroid":false,"isTiger":false,"isTHS":false,"isWeiXin":false,"isWeiXinMini":false,"isWeiBo":false,"isQQ":false,"isBaiduSwan":false,"isBaiduBox":false,"isDingTalk":false,"isToutiao":false,"isOnePlus":false,"isHuaWei":false,"isXiaomi":false,"isXiaomiWebView":false,"isOppo":false,"isVivo":false,"isSamsung":false,"isMobile":false},"href":"/m/news/2584185354","isCrawlerRequest":true}