{"@context":"https://schema.org","@type":"NewsArticle","generatedAt":"2026-09-22T03:01:07.034Z","headline":"World Labs 发布世界模型 Atlas：从少量照片生成、重建并模拟 3D 世界","description":"World Labs（李飞飞联合创立）发布世界模型 Atlas，可从几张照片完成 3D 场景生成、重建与仿真，输出最高 1440p、1 分钟的可控镜头视频，并支持点云与 3D Gaussian splats 等 3D 数据输出。","url":"https://www.aioga.com/news/cmtk2sj9l01oaron9tt7clme8/","mainEntityOfPage":"https://www.aioga.com/news/cmtk2sj9l01oaron9tt7clme8/","datePublished":"2026-09-02T12:28:36.000Z","dateModified":"2026-09-02T12:28:36.000Z","inLanguage":"zh-CN","publisher":{"@type":"NewsMediaOrganization","name":"Aioga","url":"https://www.aioga.com"},"citation":["https://the-decoder.com/world-labs-unveils-atlas-a-single-ai-model-that-generates-reconstructs-and-simulates-3d-worlds-from-just-a-few-photos","https://aihot.virxact.com/items/cmtk2sj9l01oaron9tt7clme8"],"canonicalUrl":"https://www.aioga.com/news/cmtk2sj9l01oaron9tt7clme8/","directAnswer":{"@type":"Answer","text":"World Labs 发布世界模型 Atlas，称其可从一张至数十张照片生成、重建并模拟三维场景，并根据用户指定的相机位置和角度生成新视角。模型输出最高可达 1440p、1 分钟视频，也支持点云和 3D Gaussian splats 等三维数据。","url":"https://www.aioga.com/news/cmtk2sj9l01oaron9tt7clme8/","dateCreated":"2026-09-02T12:28:36.000Z","author":{"@type":"Organization","@id":"https://www.aioga.com/authors/aioga-editorial/#editorial-team","name":"Aioga Editorial Team","url":"https://www.aioga.com/authors/aioga-editorial/"}},"evidence":[{"@type":"CreativeWork","name":"the-decoder.com source article","url":"https://the-decoder.com/world-labs-unveils-atlas-a-single-ai-model-that-generates-reconstructs-and-simulates-3d-worlds-from-just-a-few-photos","datePublished":"2026-09-02T12:28:36.000Z","provider":{"@type":"Organization","name":"the-decoder.com","url":"https://the-decoder.com/world-labs-unveils-atlas-a-single-ai-model-that-generates-reconstructs-and-simulates-3d-worlds-from-just-a-few-photos"}},{"@type":"CreativeWork","name":"AIHot archive record","url":"https://aihot.virxact.com/items/cmtk2sj9l01oaron9tt7clme8","datePublished":"2026-09-02T12:28:36.000Z","provider":{"@type":"Organization","name":"AIHot","url":"https://aihot.virxact.com/items/cmtk2sj9l01oaron9tt7clme8"}}],"aggregationSource":"The Decoder：AI News（RSS）","originalPublisher":{"name":"the-decoder.com","url":"https://the-decoder.com/world-labs-unveils-atlas-a-single-ai-model-that-generates-reconstructs-and-simulates-3d-worlds-from-just-a-few-photos"},"geoDeepAnswer":null,"article":{"id":"cmtk2sj9l01oaron9tt7clme8","slug":"cmtk2sj9l01oaron9tt7clme8","url":"https://www.aioga.com/news/cmtk2sj9l01oaron9tt7clme8/","title":"World Labs 发布世界模型 Atlas：从少量照片生成、重建并模拟 3D 世界","title_en":"","summary":"World Labs（李飞飞联合创立）发布世界模型 Atlas，可从几张照片完成 3D 场景生成、重建与仿真，输出最高 1440p、1 分钟的可控镜头视频，并支持点云与 3D Gaussian splats 等 3D 数据输出。","source":"The Decoder：AI News（RSS）","sourceUrl":"https://the-decoder.com/world-labs-unveils-atlas-a-single-ai-model-that-generates-reconstructs-and-simulates-3d-worlds-from-just-a-few-photos","aiHotUrl":"https://aihot.virxact.com/items/cmtk2sj9l01oaron9tt7clme8","publishedAt":"2026-09-02T12:28:36.000Z","category":"行业动态","score":58,"selected":false,"articleBody":["World Labs, co-founded by AI researcher Fei-Fei Li, has announced Atlas, a world model that generates, reconstructs, and simulates 3D scenes from just a few images. The company claims it beats specialized models at their own tasks, which could make many of them unnecessary.","Since its founding, World Labs has pursued the goal of \"spatial intelligence\"：https://the-decoder.com/fei-fei-lis-world-labs-raises-one-billion-dollars-for-spatial-intelligence/, the idea that AI should understand 3D space the way humans do. Atlas is the company's first model built to do that at scale. Rather than producing flat images or video clips, it grasps how a scene looks from any angle and how it changes over time.","World Labs describes Atlas as an omni-model trained from scratch on text, images, video, and 3D data. Every input gets anchored to a specific position in 3D space rather than processed as a flat sequence. The company calls this shared spatial understanding \"spatial context,\" and it's what the model uses to generate each new frame or viewpoint. According to World Labs, this anchoring separates Atlas from pure language or video models.","Fei-Fei Li laid out this exact problem：https://the-decoder.com/the-scientist-who-taught-ai-to-see-now-wants-it-to-understand-space/ in a November 2025 essay. Current multimodal language models and video diffusion models break data into one- or two-dimensional sequences, she argued, which makes even simple spatial tasks needlessly hard. What's needed are architectures that organize tokenization, context, and memory in a 3D- or 4D-aware way.","For camera-controlled generation, Atlas takes one or more images and produces new views at freely chosen camera positions and angles. Camera movement is passed as a direct geometric input rather than described through text prompts, as many video models require.","The model outputs up to one minute of video at 1440p. Users can control every shot themselves instead of \"pulling the lever on a slot machine,\" as World Labs put it, drawing a line between controlled generation and random output.","For spatial reconstruction, Atlas rebuilds real scenes from as few as one to several dozen input images without special capture equipment. The more images it receives, the less it has to fill in from its own knowledge.","With just two or three images, Atlas delivers faithful results and outperforms specialized 3D models, according to World Labs. It can also handle over a hundred inputs. In one demo, the model progressively assembles Stanford's Main Quad from two to 25 ground-level photos and generates aerial views far above the campus.","This is where existing models tend to fall apart. In a comparison within the OpenWorldLib framework：https://the-decoder.com/researchers-define-what-counts-as-a-world-model-and-text-to-video-generators-do-not/, systems like VGGT and InfiniteVGGT showed geometric inconsistencies and blurry textures as soon as the camera moved significantly.","Atlas can output results as actual 3D data, not just images or video, because it processes depth information alongside RGB. Supported formats include point clouds and 3D Gaussian splats：https://en.wikipedia.org/wiki/Gaussian_splatting, which build a scene from many small spatial data points that can be viewed smoothly from any angle. This matches the representation used in Marble, the company's existing product：https://the-decoder.com/startup-founded-by-godmother-of-ai-aims-to-give-machines-true-3d-understanding-of-the-world/.","As a simulator, Atlas models space and time together. From footage captured by just a few cameras, it can produce a \"bullet time\" effect that freezes a scene and lets users view it from otherwise impossible angles. The demo footage was shot with a handful of smartphones and action cameras, not professional gear.","For robotics, Atlas serves as a real-to-sim tool. It reconstructs a room and generates the image and depth data that a simulated robot's sensors would see along its path. From just a few photos, users can simulate and vary grasping and movement tasks by swapping out objects, positions, lighting, or backgrounds. The goal is to produce diverse training data for robots without capturing every situation in the real world.","World Labs showed this approach in August 2026 with its real-to-sim-to-real engine：https://the-decoder.com/world-labs-turns-one-real-world-robot-task-into-thousands-of-simulated-variations-for-training/ as a standalone product. That engine creates thousands of variants from a single real-world task and trains control models entirely in simulation. On five robot platforms, the models ran for an hour each without human intervention, according to the company. The technology came from SceniX, a startup World Labs acquired in July.","Text-to-image generation isn't the main focus, the company says, but Atlas can also follow complex prompts, render text, produce different visual styles, and create 360-degree panoramas.","Atlas combines ideas from both language models and video models. It generates output piece by piece like a language model, so it can use the same speedup techniques, such as KV caching. But it also uses the diffusion principle from image and video models, gradually filtering output out of noise. That side gives it access to methods that shorten the denoising process or boost image quality.","World Labs says no single benchmark captures what Atlas can do, but points to two sets of tests. In camera-controlled generation judged by external human evaluators, and in few-view 3D reconstruction, Atlas outperforms more specialized models.","Human evaluators preferred Atlas in 75 percent of comparisons against MiniMax H3：https://the-decoder.com/chinas-minimax-h3-is-the-first-open-model-to-top-an-ai-video-ranking/?cmpscreencustom=1, 81 percent against Gemini Omni Flash：https://the-decoder.com/googles-gemini-omni-1-1-flash-makes-ai-video-generation-cheaper-and-more-flexible/, 86 percent against Happy Horse 1.1, 93 percent against, and 94 percent against Seedance 2.5：https://the-decoder.com/bytedances-seedance-2-5-generates-30-second-video-clips-with-built-in-audio/. For reconstruction, Atlas leads with a median error of 25.3, ahead of Pi3X and VGGT-Ω 1B.","The company says Atlas's performance improves with more training compute and expects that trend to hold as it scales. Atlas will power future versions of Marble and other products, and is currently available through an early-access program for select partners.","World Labs was founded in 2024 by Fei-Fei Li, who created ImageNet and led Google Cloud's AI division from 2017 to 2018. The company at launch from Andreessen Horowitz, AMD, Intel, and Nvidia.","A first system in late 2024 turned, though users could only move a few virtual meters before hitting invisible boundaries. Marble followed in November 2025. In February 2026 came a $1 billion funding round：https://the-decoder.com/fei-fei-lis-world-labs-raises-one-billion-dollars-for-spatial-intelligence/ from Autodesk, Andreessen Horowitz, Nvidia, and AMD. Bloomberg had previously reported talks at a $5 billion valuation.","What counts as a world model remains contested among researchers. An international team led by Peking University proposed a unified definition：https://the-decoder.com/researchers-define-what-counts-as-a-world-model-and-text-to-video-generators-do-not/ in April 2026 through OpenWorldLib, excluding pure text-to-video models because they lack feedback loops with the real world. 3D reconstruction and simulators like those in Atlas qualify as core building blocks in that framework because they provide environments where physical rules can be verified.","Stay in the loop on AI. Clear, useful, no fluff.","Follow The Decoder for AI news, background stories and expert analyses.","The Decoder：https://the-decoder.com/"],"articleImages":[{"sourceUrl":"https://the-decoder.com/wp-content/uploads/2026/09/world-labs-atlas-01-hero.jpg","alt":"Image description","afterParagraph":0,"url":"/media/articles/cmtk2sj9l01oaron9tt7clme8/3912b0bc46556f81.jpg"},{"sourceUrl":"https://the-decoder.com/wp-content/uploads/2026/09/world-labs-atlas-02-camera-control.jpg","alt":"A three-part view showing an input image of a vine-covered cathedral, a sketched camera path, and the generated output image of the same hall from a new perspective.","afterParagraph":5,"url":"/media/articles/cmtk2sj9l01oaron9tt7clme8/ee2d1a3584a9ec58.jpg"},{"sourceUrl":"https://the-decoder.com/wp-content/uploads/2026/09/world-labs-atlas-04-aerial-reconstruction.jpg","alt":"Aerial view of the San Francisco skyline with the Transamerica Pyramid, with the street-level input photo shown as a small inset in the lower left.","afterParagraph":7,"url":"/media/articles/cmtk2sj9l01oaron9tt7clme8/ecdc4d4ae5121f01.jpg"},{"sourceUrl":"https://the-decoder.com/wp-content/uploads/2026/09/world-labs-atlas-05-point-cloud.jpg","alt":"A living room reconstructed as a point cloud with sofa, rug, and fireplace, floating above a grid floor, with marked camera positions and a blue camera path.","afterParagraph":9,"url":"/media/articles/cmtk2sj9l01oaron9tt7clme8/f3fb0c58ca4075a4.jpg"},{"sourceUrl":"https://the-decoder.com/wp-content/uploads/2026/09/world-labs-atlas-11-camera-control-preference.jpg","alt":"Dot plot with confidence intervals showing the share of human evaluators who prefer Atlas, ranging from 75 percent against MiniMax H3 to 94 percent against Seedance 2.5.","afterParagraph":16,"url":"/media/articles/cmtk2sj9l01oaron9tt7clme8/dc1d85df4e93e2f1.jpg"},{"sourceUrl":"https://the-decoder.com/wp-content/uploads/2026/09/world-labs-atlas-09-reconstruction-benchmark.jpg","alt":"Bar chart of 3D reconstruction error with Atlas at 25.3, Pi3X at 28.7, π³ at 34.7, VGGT-Ω 1B at 36.4, Depth Anything 3 at 39.3, and MapAnything at 47.7.","afterParagraph":17,"url":"/media/articles/cmtk2sj9l01oaron9tt7clme8/cf030b011d6f004f.jpg"}],"mediaStatus":"ok","articleBodyZh":["World Labs 发布世界模型 Atlas：从少量照片生成、重建并模拟 3D 世界 这条更新来自 the-decoder.com，发布时间为 2026-09-02，Aioga 保留原文入口以便核验。","摘要：World Labs（李飞飞联合创立）发布世界模型 Atlas，可从几张照片完成 3D 场景生成、重建与仿真，输出最高 1440p、1 分钟的可控镜头视频，并支持点云与 3D Gaussian splats 等 3D 数据输出。","背景：材料显示，Atlas 由 World Labs 发布；该公司由李飞飞联合创立。除视频外，模型还支持点云和 3D Gaussian splats 等 3D 数据输出。","Aioga 观察：Aioga 判断：Atlas 的公开定位集中于从有限照片构建可操作的三维场景，并同时覆盖视频与三维数据表达，核心信息是能力范围的集中呈现。","影响与后续：可能影响：相关能力若经后续材料验证，可能改变 3D 场景生成的输入与输出方式；但现有来源不足以判断生成质量、实际适用范围、用户规模或商业影响。 后续观察：应继续核对 Atlas 的公开演示、镜头控制表现、三维数据可用性和使用限制；在新增证据出现前，不应推断其市场采用情况或竞争格局变化。"],"translationStatus":"","bodyOrigin":"source-page","editorial":{"summary":"World Labs 发布世界模型 Atlas，称其可从一张至数十张照片生成、重建并模拟三维场景，并根据用户指定的相机位置和角度生成新视角。模型输出最高可达 1440p、1 分钟视频，也支持点云和 3D Gaussian splats 等三维数据。","background":"Atlas 是 World Labs 首个面向规模化空间智能的模型。公司称其从头训练于文本、图像、视频和三维数据，并将输入锚定到三维空间位置。对于场景重建，输入图像越多，模型需要自行补全的内容越少。","viewpoint":"Aioga 判断：Atlas 的核心差异在于把相机运动作为几何输入，而不是主要依赖文字描述；但目前材料中的性能比较和演示结论均主要来自 World Labs 自述，独立验证信息仍有限。","implications":"可能影响：若相关能力在更多场景中稳定成立，三维重建与可控视角生成的工作流程可能被简化；但这不代表专用模型立即失去价值，实际效果、成本和复杂场景表现仍需要进一步验证。","nextStep":"后续观察：应关注 Atlas 的公开可用范围、输入图像限制、输出质量与一致性评测，以及点云和 3D Gaussian splats 等数据能否在真实项目中稳定使用。","evidenceRefs":["title","summary","articleBody","source"],"status":"published","aiGenerated":true,"autoApproved":true,"generatedBy":"aioga-editorial:gpt-5.6-sol","reviewedBy":"aioga-editorial-review:gpt-5.6-sol","generatedAt":"2026-09-02T13:48:31.597Z","sourceHash":"f598eaec69d97a23","review":{"approved":true,"groundedness":93,"clarity":91,"duplicationRisk":18,"blockingIssues":[],"notes":["“一张至数十张照片生成、重建并模拟”略微合并了不同能力的输入范围：来源明确称场景重建可使用一张至数十张图像、可控视角生成可使用一张或多张图像，而对“模拟”能力未单独给出相同范围。可选地改为分别表述，以提高精确度。","来源还称 Atlas 可处理超过一百张输入图像；候选内容写“数十张”并非错误，但未覆盖这一能力上限。","对性能比较主要来自 World Labs 自述、仍需独立验证的提醒措辞审慎，与来源中的归因方式一致。"]},"validation":{"passed":true,"mode":"ai-auto","revisions":0,"checks":["schema","length","source-attribution","editorial-labels","inference-boundary","low-source-overlap","no-html","independent-ai-review"]}},"tags":["行业动态","The Decoder：AI News（RSS）"],"translations":{"zh-CN":{"title":"World Labs 发布世界模型 Atlas：从少量照片生成、重建并模拟 3D 世界","summary":"World Labs（李飞飞联合创立）发布世界模型 Atlas，可从几张照片完成 3D 场景生成、重建与仿真，输出最高 1440p、1 分钟的可控镜头视频，并支持点云与 3D Gaussian splats 等 3D 数据输出。","category":"行业动态","source":"the-decoder.com","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"World Labs 发布世界模型 Atlas：从少量照片生成、重建并模拟 3D 世界 - Aioga AI资讯","description":"World Labs（李飞飞联合创立）发布世界模型 Atlas，可从几张照片完成 3D 场景生成、重建与仿真，输出最高 1440p、1 分钟的可控镜头视频，并支持点云与 3D Gaussian splats 等 3D 数据输出。","url":"https://www.aioga.com/news/cmtk2sj9l01oaron9tt7clme8/","articleBody":["World Labs 发布世界模型 Atlas：从少量照片生成、重建并模拟 3D 世界 这条更新来自 the-decoder.com，发布时间为 2026-09-02，Aioga 保留原文入口以便核验。","摘要：World Labs（李飞飞联合创立）发布世界模型 Atlas，可从几张照片完成 3D 场景生成、重建与仿真，输出最高 1440p、1 分钟的可控镜头视频，并支持点云与 3D Gaussian splats 等 3D 数据输出。","背景：材料显示，Atlas 由 World Labs 发布；该公司由李飞飞联合创立。除视频外，模型还支持点云和 3D Gaussian splats 等 3D 数据输出。","Aioga 观察：Aioga 判断：Atlas 的公开定位集中于从有限照片构建可操作的三维场景，并同时覆盖视频与三维数据表达，核心信息是能力范围的集中呈现。","影响与后续：可能影响：相关能力若经后续材料验证，可能改变 3D 场景生成的输入与输出方式；但现有来源不足以判断生成质量、实际适用范围、用户规模或商业影响。 后续观察：应继续核对 Atlas 的公开演示、镜头控制表现、三维数据可用性和使用限制；在新增证据出现前，不应推断其市场采用情况或竞争格局变化。"]},"en":{"title":"Wald Labs has released the world model Atlas: generating, reconstructing, and simulating 3D worlds from a small number of photos","summary":"Wald Labs (co-founded by Li Feifei) has released the world model Atlas, which can generate 3D scenes, reconstruct, and simulate from just a few photos, output controllable footage videos up to 1440p and 1 minute, and support point clouds and 3D data such as 3D Gaussian splats.","category":"Industry","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Wald Labs has released the world model Atlas: generating, reconstructing, and simulating 3D worlds from a small number of photos - Aioga AI News","description":"Wald Labs (co-founded by Li Feifei) has released the world model Atlas, which can generate 3D scenes, reconstruct, and simulate from just a few photos, output controllable footage...","url":"https://www.aioga.com/en/news/cmtk2sj9l01oaron9tt7clme8/","contentTranslated":true,"sourceHash":"fbcaba4fd1286d9a","translatedAt":"2026-09-02T13:02:54.318Z"},"ja":{"title":"Wald Labsは、世界モデルAtlasを発表しました:少数の写真から3D世界を生成、再構築、シミュレーションする","summary":"Wald Labs(李飛飛共同設立)は、世界モデルAtlasをリリースしました。これは3Dシーンの生成、数枚の写真からの再構成・シミュレーション、最大1440p・1分の制御可能な映像出力、点群や3Dガウススプラットなどの3Dデータをサポートします。","category":"業界動向","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Wald Labsは、世界モデルAtlasを発表しました:少数の写真から3D世界を生成、再構築、シミュレーションする - Aioga AIニュース","description":"Wald Labs(李飛飛共同設立)は、世界モデルAtlasをリリースしました。これは3Dシーンの生成、数枚の写真からの再構成・シミュレーション、最大1440p・1分の制御可能な映像出力、点群や3Dガウススプラットなどの3Dデータをサポートします。","url":"https://www.aioga.com/ja/news/cmtk2sj9l01oaron9tt7clme8/","contentTranslated":true,"sourceHash":"fbcaba4fd1286d9a","translatedAt":"2026-09-02T13:02:54.531Z"},"ko":{"title":"Wald Labs는 세계 모델 아틀라스를 발표했습니다: 소수의 사진으로 3D 세계를 생성, 재구성, 시뮬레이션하는 방법","summary":"Wald Labs(리 페이페이 공동 설립)는 3D 장면을 생성하고, 몇 장의 사진만으로도 재구성 및 시뮬레이션하며, 최대 1440p와 1분 분의 제어 가능한 영상 영상을 출력하고, 점군과 3D 가우시안 스플랫과 같은 3D 데이터를 지원하는 세계 모델 아틀라스를 출시했습니다.","category":"업계 동향","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Wald Labs는 세계 모델 아틀라스를 발표했습니다: 소수의 사진으로 3D 세계를 생성, 재구성, 시뮬레이션하는 방법 - Aioga AI 뉴스","description":"Wald Labs(리 페이페이 공동 설립)는 3D 장면을 생성하고, 몇 장의 사진만으로도 재구성 및 시뮬레이션하며, 최대 1440p와 1분 분의 제어 가능한 영상 영상을 출력하고, 점군과 3D 가우시안 스플랫과 같은 3D 데이터를 지원하는 세계 모델 아틀라스를 출시했습니다.","url":"https://www.aioga.com/ko/news/cmtk2sj9l01oaron9tt7clme8/","contentTranslated":true,"sourceHash":"fbcaba4fd1286d9a","translatedAt":"2026-09-02T13:03:03.782Z"},"es":{"title":"Wald Labs ha publicado el modelo mundial Atlas: generando, reconstruyendo y simulando mundos 3D a partir de un pequeño número de fotos","summary":"Wald Labs (cofundado por Li Feifei) ha lanzado el modelo mundial Atlas, que puede generar escenas 3D, reconstruir y simular a partir de solo unas pocas fotos, generar vídeos controlables de hasta 1440p y 1 minuto, y soportar nubes de puntos y datos 3D como splats gaussianos 3D.","category":"Industria","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Wald Labs ha publicado el modelo mundial Atlas: generando, reconstruyendo y simulando mundos 3D a partir de un pequeño número de fotos - Aioga Noticias de IA","description":"Wald Labs (cofundado por Li Feifei) ha lanzado el modelo mundial Atlas, que puede generar escenas 3D, reconstruir y simular a partir de solo unas pocas fotos, generar vídeos contro...","url":"https://www.aioga.com/es/news/cmtk2sj9l01oaron9tt7clme8/","contentTranslated":true,"sourceHash":"fbcaba4fd1286d9a","translatedAt":"2026-09-02T13:03:03.876Z"},"fr":{"title":"Wald Labs a publié le modèle du monde Atlas : générer, reconstruire et simuler des mondes 3D à partir d’un petit nombre de photos","summary":"Wald Labs (cofondé par Li Feifei) a publié le modèle mondial Atlas, qui peut générer des scènes 3D, reconstruire et simuler à partir de quelques photos, produire des vidéos contrôlables jusqu’à 1440p et 1 minute, et supporter les nuages de points et les données 3D telles que les splats gaussiens 3D.","category":"Industrie","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Wald Labs a publié le modèle du monde Atlas : générer, reconstruire et simuler des mondes 3D à partir d’un petit nombre de photos - Aioga Actualités IA","description":"Wald Labs (cofondé par Li Feifei) a publié le modèle mondial Atlas, qui peut générer des scènes 3D, reconstruire et simuler à partir de quelques photos, produire des vidéos contrôl...","url":"https://www.aioga.com/fr/news/cmtk2sj9l01oaron9tt7clme8/","contentTranslated":true,"sourceHash":"fbcaba4fd1286d9a","translatedAt":"2026-09-02T13:03:13.163Z"},"de":{"title":"Wald Labs hat das Weltmodell Atlas veröffentlicht: 3D-Welten generiert, rekonstruiert und simuliert aus einer kleinen Anzahl von Fotos","summary":"Wald Labs (mitbegründet von Li Feifei) hat das Weltmodell Atlas veröffentlicht, das 3D-Szenen generieren, rekonstruieren und aus nur wenigen Fotos simulieren kann, steuerbare Aufnahmen bis zu 1440p und 1 Minute ausgeben und Punktwolken sowie 3D-Daten wie 3D-Gaußsche Splats unterstützen kann.","category":"行业动态","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Wald Labs hat das Weltmodell Atlas veröffentlicht: 3D-Welten generiert, rekonstruiert und simuliert aus einer kleinen Anzahl von Fotos - Aioga KI-News","description":"Wald Labs (mitbegründet von Li Feifei) hat das Weltmodell Atlas veröffentlicht, das 3D-Szenen generieren, rekonstruieren und aus nur wenigen Fotos simulieren kann, steuerbare Aufna...","url":"https://www.aioga.com/de/news/cmtk2sj9l01oaron9tt7clme8/","contentTranslated":true,"sourceHash":"fbcaba4fd1286d9a","translatedAt":"2026-09-02T13:03:13.207Z"},"pt-BR":{"title":"A Wald Labs lançou o modelo mundial Atlas: gerando, reconstruindo e simulando mundos 3D a partir de um pequeno número de fotos","summary":"A Wald Labs (cofundada por Li Feifei) lançou o modelo mundial Atlas, que pode gerar cenas 3D, reconstruir e simular a partir de apenas algumas fotos, gerar vídeos controláveis de até 1440p e 1 minuto, e suportar nuvens de pontos e dados 3D como splats gaussianos 3D.","category":"行业动态","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"A Wald Labs lançou o modelo mundial Atlas: gerando, reconstruindo e simulando mundos 3D a partir de um pequeno número de fotos - Aioga Notícias de IA","description":"A Wald Labs (cofundada por Li Feifei) lançou o modelo mundial Atlas, que pode gerar cenas 3D, reconstruir e simular a partir de apenas algumas fotos, gerar vídeos controláveis de a...","url":"https://www.aioga.com/pt-BR/news/cmtk2sj9l01oaron9tt7clme8/","contentTranslated":true,"sourceHash":"fbcaba4fd1286d9a","translatedAt":"2026-09-02T13:03:22.480Z"},"ru":{"title":"Wald Labs выпустила модель мира Atlas: генерация, реконструкция и симуляция 3D-миров на основе небольшого количества фотографий","summary":"Wald Labs (соучредитель Ли Фэйфэя) выпустила мировую модель Atlas, которая может генерировать 3D-сцены, реконструировать и моделировать всего на основе нескольких фотографий, выводить управляемые видео с разрешением 1440p и 1 минуту, а также поддерживать облака точек и 3D-данные, такие как 3D-гауссовские сплаты.","category":"行业动态","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Wald Labs выпустила модель мира Atlas: генерация, реконструкция и симуляция 3D-миров на основе небольшого количества фотографий - Aioga Новости ИИ","description":"Wald Labs (соучредитель Ли Фэйфэя) выпустила мировую модель Atlas, которая может генерировать 3D-сцены, реконструировать и моделировать всего на основе нескольких фотографий, вывод...","url":"https://www.aioga.com/ru/news/cmtk2sj9l01oaron9tt7clme8/","contentTranslated":true,"sourceHash":"fbcaba4fd1286d9a","translatedAt":"2026-09-02T13:03:22.506Z"},"ar":{"title":"أصدرت مختبرات والد نموذج العالم أطلس: توليد وإعادة بناء ومحاكاة عوالم ثلاثية الأبعاد من عدد قليل من الصور","summary":"أطلقت شركة Wald Labs (التي شارك في تأسيسها لي فيفي) نموذج العالم Atlas، الذي يمكنه توليد مشاهد ثلاثية الأبعاد، وإعادة بناءها، ومحاكاتها من خلال عدد قليل من الصور فقط، وإخراج فيديوهات لقطات قابلة للتحكم بدقة تصل إلى 1440p ودقيقة واحدة، ودعم سحب نقاط وبيانات ثلاثية الأبعاد مثل القطع الغاوسية ثلاثية الأبعاد.","category":"行业动态","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"أصدرت مختبرات والد نموذج العالم أطلس: توليد وإعادة بناء ومحاكاة عوالم ثلاثية الأبعاد من عدد قليل من الصور - Aioga أخبار الذكاء الاصطناعي","description":"أطلقت شركة Wald Labs (التي شارك في تأسيسها لي فيفي) نموذج العالم Atlas، الذي يمكنه توليد مشاهد ثلاثية الأبعاد، وإعادة بناءها، ومحاكاتها من خلال عدد قليل من الصور فقط، وإخراج فيديوه...","url":"https://www.aioga.com/ar/news/cmtk2sj9l01oaron9tt7clme8/","contentTranslated":true,"sourceHash":"fbcaba4fd1286d9a","translatedAt":"2026-09-02T13:03:31.455Z"},"hi":{"title":"वाल्ड लैब्स ने विश्व मॉडल एटलस जारी किया है: तस्वीरों की एक छोटी संख्या से 3 डी दुनिया को उत्पन्न करना, पुनर्निर्माण करना और अनुकरण करना","summary":"वाल्ड लैब्स (ली फेइफी द्वारा सह-स्थापित) ने विश्व मॉडल एटलस जारी किया है, जो 3 डी दृश्य उत्पन्न कर सकता है, पुनर्निर्माण कर सकता है, और केवल कुछ तस्वीरों से अनुकरण कर सकता है, 1440p और 1 मिनट तक नियंत्रणीय फुटेज वीडियो आउटपुट कर सकता है, और समर्थन बिंदु बादलों और 3 डी डेटा जैसे 3 डी गाऊसी स्प्लैट्स।","category":"行业动态","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"वाल्ड लैब्स ने विश्व मॉडल एटलस जारी किया है: तस्वीरों की एक छोटी संख्या से 3 डी दुनिया को उत्पन्न करना, पुनर्निर्माण करना और अनुकरण करना - Aioga AI समाचार","description":"वाल्ड लैब्स (ली फेइफी द्वारा सह-स्थापित) ने विश्व मॉडल एटलस जारी किया है, जो 3 डी दृश्य उत्पन्न कर सकता है, पुनर्निर्माण कर सकता है, और केवल कुछ तस्वीरों से अनुकरण कर सकता है, 1440...","url":"https://www.aioga.com/hi/news/cmtk2sj9l01oaron9tt7clme8/","contentTranslated":true,"sourceHash":"fbcaba4fd1286d9a","translatedAt":"2026-09-02T13:03:31.924Z"},"it":{"title":"Wald Labs ha pubblicato il modello mondiale Atlas: generare, ricostruire e simulare mondi 3D a partire da un piccolo numero di foto","summary":"Wald Labs (co-fondato da Li Feifei) ha rilasciato il modello mondiale Atlas, che può generare scene 3D, ricostruire e simulare da poche foto, produrre video controllabili fino a 1440p e 1 minuto, e supportare point cloud e dati 3D come gli splat gaussiani 3D.","category":"行业动态","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Wald Labs ha pubblicato il modello mondiale Atlas: generare, ricostruire e simulare mondi 3D a partire da un piccolo numero di foto - Aioga Notizie IA","description":"Wald Labs (co-fondato da Li Feifei) ha rilasciato il modello mondiale Atlas, che può generare scene 3D, ricostruire e simulare da poche foto, produrre video controllabili fino a 14...","url":"https://www.aioga.com/it/news/cmtk2sj9l01oaron9tt7clme8/","contentTranslated":true,"sourceHash":"fbcaba4fd1286d9a","translatedAt":"2026-09-02T13:03:41.150Z"},"nl":{"title":"Wald Labs heeft het wereldmodel Atlas uitgebracht: het genereren, reconstrueren en simuleren van 3D-werelden uit een klein aantal foto's","summary":"Wald Labs (mede opgericht door Li Feifei) heeft het wereldmodel Atlas uitgebracht, dat 3D-scènes kan genereren, kan reconstrueren en simuleren vanaf slechts een paar foto's, beheersbare beelden tot 1440p en 1 minuut kan uitvoeren, en puntwolken en 3D-data zoals 3D Gaussische splats' kan ondersteunen.","category":"行业动态","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Wald Labs heeft het wereldmodel Atlas uitgebracht: het genereren, reconstrueren en simuleren van 3D-werelden uit een klein aantal foto's - Aioga AI-nieuws","description":"Wald Labs (mede opgericht door Li Feifei) heeft het wereldmodel Atlas uitgebracht, dat 3D-scènes kan genereren, kan reconstrueren en simuleren vanaf slechts een paar foto's, beheer...","url":"https://www.aioga.com/nl/news/cmtk2sj9l01oaron9tt7clme8/","contentTranslated":true,"sourceHash":"fbcaba4fd1286d9a","translatedAt":"2026-09-02T13:03:41.239Z"},"tr":{"title":"Wald Labs, az sayıda fotoğraftan 3D dünyalar oluşturmak, yeniden yapılandırmak ve simülasyon yapmak üzere dünya modeli Atlas'ı yayımladı","summary":"Wald Labs (Li Feifei'nin ortak kurucusudur), sadece birkaç fotoğraftan 3D sahneler üretebilen, yeniden yapılandırabilen ve simüle edebilen, 1440p ve 1 dakikaya kadar kontrol edilebilir görüntü videoları üretebilen, nokta bulutları ve 3D Gauss splats gibi 3D verileri destekleyen dünya modeli Atlas'ı piyasaya sürdü.","category":"行业动态","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Wald Labs, az sayıda fotoğraftan 3D dünyalar oluşturmak, yeniden yapılandırmak ve simülasyon yapmak üzere dünya modeli Atlas'ı yayımladı - Aioga AI Haberleri","description":"Wald Labs (Li Feifei'nin ortak kurucusudur), sadece birkaç fotoğraftan 3D sahneler üretebilen, yeniden yapılandırabilen ve simüle edebilen, 1440p ve 1 dakikaya kadar kontrol edileb...","url":"https://www.aioga.com/tr/news/cmtk2sj9l01oaron9tt7clme8/","contentTranslated":true,"sourceHash":"fbcaba4fd1286d9a","translatedAt":"2026-09-02T13:03:50.428Z"},"vi":{"title":"Wald Labs đã phát hành Atlas mô hình thế giới: tạo ra, tái tạo và mô phỏng thế giới 3D từ một số ít ảnh","summary":"Wald Labs (đồng sáng lập bởi Li Feifei) đã phát hành mô hình thế giới Atlas, có thể tạo ra các cảnh 3D, tái tạo và mô phỏng chỉ từ một vài bức ảnh, xuất ra video có thể điều khiển lên đến 1440p và 1 phút, đồng thời hỗ trợ đám mây điểm và dữ liệu 3D như các splat Gaussian 3D.","category":"行业动态","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Wald Labs đã phát hành Atlas mô hình thế giới: tạo ra, tái tạo và mô phỏng thế giới 3D từ một số ít ảnh - Tin tức AI Aioga","description":"Wald Labs (đồng sáng lập bởi Li Feifei) đã phát hành mô hình thế giới Atlas, có thể tạo ra các cảnh 3D, tái tạo và mô phỏng chỉ từ một vài bức ảnh, xuất ra video có thể điều khiển...","url":"https://www.aioga.com/vi/news/cmtk2sj9l01oaron9tt7clme8/","contentTranslated":true,"sourceHash":"fbcaba4fd1286d9a","translatedAt":"2026-09-02T13:03:50.532Z"},"id":{"title":"Wald Labs telah merilis model dunia Atlas: menghasilkan, merekonstruksi, dan mensimulasikan dunia 3D dari sejumlah kecil foto","summary":"Wald Labs (yang didirikan bersama Li Feifei) telah merilis model dunia Atlas, yang dapat menghasilkan adegan 3D, merekonstruksi, dan mensimulasikan hanya dari beberapa foto, menghasilkan video rekaman yang dapat dikontrol hingga 1440p dan 1 menit, serta mendukung awan titik dan data 3D seperti splat Gaussian 3D.","category":"行业动态","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Wald Labs telah merilis model dunia Atlas: menghasilkan, merekonstruksi, dan mensimulasikan dunia 3D dari sejumlah kecil foto - Berita AI Aioga","description":"Wald Labs (yang didirikan bersama Li Feifei) telah merilis model dunia Atlas, yang dapat menghasilkan adegan 3D, merekonstruksi, dan mensimulasikan hanya dari beberapa foto, mengha...","url":"https://www.aioga.com/id/news/cmtk2sj9l01oaron9tt7clme8/","contentTranslated":true,"sourceHash":"fbcaba4fd1286d9a","translatedAt":"2026-09-02T13:03:59.642Z"},"th":{"title":"Wald Labs ได้เปิดตัว Atlas โมเดลโลก: การสร้าง การจําลอง และจําลองโลก 3 มิติจากภาพถ่ายจํานวนน้อย","summary":"Wald Labs (ร่วมก่อตั้งโดย Li Feifei) ได้ปล่อยโมเดลโลก Atlas ซึ่งสามารถสร้างฉาก 3 มิติ สร้างภาพใหม่ และจําลองจากภาพถ่ายเพียงไม่กี่ภาพ ส่งออกวิดีโอที่ควบคุมได้ถึง 1440p และ 1 นาที และรองรับเมฆจุดและข้อมูล 3 มิติ เช่น 3D Gaussian splats","category":"行业动态","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Wald Labs ได้เปิดตัว Atlas โมเดลโลก: การสร้าง การจําลอง และจําลองโลก 3 มิติจากภาพถ่ายจํานวนน้อย - ข่าว AI Aioga","description":"Wald Labs (ร่วมก่อตั้งโดย Li Feifei) ได้ปล่อยโมเดลโลก Atlas ซึ่งสามารถสร้างฉาก 3 มิติ สร้างภาพใหม่ และจําลองจากภาพถ่ายเพียงไม่กี่ภาพ ส่งออกวิดีโอที่ควบคุมได้ถึง 1440p และ 1 นาที แล...","url":"https://www.aioga.com/th/news/cmtk2sj9l01oaron9tt7clme8/","contentTranslated":true,"sourceHash":"fbcaba4fd1286d9a","translatedAt":"2026-09-02T13:03:59.674Z"},"pl":{"title":"Wald Labs wydało model świata Atlas: generowanie, rekonstrukcję i symulację światów 3D na podstawie niewielkiej liczby zdjęć","summary":"Wald Labs (współzałożone przez Li Feifei) wypuściło model świata Atlas, który potrafi generować sceny 3D, rekonstruować i symulować na podstawie zaledwie kilku zdjęć, generować kontrolowane nagrania wideo do 1440p i 1 minuty oraz wspierać chmury punktów i dane 3D, takie jak 3D splaty Gaussa.","category":"行业动态","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Wald Labs wydało model świata Atlas: generowanie, rekonstrukcję i symulację światów 3D na podstawie niewielkiej liczby zdjęć - Aioga Wiadomości AI","description":"Wald Labs (współzałożone przez Li Feifei) wypuściło model świata Atlas, który potrafi generować sceny 3D, rekonstruować i symulować na podstawie zaledwie kilku zdjęć, generować kon...","url":"https://www.aioga.com/pl/news/cmtk2sj9l01oaron9tt7clme8/","contentTranslated":true,"sourceHash":"fbcaba4fd1286d9a","translatedAt":"2026-09-02T13:04:08.960Z"}},"evidenceTier":"verified-news","reviewStatus":"automated-ingest","indexable":true,"editorialCover":""}}