TGViewer
Startups & Ventures Startups & Ventures @tech · 2.19M subscribers
Post #3840 6.1K
📍 World Labs Unveils 3D Model Atlas

Atlas reconstructs a surrounding space in 3D from text or visual files. Users can then move the camera and change the view while the scene geometry stays intact.

With several photos, it builds a complete 3D space. From one image, it can infer hidden parts, while more source frames improve accuracy. Atlas also generates controllable video up to 1 minute in 1440p, with the camera path set directly. The same system can turn footage of a real room into a simulation for robot training.

Atlas is currently available only to early-access partners. It will later serve as the basis for new versions of Marble and other World Labs products.

📊@tech
  • 🤩 488
  • ❤ 429
  • 👍 9
More from @tech
  1. Oct 5, 2026Ⓜ️ Meta Opens Muse to DIY Devices Meta’s open-source platform connects the Muse AI agent t…
  2. Oct 5, 2026🤖 Anthropic Studies AI Morality Since autumn 2025, Anthropic co-founder Chris Olah has he…
  3. Oct 5, 2026🔍 Google puts 4 TPUs in orbit Project Suncatcher launched on 1 October aboard a SpaceX ro…
  4. Oct 4, 2026🤖 GPT-6.1 Astra May Arrive Next Week Thibault and other OpenAI developers are hinting at…
  5. Oct 4, 2026🙂‍↔️ DeepSeek Brings Harness to Desktop Harness is available for macOS and Windows as an…
  6. Oct 4, 2026🔗 AI Progress Could Compress Years A Cambridge paper by 22 authors, including Geoffrey Hi…
Threads Profile ViewerView any public Threads profile without an account.Open ThreadLook →Writing with AI? Make it sound human.Metric37 rewrites AI drafts so they read naturally. Free AI detector, 1,500 words free.Try Metric37 →