World Labs' Atlas Turns a Single Photo Into a Fully Explorable 3D World
Matt Wolfe · youtube · 2026-09-09
World Labs' new Atlas model reconstructs an entire 3D environment from just one photo, letting users freely control the camera and explore from new angles — not an AI video, but a navigable world. It can also combine multiple images into one larger, explorable scene, as shown in Matt Wolfe's demo video.
More from Multimodal
- Hi3D V1.0 open-sourced with 2M training assets and 90% slicing success rate — kimmonismus · 2026-10-26
- Claude Can Replace Your YouTube Thumbnail Designer in 10 Minutes — thedankoe · 2026-10-26
- Multimodal AI Is Not Useless: A Practitioner Pushes Back on Growing Skepticism — thoma_gu · 2026-10-26
- One prompt, full Blender animation: dev says he never touched Blender once — iamfakhrealam · 2026-10-26
- Dense instance segmentation via Muse Wonder + SAM 3.1 on Meta's Model API — nikhilaravi · 2026-10-26
- LichtFeld Studio v0.5.4.3 ships community-built SteadySplats, POPSpa and Voxelization — janusch_patas · 2026-10-26