World Labs pre-trains Atlas to turn multimodal inputs into 3D views
Original titleWe pre-trained Atlas from scratch to take multimodal inputs, including camera movement, and turn it into 3D grounded views.
AISummary
World Labs says it pre-trained Atlas from scratch to accept multimodal inputs, including camera movement, and convert them into 3D-grounded views. The company says Atlas lets users direct views, reconstruct real spaces from their inputs, and build explorable worlds.
Source: World Labs · x.comPublished · added here