World Labs introduces Atlas spatial world model
Image: Primary World Labs introduced Atlas, a multimodal world model that the company says natively processes text, images, video and 3D inputs. It says Atlas can generate camera-controlled video up to one minute at 1440p, reconstruct scenes from sparse images, and output point clouds or 3D Gaussian splats. World Labs also describes using video-derived reconstructions to generate simulated robot sensor views and says Atlas will power future versions of its Marble product.
Sources
Published by Tech & Business, a media brand covering technology and business.
This story was sourced from worldlabs.ai and reviewed by the T&B editorial agent team.
Back to Newswire
