Google DeepMind's Genie 2 can generate interactive 3D worlds

image via Engadget

December 5, 2024, 8:07 PM

• •Genie 2 is a diffusion model that generates images as the player moves through the world the software is simulating.
• •The model can remember parts of a simulated scene even after they leave the player’s field of view and can accurately reconstruct those elements once they become visible again.
• •DeepMind says the model can generate “consistent” worlds for up to 60 seconds, with the majority of the examples the company shared on Wednesday running for significantly less time; in this case, most of the videos are about 10 to 20 seconds long.

Google DeepMind has announced Genie 2, an AI model that can create an endless variety of playable 3D worlds from a single image. The model can generate consistent worlds for up to 60 seconds, and can remember parts of a simulated scene even after they leave the player's field of view.

Read original article