PANews, December 3 - World Labs, a spatial intelligence company founded by Stanford University professor Fei-Fei Li, announced the development of an AI system that can generate a complete 3D world from a single input image, addressing the lack of control and consistency in existing generative AI models. This system can not only estimate 3D geometric shapes but also fill in unseen parts of the scene to create new content, allowing users to freely explore 3D scenes in a game-like manner.
The generated 3D scenes support real-time rendering in a browser, allowing for the simulation of 3D camera effects such as shallow depth of field and dolly zoom. Compared to pixel prediction generative models, this system adheres to 3D geometric rules, ensuring consistency in the scene and supporting dynamic interactions, such as modifying lighting, appearance, and inserting new objects.
