Link: World Labs, founded by Fei-Fei Li, gives an "early preview" of its first project, an AI system that generates game-like, 3D scenes from a single image (Kyle Wiggers/TechCrunch)

World Labs has developed an AI that can transform a single photo into an interactive 3D environment. This innovation was announced by the startup, founded by AI pioneer Fei-Fei Li.

The AI's unique feature is its interactivity, allowing users to modify and explore the generated scenes as if they were in a video game. These scenes are live-rendered in a browser with control over the camera and depth of field.

Unlike other AI-generated 3D models that suffer from artifacting, World Labs' creations maintain their layout and adhere to physical laws, enhancing realism. The AI can also introduce dynamic effects like lighting changes and color adjustments.

These interactive environments are aimed at revolutionizing industries such as gaming and film production, offering a more robust and cost-effective tool for professionals. Currently, users can only explore a limited area in the demos with occasional rendering errors, highlighting areas for future improvement.

Since its launch, World Labs has secured $230 million in funding from notable investors including Andreessen Horowitz and Eric Schmidt. They plan to expand their offerings to professionals in various creative fields, aiming for a broader application of their technology.

With a product launch planned for 2025, World Labs continues to refine their AI to create larger, more detailed virtual worlds, promising new ways for user interaction in digital settings.

 #

--

Yoooo, this is a quick note on a link that made me go, WTF? Find all past links here.