Google's Genie 2 AI tool can generate a playable 3D world from a "single prompt image"

Genie 2 transforms single images into interactive 3D environments, enabling rapid prototyping for designers and accelerating creative workflows. This capability allows concept art to become playable worlds, significantly streamlining the initial stages of environment design. The technology supports diverse perspectives and complex physics, allowing both humans and AI agents to interact with generated scenes. By facilitating safe, large-scale training for embodied agents, it addresses structural challenges in developing general artificial intelligence. This advancement is crucial for open data as it demonstrates how generative models can create synthetic, accessible training environments. Such tools democratize access to complex simulation data, fostering innovation in AI research without requiring expensive real-world datasets or physical infrastructure.

Source: gamesindustry.biz
Published on 2024-12-06

Google DeepMind and World Labs unveil AI tools to create 3D spaces from simple prompts »

Open Data

Related news