Stay informed
Get industry news delivered to your inbox…
Register today
Search giant Google has unveiled its Genie 2 AI tool, capable of generating a wide range of playable and action-controllable 3D environments from single-frame prompts.
According to the Deep Mind ReportGenie 2 can create various perspectives, such as first-person, isometric, or third-person views, and produce complex 3D scenes with interactive elements like doors and explosive barrels.
Genie 2 can also prototype physical effects such as smoke, gravity, lighting and reflections, which can be played by both humans and AI agents using a keyboard and mouse .
Google said the AI tool will allow artists and designers to speed up the prototyping process, which “can begin the creative process for environment design, thereby speeding up research.”
The role of games in advancing AI research
“Games play a key role in the world of artificial intelligence (AI) research,” the report explains. Their engaging nature, unique mix of challenges, and measurable progress make them ideal environments to safely test and advance AI capabilities. »
“With Genie 2’s out-of-distribution generalization capabilities, concept art and designs can be transformed into fully interactive environments. This allows artists and designers to quickly create prototypes, which can speed up the creative process of designing the environment, further speeding up research.
“While this research is still in its early stages and there is substantial room for improvement in agent and environment generation capabilities, we believe that Genie 2 is the way forward to solve a problem “structural framework for training embodied agents safely while achieving the scale and generality required to progress toward AGI.”