Google has developed a new artificial intelligence tool that can generate a fully playable 3D game world from a single image.
Genie 2, as the tool is known, is described as a “global model.” So where Genie 1 generated 2D worlds, this later tool can create 3D worlds in a variety of perspectives and includes the consequences of performing actions like jumping or swimming.
Google emphasizes that the tool can be used for “rapid prototyping,” as it “allows artists and designers to create prototypes quickly, which can boost the creative process for environment design, further accelerating research.”
It works using a single image message, and Google of course uses examples from its own text-to-image AI tool, Image 3, although real-world images can also be used.
From there, users can jump around and interact with the world, and the AI overcomes challenges like understanding control inputs and remembering the world that was created as the camera pans elements in and out of view. It then generates new plausible content on the fly for up to one minute of gameplay.
You can spawn even more NPCs and interactions with them; the physics of water or gravity; lighting and reflection models; and multiple animations.
“While this research is still in its early stages and there is substantial room to improve agent and environment generation capabilities, we believe that Genie 2 is the way to solve the structural problem of training embedded agents safely and at the same time. time to achieve the breadth and generality necessary to move towards AGI [Artificial General Intelligence]” reads a blog post about the Google tool.
So while the tool can be used for prototyping, it is also used to train more AI models.
Discussing how Google developed the technology responsibly, the blog post says: “Genie 2 shows the potential of fundamental world models to create diverse 3D environments and accelerate agent research. This research direction is in its early stages and we look forward to continuing to improve Genie’s technology-leading capabilities in terms of generality and consistency.
“As with SIMA [Scalable Instructable Multiworld Agent]”Our research is moving toward more general AI systems and agents that can safely understand and carry out a wide range of tasks in a way that is useful to people online and in the real world.”
As such, its purpose so far does not appear to be directly in video game development, although the potential is clear.
In fact, AI is changing video game development with its use in multiple areas, from NPCs to scriptwriting and voice acting.
Several studies have already expressed their interest in artificial intelligence technology, both for and against. More recently, PlayStation co-CEO Hermen Hulst stated that AI technology has the ability to “revolutionize” the gaming industry, but it will not replace the “human touch.”
