Google Deepmind Genie 3 is a New Frontier for World Models
Google DeepMind Tuesday released Genie 3, a general purpose world model, that the tech giant said, can generate an unprecedented diversity of interactive environments
[Screenshot of Genie Intro Video]
Google DeepMind Tuesday released Genie 3, a general purpose world model, that the tech giant said, can generate an unprecedented diversity of interactive environments.
As per Google, Genie 3 can create 3D spaces where both humans and AI agents can move and interact in real time.
The new model also aims to deliver longer and more realistic experiences, with the ability to remember where objects are placed even if you look away and return later.
"Given a text prompt, Genie 3 can generate dynamic worlds that you can navigate in real time at 24 frames per second, retaining consistency for a few minutes at a resolution of 720p", Google said in a blog post.
Genie 3 Features, Capabilities
- Modelling physical properties of the world
- Simulating the natural world
- Modelling animation and fiction
- Exploring locations and historical settings
- Pushing the frontier of real-time capabilities
- Environmental consistency over a long horizon
Genie 3’s consistency is an emergent capability. Other methods such as NeRFs and Gaussian Splatting also allow consistent navigable 3D environments, but depend on the provision of an explicit 3D representation.
"By contrast, worlds generated by Genie 3 are far more dynamic and rich because they’re created frame by frame based on the world description and actions by the user", DeepMind said.
Genie 3 Earlier Versions
DeepMind had last year introduced the first foundation world models with Genie 1 and Genie 2, which could generate new environments for agents.
"Genie 3 is our first world model to allow interaction in real-time, while also improving consistency and realism compared to Genie 2", the company said.
"We have also continued to push the state of the art in video generation with our models Veo 2 and Veo 3, which exhibit a deep understanding of intuitive physics", DeepMind said.
Genie 3 will not be open to the public right away. DeepMind is rolling out Genie 3 as a limited research preview for a small group of academics and creators to study possible risks and decide on safety measures.
Follow ummid.com WhatsApp Channel for all the latest updates.
Select Language to Translate in Urdu, Hindi, Marathi or Arabic
