fourpiAI
Geometric AI for the metaverse of the future
Today’s AI techniques have shown remarkable performance and are changing the world in which we live. However, standard deep learning techniques simply do not work for scenarios involving complex geometries, such as the metaverse.
Kagenova has developed the fourpiAI platform, delivering geometric AI to power the metaverse of the future.
Features
In fourpiAI, Kagenova has built efficient geometric AI techniques for 360° data from the ground up. Our approach retains the symmetries of the sphere, eliminates any distortions due to projections, encodes rotational equivariance as a powerful inductive bias, and is scalable.
Learn more about the technical details in our research articles.
Preserve symmetries
Eliminate distortions
Rotational equivariance
Scalable
Usage
fourpiAI powers our copernic360 and copernic worlds products that take first steps towards delivering photorealism and interactivity in virtual reality.
fourpiAI provides underlying geometry AI techniques that can be leveraged to solve many computer vision problems for 360° data, such as classification, depth estimation, semantic segmentation, and object detection and tracking, to name just a few. Please get in touch to discuss your use case.
Get in touch
Do you want to find out more about fourpiAI? Do you already have applications in mind? Let us know!