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.


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



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.