Generative AI Environments

Next wave of generative AI

Generative AI Environments


Generative AI has undergone remarkable progress in recent years, with the quality of AI-generated text and imagery today continuing to amaze. Other data modalities are following. The most ambitious, perhaps, is to fully generate 3D environments.

The first step to generative environments is what we call a 2+1D approach, where generated 2D imagery is augmented with 1D depth information. Leveraging our recent research, published in the premiere deep learning conferences, we can realize generative 2+1D environments today, as we work towards full AI generated 3D environments.

AI generated 360 panoramas

    Text to 360° panoramic images

    Try our alpha release. Major improvements in quality compared to our pre-alpha, with further improvements coming soon!



    Download

    Turn your 360° image into a 2+1D environment (panoramic + depth) using copernic360.

    License

    Generated 360° images can be used freely for commercial and non-commercial use, following the Creative ML OpenRAIL-M license.

    AI generated 2+1D environments

    Create 2+1D environments (panoramic + depth) from 360° images and video with copernic360.

    Explore CopernicAI environments in VR

    Sidequest

    For the Quest headset (contact us for other headsets).

    Roadmap

    • Efficient Panoramic AI

      Published in ICLR 2021

      Efficient techniques providing significant improvements in computational complexity and state-of-the-art performance on low-resolution tasks. But still limited to very low-resolution.

    • Partially Scalable Panoramic AI

      Published in ICLR 2022

      High-resolution input data but only low-resolution output data. Applicable for classical AI tasks with low resolution outputs (e.g. image classification, object detection and tracking).

    • Scalable Panoramic AI

      Published in ICLR 2023

      High-resolution input and output data. Achieves state-of-the-art for dense-prediction tasks (e.g. semantic segmentation, depth estimation). Building blocks for Generative Panoramic AI.

    • Generative Panoramic AI

      Under Development

      Generative AI panoramic images and videos using Scalable Panoramic AI building blocks. Early pre-alpha available now, with major improvements coming soon…

    • Generative AI Environments

      Next!

      Generative AI for 2+1D (panoramic + depth) environments. Early pre-alpha through copernic360 available now, with major improvements coming soon and full 3D environments next.



    Learn more about our R&D in our blog posts in Towards Data Science and Towards AI.

    Sign-up

    Drop us your email if you would like to receive updates and announcements…
    and an invitation to the upcoming closed alpha release of CopernicAI.

    (We will never pass your email on to other parties.)