6D.ai co-founder Victor (left) with Apple CEO Tim Cook, showcasing an early prototype of 6D.ai technology.
It is an exciting time to build an AR app. The release of ARCore and ARKit in addition to recent hardware improvements have made it easier than ever. However, there are still major limitations and constraints that can keep you from building an AR app that is true to your vision. Ideal conditions are still indoors on a table top. Objects still don't quite feel like they are a persistent part of the real world. Multiplayer experiences are a pain to implement.
6D.ai helps developers build AR apps that users would find meaningful, useful and exciting.
Founded in 2017, 6D.ai was spun out from Oxford University’s Active Vision Lab, building APIs to help developers augment reality in ways that users would find meaningful, useful and exciting. The 6D.ai SDK uses a standard built-in smartphone camera to build a cloud-based, crowdsourced three-dimensional semantic map of the world all in real-time, in the background.
Our goal with the 6D.ai SDK is to enhance the AR apps you build, helping them interact with the world in a natural and realistic way. Current AR limits a user to a small area, where content is lost as soon as an app is closed. Devices using the 6D.ai platform will be able to have a deeper understanding of the world around a user. Our goal is to publish an SDK that will allow you to create apps at room, house, city, or even world scale, with assets that go around and behind objects, that remember what a user did weeks, months, or even years ago.
We have a lot of work ahead of us, but are shipping improvements multiple times a month. Our private beta currently has the following features:
Real time 3D mesh reconstruction: The first ever real-time, high-fidelity 3D reconstruction from monocular RGB capability in the industry! We call this feature "meshing" as it outputs, several times a second, an updated 3D mesh of the environment around the user.
Just like relocalization enables multiplayer and persistence, meshing enables critical augmented reality features: occlusion, physics, real world interaction, and procedural augmentation.
Real time object occlusion: In 3D graphic design, occlusion is the effect of one object in a 3D space blocking another object from view. Our mesh allows for this type of interaction between AR objects and real world objects. This helps you create powerful, natural feeling, experiences for your augmented reality app.
We have two sample apps you can build which will demonstrate our real time mesh and occlusion of objects - the Meshing Sample App and the Ball Pit Sample App.