Microsoft Hololens headset with black background

Mixed Reality & AI Lab – Cambridge

This image contains two panels. The panel on the left is titled “3D face reconstruction” and depicts two faces of real people and corresponding face models developed using the dense landmarks method with 703 facial landmarks. The panel on the right is titled “Benchmarking localization and mapping for AR” and shows the interior of a building with paths—or sequences—where people had captured the environment using Microsoft HoloLens.

ECCV 2022 highlights: Advancing the foundations of mixed reality

3D Face Reconstruction with Dense Landmarks

Neural rendering offers new ways to represent ourselves remotely

synthetic image of a man rendered with computer graphics

Realistic synthetic training data enables rapid AI advances

The Microsoft Mixed Reality & AI Lab – Cambridge sits at the forefront of research, hardware, and software development in the field of social presence in mixed reality. We build the AI technology that powers Microsoft Mesh, spanning the presence spectrum from avatars, through to holoportation, to digitization of objects and environments, and spanning the incubation lifecycle from research prototypes to shipping products.

We combine insights in computer vision, machine learning and graphics to understand the motion, shape, and appearance of a user, and recreate their likeness remotely. As a diverse, multidisciplinary team, we approach our work not just as an exciting technological opportunity, but also as a responsibility to develop new mediums of 3D communication in an inclusive and ethical way. We collaborate very closely with design, art, engineering and program management teams to build the best solutions for our customers!

The Mixed Reality & AI Lab – Cambridge sits alongside Microsoft Research Lab – Cambridge, and works closely with the partner team in Zurich.

The lab is currently recruiting diverse, world-class expertise across computer vision, graphics, machine learning, experience, and software engineering. You can find current openings on the Career opportunities tab.

Our focus areas

Tracking of human faces, bodies, and hands, parametric models of human appearance, Gaussian splatting, temporal models of human motion, multimodal foundational models, 3D reconstruction, holoportation, avatars

Thoughts from our team

“I love that my job provides a continuous source of learning, I work with colleagues whom I can learn from, and we get to solve together fascinating real-world problems.”
– Virginia Estellers, Senior Scientist

“Working at the intersection of machine learning, 3D computer vision and speech processing, my work with an amazing team of scientists and engineers has helped me grow both my research and software engineering skills.”
– John Olafenwa, Scientist