Enabling computers and devices to understand what they see.
Microsoft’s Cloud Operations & Innovation (CO+I) is the engine that powers our cloud services. As a datacenter Simulation Expert, you will perform a key role in delivering the core infrastructure and foundational technologies for Microsoft’s…
We are seeking Research Interns in Computer Vision, Machine Learning and Robotics, broadly defined, for our Spatial AI Lab in Zurich. As an intern, you will collaborate with one or more mentors and use the…
The Interactive Multimodal AI Systems (IMAIS) group at Microsoft Research seeks a Research Intern to work on a project related to Situated Intelligence. The Situated Intelligence research effort aims to enable computers to reason about the physical everyday world,…
The Microsoft Spatial AI Lab in Zurich, Switzerland, is a research and development team building the future of spatial computing. We are looking for computer vision and machine learning scientists who share our passion for…
The Microsoft Spatial AI Lab in Zurich, Switzerland, is a research and development team building the future of spatial computing. We are looking for computer vision and machine learning scientists who share our passion for…
The Microsoft Applied Sciences Group incubates disruptive technologies for Microsoft’s next-gen Windows and Surface products. Operating as a startup within the company, this team works closely with several research and product teams to bring compelling…
The Microsoft Applied Sciences Group incubates disruptive technologies for Microsoft’s next-gen Windows and Surface products. Operating as a startup within the company, this team works closely with several research and product teams to bring compelling…
We present a method for prediction of a person’s hairstyle from a single image. Despite growing use cases in user digitization and enrollment for virtual experiences, available methods are limited, particularly in the range of…
We tackle the problem of highly-accurate, holistic performance capture for the face, body and hands simultaneously. Motion-capture technologies used in film and game production typically focus only on face, body or hand capture independently, involve…
OmniParser is a comprehensive method for parsing user interface screenshots into structured and easy-to-understand elements, which significantly enhances the ability of GPT-4V to generate actions that can be accurately grounded in the corresponding regions of…
