Generating realistic images from a text description is a challenging task for a bot. A solution to this task has potential applications in the video game and image editing industries, among many others. Recently, researchers…
The notion of an “uncanny valley” is well known in robotics[1]. This is when increasing the realism of a robot’s human-like appearance can lead to feelings of unease—or even revulsion—as a robot becomes more and…
Networks, applications, and media codecs frequently treat one another as strangers. By expressing large systems as compositions of small, pure functions, we’ve found it’s possible to achieve tighter couplings between these components, improving performance without…
Two topics are addressed in this talk. Sound field capturing is aimed at interpolating and reconstructing a spatial acoustic filed with multiple microphones, which can be applied to high fidelity audio playback using loudspeakers or…
I will be talking about some of my recent work on reconstructing faces, materials and 360 environments from images and videos. The projects I will talk about are published at IEEE VR 2018, and others…
Demonstration of Live 360 degrees Audio and Video Streaming during Microsoft Research TechFest, as well as at ICASSP and Interspeech conferences. Designed by members of the Audio and Acoustics Research Group and Microsoft Research Hardware…
The Microsoft Research Redmond Lab’s Central Engineering Team develops software and hardware technologies and components based on Microsoft Research innovations.
Last week’s rollout of SwiftKey 7.0 is the intelligent keyboard app’s biggest update since joining Microsoft in April 2016. Available on both Android and iOS, SwiftKey 7.0 debuts Toolbar, an expandable menu found under a…
Today’s update from Microsoft debuts a new feature for its intelligent camera app, Microsoft Pix, that works with LinkedIn, showcasing the productivity capabilities of the AI-powered camera. The new Business Card feature for iPhones makes…
