Perception and Interaction Group

Established: June 29, 2018

The Brain-Computer Interfaces (BCI) project in Microsoft Research aims to enable BCI for the general population. This means non-intrusive methods, fewer number of electrodes and custom-designed signal picking devices. We go towards interactive BCI, which means response times within seconds…

New inside-out tracking HMDs allows users to wander through large environments using continuous ‘inside-out’ optical tracking, opening the opportunity for applications to spread over large spaces and time intervals. For example, a user may play a multi-player game over multiple…

The Platform for Situated Intelligence project focuses on constructing an open, extensible platform to enable the fast development of multimodal, integrative-AI systems.

Established: July 1, 2015

Abstract We propose Glabella, a wearable device that continuously and unobtrusively monitors heart rates at three sites on the wearer’s head. Our glasses prototype incorporates optical sensors, processing, storage, and communication components, all integrated into the frame to passively collect physiological data about the…

Established: June 1, 2016

Abstract Increased visual attention, such as during computer use leads to less blinking, which can cause dry eyes—the leading cause of computer vision syndrome. As people spend more time looking at screens on mobile and desktop devices, computer vision syndrome…

Intelligent agents that can handle human language play a growing role in personalized, ubiquitous computing and the everyday use of devices. Agents need to be able to communicate and collaborate with humans in ways that are seamless and natural, and…

Established: May 4, 2017

  The user of Virtual Reality, may find himself in different virtual worlds, such as a spy game (middle) or a space simulator(right) , yet they all give him tangible feedback using the same physical geometry in the real world…

Established: January 1, 2000

Video: Making Faces. An actress reads from a script designed to provide maximal phonetic coverage (we were planning to do automatic lip sync as a follow-on research project but never got around to it). Hence the funky monologue. Real-time, Photo-realistic, Physically…

Established: January 1, 2005

Using a piecewise parametric representation, we have made complex procedural objects that have a memory footprint of just 7-11 KBytes, which render at approximately 20 million triangles/ sec. on an NVidia 6800 GPU.