Misha is a PhD student working on machine learning, specifically computer vision based mechanisms to automatically create VR environments. She is investigating ways to bring redirected walking and new user safety techniques to room-scale VR. This includes exploring methods for altering user perception both visually as well as through direct manipulation of the vestibular system using Galvanic Vestibular Stimulation (GVS). Here are some of her VR Projects and more.

Misha Sra, Sergio Garrido-Jurado, Pattie Maes. "Oasis: Procedurally Generated Social Virtual Spaces from 3D Scanned Real Spaces" IEEE Transactions on Visualization and Computer Graphics, 2017.   [Link]

Misha Sra, Prashanth Vijayaraghavan, Ognjen Rudovic, Pattie Maes, Deb Roy, "DeepSpace: Mood-Based Image Texture Generation for Virtual Reality from Music." Computer Vision and Pattern Recognition Workshops (CVPRW), 2017 IEEE Conference on, 2017.   [Link]