Misha Sra, Sergio Garrido-Jurado, Chris Schmandt, and Pattie Maes. 2016. Procedurally generated virtual reality from 3D reconstructed physical space. In Proceedings of the 22nd ACM Conference on Virtual Reality Software and Technology (VRST '16).
- Login
- Register
Work for a Member company and need a Member Portal account? Register here with your company email address.
Publication
Procedurally generated virtual reality from 3D reconstructed physical space
Abstract
We present a novel system for automatically generating immersive and interactive virtual reality (VR) environments using the real world as a template. The system captures indoor scenes in 3D, detects obstacles like furniture and walls, and maps walkable areas (WA) to enable real-walking in the generated virtual environment (VE). Depth data is additionally used for recognizing and tracking objects during the VR experience. The detected objects are paired with virtual counterparts to leverage the physicality of the real world for a tactile experience. Our approach is new, in that it allows a casual user to easily create virtual reality worlds in any indoor space of arbitrary size and shape without requiring specialized equipment or training.
Best Paper Award VRST 2016
Related Project: Oasis