Issue No.02 - March (1996 vol.16)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/38.486677
This article presents automated techniques for creating large, high-resolution images and environment maps from regular low-resolution video and photographic imagery. By panning a camera over a scene and automatically compositing the resulting frames, this system can create images and panoramas of arbitrary shape and detail. Translating the camera causes motion parallax in the video, which can be exploited to recover depth maps of the scene and thereby enable limited 3D rendering through view interpolation. The article discusses applications of these techniques to the creation of novel virtual environments and experiences such as virtual travel, home walkthroughs, and home supermarket shopping.
image processing, visual mosaicing, virtual reality, virtual environments
Richard Szeliski, "Video Mosaics for Virtual Environments", IEEE Computer Graphics and Applications, vol.16, no. 2, pp. 22-30, March 1996, doi:10.1109/38.486677