The Robotics Institute

Carnegie Mellon Robotics Institute

Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Abstract

We present appearance-based virtual view generation which allows viewers to y through a real dynamic scene. The scene is cap- tured by synchronized multiple cameras. Arbitrary views are generated by interpolating two original camera-view images near the given view- point. The quality of the generated synthetic view is determined by the precision, consistency and density of correspondences between the two images. All or most of previous work that uses interpolation extracts the correspondences from these two images. However, not only is it di?ult to do so reliably (the task requires a good stereo algorithm), but also the two images alone sometimes do not have enough information, due to problems such as occlusion. Instead, we take advantage of the fact that we have many views, from which we can extract much more reliable and comprehensive 3D geometry of the scene as a 3D model. The dense and precise correspondences between the two images, to be used for interpo- lation, are derived from this constructed 3D model. Our method of 3D modeling from multiple images uses the Multiple Baseline Stereo method and Shape from Silhouette method.

Notes

Associated Center(s) / Consortia: Vision and Autonomous Systems Center

Associated Lab(s) / Group(s): Virtualized Reality^TM

Text Reference

Shigeyuki Baba, Hideo Saito, Sundar Vedula, Kong Man Cheung, and Takeo Kanade, "Appearance-Based Virtual-View Generation for Fly Through in a Real Dynamic Scene," VisSym '00 (Joint Eurographics - IEEE TCVG Symposium on Visualization), May, 2000.

BibTeX Reference

@inproceedings{Baba_2000_3299,
   author = "Shigeyuki Baba and Hideo Saito and Sundar Vedula and Kong Man Cheung and Takeo Kanade",
   title = "Appearance-Based Virtual-View Generation for Fly Through in a Real Dynamic Scene",
   booktitle = "VisSym '00 (Joint Eurographics - IEEE TCVG Symposium on Visualization)",
   month = "May",
   year = "2000",
}

The Robotics Institute

Menu