Recognition by Linear Combinations of Models
IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part I
QuickTime VR: an image-based approach to virtual environment navigation
SIGGRAPH '95 Proceedings of the 22nd annual conference on Computer graphics and interactive techniques
Plenoptic modeling: an image-based rendering system
SIGGRAPH '95 Proceedings of the 22nd annual conference on Computer graphics and interactive techniques
VRAIS '96 Proceedings of the 1996 Virtual Reality Annual International Symposium (VRAIS 96)
Affine Object Representations for Calibration-Free Augmented Reality
VRAIS '96 Proceedings of the 1996 Virtual Reality Annual International Symposium (VRAIS 96)
A Panoramic-Based Walkthrough System Using Real Photos
PG '99 Proceedings of the 7th Pacific Conference on Computer Graphics and Applications
Presence: Teleoperators and Virtual Environments
Hi-index | 0.00 |
This paper introduces methodologies which generate 3D worlds from 2D photographic images instead of from 3D geometrical models. These methodologies have an advantage for generating photographically realistic 3D world: If we call conventional methodologies "algorithm intensive methodologies," these methodologies can be called "data intensive methodologies". In this paper, several prototype systems including the "Virtual Dome" and "Camera with GPS" are introduced as examples of data intensive methodologies. Of course, each of the two methodologies has its advantages; trade offs and combinations of the two methodologies are also discussed briefly. Readers may contact Hirose at the Dept. of Mechano-Informatics, University of Tokyo, 7-3-1, Hongo, Bunkyo-ku, Tokyo, 113, Japan, e-mail hirose@ihl.t.u-tokyo.ac.jp or visit his Web site at http://www.ihl.t.u-tokyo.ac.jp/index-j.html.