Free viewpoint video synthesis and presentation of sporting events for mixed reality entertainment
Proceedings of the 2004 ACM SIGCHI International Conference on Advances in computer entertainment technology
Novel View Generation from Multiple Omni-Directional Videos
ISMAR '05 Proceedings of the 4th IEEE/ACM International Symposium on Mixed and Augmented Reality
Virtualized Reality: Perspectives on 4D Digitization of Dynamic Events
IEEE Computer Graphics and Applications
Multi-View Video: Get Ready for Next-Generation Television
IEEE Distributed Systems Online
3DTV view generation using uncalibrated pure rotating and zooming cameras
Image Communication
Human motion modeling using multivision
HCI'07 Proceedings of the 12th international conference on Human-computer interaction: intelligent multimodal interaction environments
3D reconstruction of a human body from multiple viewpoints
PSIVT'07 Proceedings of the 2nd Pacific Rim conference on Advances in image and video technology
Trifocal transfer based novel view synthesis for micromanipulation
ISVC'06 Proceedings of the Second international conference on Advances in Visual Computing - Volume Part I
| Hi-index | 0.00 |
We present an appearance-based virtual view generation method that allows viewers to fly through a real dynamic scene. The scene is captured by multiple synchronized cameras. Arbitrary views are generated by interpolating two original camera-views near the given viewpoint. 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 difficult 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. Dense and precise correspondences between the two images, to be used for interpolation, are obtained using this constructed 3D model.