Multi-View 3D Analysis with Applications for Augmented Reality and Enhanced Video Visualization
Abstract
The article presents methods for 3D scene geometry recovery/refinement and pose estimation from motion imagery in two representative scenarios. First, we present a method for pose estimation and scene geometry recovery from extended sequences without prior knowledge of the scheme. Second, we discuss how to recover camera poses when a rough scene model is provided. We show how to extend and refine the scene model using the recovered poses. Finally, we present applications of the above techniques for 3D imagery manipulation such as enhanced visualization for video and 3D insertion of synthetic objects in the imagery.
Cite
Text
Guo et al. "Multi-View 3D Analysis with Applications for Augmented Reality and Enhanced Video Visualization." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2000. doi:10.1109/CVPR.2000.854955Markdown
[Guo et al. "Multi-View 3D Analysis with Applications for Augmented Reality and Enhanced Video Visualization." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2000.](https://mlanthology.org/cvpr/2000/guo2000cvpr-multi/) doi:10.1109/CVPR.2000.854955BibTeX
@inproceedings{guo2000cvpr-multi,
title = {{Multi-View 3D Analysis with Applications for Augmented Reality and Enhanced Video Visualization}},
author = {Guo, Yanlin and Hsu, Steven C. and Samarasekera, Supun and Sawhney, Harpreet S. and Kumar, Rakesh},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2000},
pages = {2780-2781},
doi = {10.1109/CVPR.2000.854955},
url = {https://mlanthology.org/cvpr/2000/guo2000cvpr-multi/}
}