4D Visualization of Dynamic Events from Unconstrained Multi-View Videos
Abstract
We present a data-driven approach for 4D space-time visualization of dynamic events from videos captured by hand-held multiple cameras. Key to our approach is the use of self-supervised neural networks specific to the scene to compose static and dynamic aspects of an event. Though captured from discrete viewpoints, this model enables us to move around the space-time of the event continuously. This model allows us to create virtual cameras that facilitate: (1) freezing the time and exploring views; (2) freezing a view and moving through time; and (3) simultaneously changing both time and view. We can also edit the videos and reveal occluded objects for a given view if it is visible in any of the other views. We validate our approach on challenging in-the-wild events captured using up to 15 mobile cameras.
Cite
Text
Bansal et al. "4D Visualization of Dynamic Events from Unconstrained Multi-View Videos." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020. doi:10.1109/CVPR42600.2020.00541Markdown
[Bansal et al. "4D Visualization of Dynamic Events from Unconstrained Multi-View Videos." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020.](https://mlanthology.org/cvpr/2020/bansal2020cvpr-4d/) doi:10.1109/CVPR42600.2020.00541BibTeX
@inproceedings{bansal2020cvpr-4d,
title = {{4D Visualization of Dynamic Events from Unconstrained Multi-View Videos}},
author = {Bansal, Aayush and Vo, Minh and Sheikh, Yaser and Ramanan, Deva and Narasimhan, Srinivasa},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2020},
doi = {10.1109/CVPR42600.2020.00541},
url = {https://mlanthology.org/cvpr/2020/bansal2020cvpr-4d/}
}