4D Visualization of Dynamic Events From Unconstrained Multi-View Videos

June 2020

4D Visualization of Dynamic Events From Unconstrained Multi-View Videos

Conference Paper
Proceedings of (CVPR) Computer Vision and Pattern Recognition

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.
@conference{Bansal-2020-125600,
author = {Aayush Bansal And Minh Vo And Yaser Sheikh And Deva Ramanan And Srinivasa Narasimhan},
title = {4D Visualization of Dynamic Events From Unconstrained Multi-View Videos},
booktitle = {Proceedings of (CVPR) Computer Vision and Pattern Recognition},
year = {2020},
month = {June},
pages = {5365 - 5374},
}
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.