Real-Time Non-Rigid Multi-Frame Depth Video Super-Resolution
Abstract
This paper proposes to enhance low resolution dynamic depth videos containing freely non-rigidly moving objects with a new dynamic multi-frame super-resolution algorithm. Existent methods are either limited to rigid objects, or restricted to global lateral motions discarding radial displacements. We address these shortcomings by accounting for non-rigid displacements in 3D. In addition to 2D optical flow, we estimate the depth displacement, and simultaneously correct the depth measurement by Kalman filtering. This concept is incorporated efficiently in a multi-frame super-resolution framework. It is formulated in a recursive manner that ensures an efficient deployment in real-time. Results show the overall improved performance of the proposed method as compared to alternative approaches, and specifically in handling relatively large 3D motions. Test examples range from a full moving human body to a highly dynamic facial video with varying expressions.
Cite
Text
Al Ismaeil et al. "Real-Time Non-Rigid Multi-Frame Depth Video Super-Resolution." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2015. doi:10.1109/CVPRW.2015.7301389Markdown
[Al Ismaeil et al. "Real-Time Non-Rigid Multi-Frame Depth Video Super-Resolution." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2015.](https://mlanthology.org/cvprw/2015/ismaeil2015cvprw-realtime/) doi:10.1109/CVPRW.2015.7301389BibTeX
@inproceedings{ismaeil2015cvprw-realtime,
title = {{Real-Time Non-Rigid Multi-Frame Depth Video Super-Resolution}},
author = {Al Ismaeil, Kassem and Aouada, Djamila and Solignac, Thomas and Mirbach, Bruno and Ottersten, Björn E.},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2015},
pages = {8-16},
doi = {10.1109/CVPRW.2015.7301389},
url = {https://mlanthology.org/cvprw/2015/ismaeil2015cvprw-realtime/}
}