Reliability-based Mesh-to-Grid Image Reconstruction

Conference contribution


Publication Details

Author(s): Koloda J, Seiler J, Kaup A
Publication year: 2016
Conference Proceedings Title: IEEE Workshop on Multimedia Signal Processing (MMSP)
Pages range: 1-5
ISBN: 978-1-5090-3724-7
ISSN: 2473-3628
Language: English


Abstract

This paper presents a novel method for the reconstruction of images from samples located at non-integer positions, called mesh. This is a common scenario for many image processing applications, such as super-resolution, warping or virtual view generation in multi-camera systems. The proposed method relies on a set of initial estimates that are later refined by a new reliability-based content-adaptive framework that employs denoising in order to reduce the reconstruction error. The reliability of the initial estimate is computed so stronger denoising is applied to less reliable estimates. The proposed technique can improve the reconstruction quality by more than 2 dB (in terms of PSNR) with respect to the initial estimate and it outperforms the state-of-the-art denoising-based refinement by up to 0.7 dB.


FAU Authors / FAU Editors

Kaup, André Prof. Dr.-Ing.
Lehrstuhl für Multimediakommunikation und Signalverarbeitung
Koloda, Jan
Lehrstuhl für Multimediakommunikation und Signalverarbeitung
Seiler, Jürgen PD Dr.-Ing.
Lehrstuhl für Multimediakommunikation und Signalverarbeitung


How to cite

APA:
Koloda, J., Seiler, J., & Kaup, A. (2016). Reliability-based Mesh-to-Grid Image Reconstruction. In IEEE Workshop on Multimedia Signal Processing (MMSP) (pp. 1-5). Montreal, CA.

MLA:
Koloda, Jan, Jürgen Seiler, and André Kaup. "Reliability-based Mesh-to-Grid Image Reconstruction." Proceedings of the IEEE 18th Workshop on Multimedia Signal Processing (MMSP), Montreal 2016. 1-5.

BibTeX: 

Last updated on 2019-19-04 at 15:10