Iterative Denoising-Based Mesh-to-Grid Reconstruction with Hyperparametric Adaptation

Koloda J, Bätz M, Kaup A (2017)

Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2017

Event location: London-Luton GB

ISBN: 978-1-5090-3649-3

DOI: 10.1109/MMSP.2017.8122288

Abstract

This paper presents a new method for the reconstruction of images from samples located at non-integer mesh positions. This is a common scenario for many image processing applications such as multi-image super-resolution, frame-rate up-conversion, or virtual view synthesis in multi-camera systems. The proposed method consists of an iterative procedure that employs adaptive denoising in order to reduce the reconstruction error. The denoising strength is controlled by a novel hyper-parametric adaptation mechanism that aims at maximizing the reconstruction quality in each iteration. Furthermore, the usage of the proposed hyperparametric model drastically reduces the number of necessary parameters that need to be trained or stored. In terms of luminance PSNR, the proposed approach improves the reconstruction quality by more than 1 dB with respect to the initial estimate and outperforms current state-of-the-art denoising-based reconstruction schemes by up to 0.5 dB.

Authors with CRIS profile

Jan Koloda Lehrstuhl für Multimediakommunikation und Signalverarbeitung (LMS) Michel Bätz Lehrstuhl für Multimediakommunikation und Signalverarbeitung (LMS) Andre Kaup Lehrstuhl für Multimediakommunikation und Signalverarbeitung (LMS)

How to cite

APA:

Koloda, J., Bätz, M., & Kaup, A. (2017). Iterative Denoising-Based Mesh-to-Grid Reconstruction with Hyperparametric Adaptation. In Proceedings of the IEEE International Workshop on Multimedia Signal Processing. London-Luton, GB.

MLA:

Koloda, Jan, Michel Bätz, and André Kaup. "Iterative Denoising-Based Mesh-to-Grid Reconstruction with Hyperparametric Adaptation." Proceedings of the IEEE International Workshop on Multimedia Signal Processing, London-Luton 2017.

BibTeX: Download