Please use this identifier to cite or link to this item: doi:10.22028/D291-39175
Volltext verfügbar? / Dokumentlieferung
Title: A Comparative Study of PnP and Learning Approaches to Super-Resolution in a Real-World Setting
Author(s): Taray, Samim Zahoor
Jaiswal, Sunil Prasad
Sharma, Shivam
Cheema, Noshaba
Illgner-Fehns, Klaus
Slusallek, Philipp
Ihrke, Ivo
Editor(s): Bauckhage, Christian
Gall, Juergen
Schwing, Alexander
Language: English
Title: Pattern Recognition : 43rd DAGM German Conference, DAGM GCPR 2021, Bonn, Germany, September 28 – October 1, 2021, Proceedings
Pages: 313-327
Publisher/Platform: Springer
Year of Publication: 2021
Place of publication: Cham
Place of the conference: Bonn, Germany
DDC notations: 004 Computer science, internet
Publikation type: Conference Paper
Abstract: Single-Image Super-Resolution has seen dramatic improvements due to the application of deep learning and commonly achieved results show impressive performance. Nevertheless, the applicability to real-world images is limited and expectations are often disappointed when comparing to the performance achieved on synthetic data. For improving on this aspect, we investigate and compare two extensions of orthogonal popular techniques, namely plug-and-play optimization with learned priors, and a single end-to-end deep neural network trained on a larger variation of realistic synthesized training data, and compare their performance with special emphasis on model violations. We observe that the end-to-end network achieves a higher robustness and flexibility than the optimization based technique. The key to this is a wider variability and higher realism in the training data than is commonly employed in training these networks.
DOI of the first publication: 10.1007/978-3-030-92659-5_20
URL of the first publication:
Link to this record: urn:nbn:de:bsz:291--ds-391757
ISBN: 978-3-030-92659-5
Date of registration: 28-Feb-2023
Notes: Image Processing, Computer Vision, Pattern Recognition, and Graphics ; 13024
Faculty: MI - Fakultät für Mathematik und Informatik
Department: MI - Informatik
Professorship: MI - Prof. Dr. Philipp Slusallek
Collections:SciDok - Der Wissenschaftsserver der Universität des Saarlandes

Files for this record:
There are no files associated with this item.

Items in SciDok are protected by copyright, with all rights reserved, unless otherwise indicated.