Please use this identifier to cite or link to this item:
Volltext verfügbar? / Dokumentlieferung
doi:10.22028/D291-39175
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: | https://link.springer.com/chapter/10.1007/978-3-030-92659-5_20 |
Link to this record: | urn:nbn:de:bsz:291--ds-391757 hdl:20.500.11880/35319 http://dx.doi.org/10.22028/D291-39175 |
ISBN: | 978-3-030-92659-5 978-3-030-92658-8 |
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.