Publication detail

Impact of loss function on multi-frame super-resolution

MEZINA, A.

Original Title

Impact of loss function on multi-frame super-resolution

Type

conference paper

Language

English

Original Abstract

Nowadays, one of the most popular topics in image processing is super-resolution. This problem is getting more actual even in security, since monitoring cameras are everywhere and in the case of an incident, it is necessary to recognize a person from records. A lot of approaches exist, which are able to reconstruct image, and the most of them are based on deep learning. The main focus of this work is to analyze, which loss function for neural networks is more effective for real-world image reconstruction. For this experiment chosen architecture and dataset are used for multi-frame super-resolution for 8 scaling.

Keywords

super-resolution, image processing, loss function, deep learning

Authors

MEZINA, A.

Released

27. 4. 2021

Publisher

Brno University of Technology, Faculty of Electrical Engineering and Communication

Location

Brno

ISBN

978-80-214-5942-7

Book

Proceedings I of the 27th Conference STUDENT EEICT 2021: General papers

Edition

1

Pages from

601

Pages to

605

Pages count

5

URL

https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2021_sbornik_1.pdf

BibTex

@inproceedings{BUT171575,
  author="Anzhelika {Mezina}",
  title="Impact of loss function on multi-frame super-resolution",
  booktitle="Proceedings I of the 27th Conference STUDENT EEICT 2021: General papers",
  year="2021",
  series="1",
  pages="601--605",
  publisher="Brno University of Technology, Faculty of Electrical Engineering and Communication",
  address="Brno",
  isbn="978-80-214-5942-7",
  url="https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2021_sbornik_1.pdf"
}