Viral News

SRZoo: An integrated repository for super-resolution using deep learning. (arXiv:2006.01339v1 [eess.IV])

[Submitted on 2 Jun 2020]

Download PDF

Abstract: Deep learning-based image processing algorithms, including image
super-resolution methods, have been proposed with significant improvement in
performance in recent years. However, their implementations and evaluations are
dispersed in terms of various deep learning frameworks and various evaluation
criteria. In this paper, we propose an integrated repository for the
super-resolution tasks, named SRZoo, to provide state-of-the-art
super-resolution models in a single place. Our repository offers not only
converted versions of existing pre-trained models, but also documentation and
toolkits for converting other models. In addition, SRZoo provides
platform-agnostic image reconstruction tools to obtain super-resolved images
and evaluate the performance in place. It also brings the opportunity of
extension to advanced image-based researches and other image processing models.
The software, documentation, and pre-trained models are publicly available on
GitHub.

Submission history

From: Jun-Ho Choi [view email]

[v1]
Tue, 2 Jun 2020 01:46:09 UTC (435 KB)

Read More

Tags
Show More

Leave a Reply

Your email address will not be published. Required fields are marked *

Back to top button
Close
Close

Adblock Detected

Please consider supporting us by disabling your ad blocker