Abstract

Low light image enhancement is an important challenge for the development of robust computer vision algorithms. The machine learning approaches to this have been either unsupervised, supervised based on paired dataset or supervised based on unpaired dataset. This paper presents a novel deep learning pipeline that can learn from both paired and unpaired datasets. Convolution Neural Networks (CNNs) that are optimized to minimize standard loss, and Generative Adversarial Networks (GANs) that are optimized to minimize the adversarial loss are used to achieve different steps of the low light image enhancement process. Cycle consistency loss and a patched discriminator are utilized to further improve the performance. The paper also analyses the functionality and the performance of different components, hidden layers, and the entire pipeline.


Original document

The different versions of the original document can be found in:

http://dx.doi.org/10.1109/mercon50084.2020.9185373
https://arxiv.org/pdf/2006.15304,
https://ui.adsabs.harvard.edu/abs/2020arXiv200615304W/abstract,
https://academic.microsoft.com/#/detail/3083484956
Back to Top

Document information

Published on 01/01/2020

Volume 2020, 2020
DOI: 10.1109/mercon50084.2020.9185373
Licence: CC BY-NC-SA license

Document Score

0

Views 13
Recommendations 0

Share this document

claim authorship

Are you one of the authors of this document?