Enhanced CycleGAN Dehazing Network

Zahra Anvari, Vassilis Athitsos

2021

Abstract

Single image dehazing is a challenging problem, and it is far from solved. Most current solutions require paired image datasets that include both hazy images and their corresponding haze-free ground-truth. However, in reality lighting conditions and other factors can produce a range of haze-free images that can serve as ground truth for a hazy image, and a single ground truth image cannot capture that range. This limits the scalability and practicality of paired methods in real-world applications. In this paper, we focus on unpaired single image dehazing and reduce the image dehazing problem to an unpaired image-to-image translation and propose an Enhanced CycleGAN Dehazing Network (ECDN). We enhance CycleGAN from different angles for the dehazing purpose. We employ a global-local discriminator structure to deal with spatially varying haze. We define self-regularized color loss and utilize it along with perceptual loss to generate more realistic and visually pleasing images. We use an encoder-decoder architecture with residual blocks in the generator with skip connections so that the network better preserves the details. Through an ablation study, we demonstrate the effectiveness of different modules in the performance of the proposed network. Our extensive experiments over two benchmark datasets show that our network outperforms previous work in terms of PSNR and SSIM.

Download


Paper Citation


in Harvard Style

Anvari Z. and Athitsos V. (2021). Enhanced CycleGAN Dehazing Network. In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 4: VISAPP; ISBN 978-989-758-488-6, SciTePress, pages 193-202. DOI: 10.5220/0010347701930202


in Bibtex Style

@conference{visapp21,
author={Zahra Anvari and Vassilis Athitsos},
title={Enhanced CycleGAN Dehazing Network},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 4: VISAPP},
year={2021},
pages={193-202},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010347701930202},
isbn={978-989-758-488-6},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 4: VISAPP
TI - Enhanced CycleGAN Dehazing Network
SN - 978-989-758-488-6
AU - Anvari Z.
AU - Athitsos V.
PY - 2021
SP - 193
EP - 202
DO - 10.5220/0010347701930202
PB - SciTePress