Image dehazing is a common operation in autonomous driving, traffic monitoring and surveillance. Learning-based image dehazing has achieved excellent performance recently. However, it is nearly impossible to capture pairs of hazy/clean images from the real world to train an image dehazing network. Most of existing dehazing models that are learnt from synthetically generated hazy images generalize poorly on real-world hazy scenarios due to the obvious domain shift. To deal with this unpaired problem arisen by real-world hazy images, we present Cycle Spectral Normalized Soft likelihood estimation Patch Generative Adversarial Network (Cycle-SNSPGAN) for image dehazing. Cycle-SNSPGAN is an unsupervised dehazing framework to boost the generalization ability on real-world hazy images. To leverage unpaired samples of real-world hazy images without relying on their clean counterparts, we design an SN-Soft-Patch GAN and exploit a new cyclic self-perceptual loss which avoids using the ground-truth image to compute the perceptual similarity. Moreover, a significant color loss is adopted to brighten the dehazed images as human expects. Both visual and numerical results show clear improvements of the proposed Cycle-SNSPGAN over state-of-the-arts in terms of hazy-robustness and image detail recovery, with even only a small dataset training our Cycle-SNSPGAN. Code has been available at https://github.com/yz-wang/Cycle-SNSPGAN.
Cycle-SNSPGAN: Towards Real-World Image Dehazing via Cycle Spectral Normalized Soft Likelihood Estimation Patch GAN
IEEE Transactions on Intelligent Transportation Systems ; 23 , 11 ; 20368-20382
2022-11-01
4852327 byte
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Overwater Image Dehazing via Cycle-Consistent Generative Adversarial Network
British Library Conference Proceedings | 2021
|Springer Verlag | 2021
|Unified Density-Aware Image Dehazing and Object Detection in Real-World Hazy Scenes
British Library Conference Proceedings | 2021
|Single Image Dehazing via Image Generating
British Library Conference Proceedings | 2018
|DAY/NIGHT UNCONSTRAINED IMAGE DEHAZING
British Library Conference Proceedings | 2016
|