Single remote sensing image dehazing using gaussian and physics-guided process
Y Bie, S Yang, Y Huang - IEEE Geoscience and Remote …, 2022 - ieeexplore.ieee.org
Y Bie, S Yang, Y Huang
IEEE Geoscience and Remote Sensing Letters, 2022•ieeexplore.ieee.orgRemote sensing (RS) dehazing is a challenging task since various haze distributions
severely degrade the image quality. Recent learning-based methods achieve dramatic
performance for RS dehazing; however, previous ways are limited to their generality using
only fully labeled datasets and less prior-guided information. In this letter, we explore the
Gaussian and physics-guided dehazing network (GPD-Net) to better obtain hazy feature and
improve the generalization ability in real-world condition. To promote the feature extraction …
severely degrade the image quality. Recent learning-based methods achieve dramatic
performance for RS dehazing; however, previous ways are limited to their generality using
only fully labeled datasets and less prior-guided information. In this letter, we explore the
Gaussian and physics-guided dehazing network (GPD-Net) to better obtain hazy feature and
improve the generalization ability in real-world condition. To promote the feature extraction …
Remote sensing (RS) dehazing is a challenging task since various haze distributions severely degrade the image quality. Recent learning-based methods achieve dramatic performance for RS dehazing; however, previous ways are limited to their generality using only fully labeled datasets and less prior-guided information. In this letter, we explore the Gaussian and physics-guided dehazing network (GPD-Net) to better obtain hazy feature and improve the generalization ability in real-world condition. To promote the feature extraction, a novel global attention mechanism (GAM) is involved to extract feature from different haze distributions. Then, an encoder–decoder network is designed with Gaussian process (GP) in the intermediate latent space, in order to learn the full labeled dehazing and guide to handle the unlabeled learning. For the fine-tuning, we select some physical prior knowledge to refine the dehazed results. Extensive experiments demonstrate that our method outperforms the recent comparing approaches on the synthetic and real-world datasets.
ieeexplore.ieee.org