RGAN: Rethinking generative adversarial networks for cloud removal

Ran, Xinyu; Ge, Liang; Zhang, Xiaofeng

doi:10.1002/int.22566

Cited by 12 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(iii) Recurrent neural network (RNN)-based methods use a recurrent neural network to memorize short time series and combine the front layer features with current features to realize the reasonable supplement of missing information. The commonly used classical methods are PixelRNN [40] and the RGAN model [41]. These methods are used less because they have high computational costs and are not capable of using global information.…”

Section: B Reconstruction Of Temporal-based Methodsmentioning

confidence: 99%

DecRecNet: A Decoupling-Reconstruction Network for Restoring the Missing Information of Optical Remote Sensing Images

Liu,

Cui,

Jiang

et al. 2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Temporal-based methods effectively improve the utilization rate of remote sensing images, but large ratios of missing information still need to be improved in the reconstruction models. In this paper, based on the imaging theory with the help of a radiation correction model, a decoupling-reconstruction network (DecRecNet) for image reconstruction is proposed. The network uses a ground content radiation (GCR) correction module and imaging environment radiation (IER) correction module and their corresponding loss functions to decouple the image radiation information into ground content radiation related to the ground objects and imaging environment radiation related to the imaging conditions and carry out targeted processing to achieve the purpose of missing information reconstruction. The ground content radiation consistency loss function is used to preserve the ground content information, and the imaging environment radiation consistency loss function and imaging environment radiation smoothness loss are used to coordinate the imaging environment. The radiation guiding module further performs targeted radiation adjustment on the foreground and background images to transfer the background imaging environment to the foreground and consistent radiation information of the same ground object. Compared with the classical U-Net, DeepLabV3+, RFR-Net, and STS-CNN methods, our model showed remarkable advantages in cloud occlusion and stripes of Landsat-8 (30 m), GaoFen-1 (2 m), and Landsat-7 (30 m) at various missing ratios, data sources, resolutions, and scenes, and achieving the goal of missing information reconstruction in large missing ratios.

show abstract

Section: B Reconstruction Of Temporal-based Methodsmentioning

confidence: 99%

DecRecNet: A Decoupling-Reconstruction Network for Restoring the Missing Information of Optical Remote Sensing Images

Liu,

Cui,

Jiang

et al. 2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The structure of SpA-Former is shown in Fig 2 . SpA-Former is enspired by [16], [19], [20], [22], it consists of…”

Section: Methodsmentioning

confidence: 99%

SpA-Former: Transformer image shadow detection and removal via spatial attention

Zhang¹,

Gu²,

Zhu³

2022

Preprint

View full text Add to dashboard Cite

n this paper, we propose an end-to-end SpA-Former to recover a shadow-free image from a single shaded image. Unlike traditional methods that require two steps for shadow detection and then shadow removal, the SpA-Former unifies these steps into one, which is a one-stage network capable of directly learning the mapping function between shadows and no shadows, it does not require a separate shadow detection. Thus, SpAformer is adaptable to real image de-shadowing for shadows projected on different semantic regions. SpA-Former consists of transformer layer and a series of joint Fourier transform residual blocks and two-wheel joint spatial attention. The network in this paper is able to handle the task while achieving a very fast processing efficiency. Our code is relased on https://github.com/ zhangbaijin/Spatial-Transformer-shadow-removal

show abstract

“…The probability distribution in the other models is not explicitly expressed. It is called the implicit generative model [8,9] , such as the generative adversarial network (GAN) [10] . It enables the generator to generate image samples from random noise through adversarial learning.…”

Section: Introductionmentioning

confidence: 99%

P‐2.9: A review of image generation methods based on deep learning

Wang

Song

Wang

2023

Symp Digest of Tech Papers

View full text Add to dashboard Cite

Image as a medium of visual information transmission have the advantages of vividness, intuition and easy understanding. They play an important role in information transmission and utilization. In recent years, due to the rapid development of deep learning technology in the field of image processing, image generative model based on neural network has become one of the current research hotspots. In the field of deep learning, unsupervised learning model has received more and more attentions, especially in the field of deep generative models, which has made breakthrough progress [1] . Among them, Variational Auto-Encoder (VAE), Generative Adversarial Network (GAN), and Diffusion Model are the three most representative research methods in the field of unsupervised learning. They have been applied more and more in the field of deep generative models. Especially, the high-quality image generative models based on the generative adversarial network continue to be hot. The diffusion model is a rising star, which is favored by more and more researchers. This paper first summarizes the main research work, improvement mechanism and features of image generation methods based on VAE and GAN, then introduces the principle of the rising diffusion model and its representative models. Finally, the advantages and limitations of the above methods are compared and analyzed, and prospects for future research are put forward.

show abstract

RGAN: Rethinking generative adversarial networks for cloud removal

Cited by 12 publications

References 22 publications

DecRecNet: A Decoupling-Reconstruction Network for Restoring the Missing Information of Optical Remote Sensing Images

DecRecNet: A Decoupling-Reconstruction Network for Restoring the Missing Information of Optical Remote Sensing Images

SpA-Former: Transformer image shadow detection and removal via spatial attention

P‐2.9: A review of image generation methods based on deep learning

Contact Info

Product

Resources

About