MRDDANet: A Multiscale Residual Dense Dual Attention Network for SAR Image Denoising

Liu, Shuaiqi; Lei, Yu; Zhang, Luyao; Li, Bing; Hu, Weiming; Zhang, Yudong

doi:10.1109/tgrs.2021.3106764

Cited by 41 publications

(23 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To verify the performance of the proposed SAR-CAM model, experiments conducted on simulated and real SAR data are described. For comparison, three NL methods and six deep learning methods were chosen: the probabilistic patch-based (PPB) [13], the SAR block-matching 3D (SAR-BM3D) [14], the fast adaptive nonlocal SAR (FANS) [15], the dilated residual network-based SAR (SAR-DRN) [30], the hybrid dilated residual attention network (HDRANet) [32], the U-Net [35], the spatial and transform domain convolutional neural network (STD-CNN) [33], the multi-objective network (MONet) [29], and the multiscale residual dense dual attention network (MRDDANet) [34].…”

Section: Resultsmentioning

confidence: 99%

“…Attention modifies existing convolutional features by multiplying generated attention weights to highlight strong features while restraining non-important features. A couple of works have been designed for SAR image despeckling based on attention blocks [32]- [34], [40], and have achieved superior results compared with non-attention CNNs. Thus, the proposed method also utilizes an attention mechanism to enhance its despeckling capability.…”

Section: Methodsmentioning

confidence: 99%

“…Speaking of attention modules, a spatial-channel attention module (SCAM) was proposed in the STD-CNN [33] to enhance the isolation of the noise-related features from the real image for developing despeckling performance. Moreover, the MRDDANet [34] employed a residual dense dual attention block (RDDAB) that increases the capability of extracting principal information inside the SAR image, hence improving the deep feature extraction ability. Differing in network structural property, an encoder-decoder architecture, the U-Net [35], originally designed for image segmentation tasks [36], is applied for the speckle noise removal task-it effectively suppresses noise with remarkable edge detail preservation via downsampling operations and skip connections along the same image scale.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

SAR Image Despeckling Using Continuous Attention Module

Lee

2022

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

View full text Add to dashboard Cite

Speckle removal process is inevitable in the restoration of synthetic aperture radar (SAR) images. Several variant methods have been proposed for enhancing SAR images over the past decades. However, in recent studies, convolutional neural networks (CNNs) have been widely applied in SAR image despeckling because of their versatility in representation learning. Nonetheless, a fair number of textures of the images are still lost when despeckling using simple CNN structures. To solve this problem, an encoder-decoder architecture was previously proposed. Although this architecture extracts features on different scales and has been shown to yield state-of-theart performance, it still learns representation locally, resulting in missing overall information of convolutional features. Therefore, we herein introduce a new method for SAR image despeckling (SAR-CAM), which improves the performance of an encoder-decoder CNN architecture by using various attention modules. Moreover, a context block is introduced at the minimum scale to capture multiscale information. The model is trained via a data-driven approach using the gradient descent algorithm with a combination of modified despeckling gain and total variation loss function. Experiments performed on simulated and real SAR data demonstrate that the proposed method achieves significant improvements over state-of-the-art methodologies.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

SAR Image Despeckling Using Continuous Attention Module

Lee

2022

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

View full text Add to dashboard Cite

show abstract

“…In recent years, with the wide application of deep learning in various fields, optical problems are also more widely solved by deep learning, including optical interferometry [ 13 ], single-pixel imaging [ 14 , 15 ], wavefront sensing [ 16 , 17 , 18 ], remote sensing [ 19 , 20 , 21 , 22 , 23 , 24 , 25 , 26 ] and Fourier ptychography [ 27 , 28 , 29 ]. Using deep learning for image enhancement in imaging systems is also more attractive [ 22 , 23 , 30 , 31 , 32 ]. Chang et al [ 33 ] applied the deep residual network to infrared images and showed good robustness to vignetting and noise-induced nonuniformity.…”

Section: Introductionmentioning

confidence: 99%

Nonuniform Correction of Ground-Based Optical Telescope Image Based on Conditional Generative Adversarial Network

Guo

Chen

Liu

et al. 2023

Sensors

View full text Add to dashboard Cite

Ground-based telescopes are often affected by vignetting, stray light and detector nonuniformity when acquiring space images. This paper presents a space image nonuniform correction method using the conditional generative adversarial network (CGAN). Firstly, we create a dataset for training by introducing the physical vignetting model and by designing the simulation polynomial to realize the nonuniform background. Secondly, we develop a robust conditional generative adversarial network (CGAN) for learning the nonuniform background, in which we improve the network structure of the generator. The experimental results include a simulated dataset and authentic space images. The proposed method can effectively remove the nonuniform background of space images, achieve the Mean Square Error (MSE) of 4.56 in the simulation dataset, and improve the target’s signal-to-noise ratio (SNR) by 43.87% in the real image correction.

show abstract

“…In [7], ID-CNN network is trained with composite loss function comprising of a Mean Square Error (MSE) and Kullback-Leibler divergence (KL) between the predicted and simulated speckle probability distribution. Liu et al [8] proposed a multiscale residual dense dual attention network (MRDDANet) for despeckling which focuses on suppressing the speckle while fully retaining the texture details of the image.…”

Section: Introductionmentioning

confidence: 99%

SAR Despeckling Using Overcomplete Convolutional Networks

Perera¹,

Bandara²,

Valanarasu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Synthetic Aperture Radar (SAR) despeckling is an important problem in remote sensing as speckle degrades SAR images, affecting downstream tasks like detection and segmentation. Recent studies show that convolutional neural networks (CNNs) outperform classical despeckling methods. Traditional CNNs try to increase the receptive field size as the network goes deeper, thus extracting global features. However, speckle is relatively small, and increasing receptive field does not help in extracting speckle features. This study employs an overcomplete CNN architecture to focus on learning low-level features by restricting the receptive field. The proposed network consists of an overcomplete branch to focus on the local structures and an undercomplete branch that focuses on the global structures. We show that the proposed network improves despeckling performance compared to recent despeckling methods on synthetic and real SAR images. Our code is available at : https://github.com/malshaV/sar_overcomplete

show abstract

MRDDANet: A Multiscale Residual Dense Dual Attention Network for SAR Image Denoising

Cited by 41 publications

References 44 publications

SAR Image Despeckling Using Continuous Attention Module

SAR Image Despeckling Using Continuous Attention Module

Nonuniform Correction of Ground-Based Optical Telescope Image Based on Conditional Generative Adversarial Network

SAR Despeckling Using Overcomplete Convolutional Networks

Contact Info

Product

Resources

About