A Noisy SAR Image Fusion Method Based on NLM and GAN

Abstract

The unavoidable noise often present in synthetic aperture radar (SAR) images, such as speckle noise, negatively impacts the subsequent processing of SAR images. Further, it is not easy to find an appropriate application for SAR images, given that the human visual system is sensitive to color and SAR images are gray. As a result, a noisy SAR image fusion method based on nonlocal matching and generative adversarial networks is presented in this paper. A nonlocal matching method is applied to processing source images into similar block groups in the pre-processing step. Then, adversarial networks are employed to generate a final noise-free fused SAR image block, where the generator aims to generate a noise-free SAR image block with color information, and the discriminator tries to increase the spatial resolution of the generated image block. This step ensures that the fused image block contains high resolution and color information at the same time. Finally, a fused image can be obtained by aggregating all the image blocks. By extensive comparative experiments on the SEN1–2 datasets and source images, it can be found that the proposed method not only has better fusion results but is also robust to image noise, indicating the superiority of the proposed noisy SAR image fusion method over the state-of-the-art methods.

PGSOFuse-Net: PCA and GAN Integration for SAROptical Image Fusion

“…In the present section, the proposed work is compared with different fusion methods starting from traditional to advanced deep learning-based algorithms including guided GFF [45], DWT [46], NSCT [47], multi-focus based on gradient image fusion (MWGF) [48], fast filtering image fusion (FFIF) [49], convolutional neural network based on general architecture (IFCNN) [50], and image fusion based on dense blocks (DenseFuse) [51]. Further, the proposed results are compared with two hybrid neural network architectures such as U-GAN + Gram Schmidt transform (U-GAN+GST) [52], and GAN + Non-local means (GAN+NLM) [53] to show the success of the proposed work. Figure 7, Figure 9, Figure 10, and Figure 11 represents the model outcomes of the dataset described in section 3.1.…”