TVTADMM-Net: an ADMM network based on total variation polarization texture denoising

Polarimetric Synthetic Aperture Radar (SAR) system can obtain richer scattering characteristics of ground objects. However, the inherent speckle noise in SAR images severely degrades their quality, and traditional denoising methods are difficult to apply to denoise polarimetric SAR images in complex scenarios, especially the texture details. Therefore, an ADMM network based on total variation (TV) polarization texture denoising is proposed in this paper. It preserves the backscatter coefficient properties of the feature target by "smoothing" the texture details. That is, the TV regularization term is added to the denoising process to construct a polarised texture sparse denoising model. The effectiveness of the proposed method is validated through experiments with multi-band airborne and spaceborne polarimetric SAR data