A Multi-scale Generalized Shrinkage Threshold Network for Image Blind Deblurring in Remote Sensing

Abstract

Remote sensing images are essential for many applications of the earth's sciences, but their quality can usually be degraded due to limitations in sensor technology and complex imaging environments. To address this, various remote sensing image deblurring methods have been developed to restore sharp and high-quality images from degraded observational data. However, most traditional model-based deblurring methods usually require predefined {hand-crafted} prior assumptions, which are difficult to handle in complex applications. On the other hand, deep learning-based deblurring methods are often considered as black boxes, lacking transparency and interpretability. In this work, we propose a new blind deblurring learning framework that utilizes alternating iterations of shrinkage thresholds. This framework involves updating blurring kernels and images, with a theoretical foundation in network design. Additionally, we propose a learnable blur kernel proximal mapping module to improve the accuracy of the blur kernel reconstruction. Furthermore, we propose a deep proximal mapping module in the image domain, which combines a generalized shrinkage threshold with a multi-scale prior feature extraction block. This module also incorporates an attention mechanism to learn adaptively the importance of prior information, improving the flexibility and robustness of prior terms, and avoiding limitations similar to hand-crafted image prior terms. Consequently, we design a novel multi-scale generalized shrinkage threshold network (MGSTNet) that focuses specifically on learning deep geometric prior features to enhance image restoration. Experimental results on real and synthetic remote sensing image datasets demonstrate the superiority of our MGSTNet framework compared to existing deblurring methods.

arXiv comment16 pages,Accepted to IEEE Transactions on Geoscience and Remote Sensing,2024

References in corpus (15)

• Adam: A Method for Stochastic Optimization
• AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification
• Diffusion Models in Vision: A Survey
• UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagery
• Aerial Imagery for Roof Segmentation: A Large-Scale Dataset towards Automatic Mapping of Buildings
• BANet: Blur-aware Attention Networks for Dynamic Scene Deblurring
• Dual-Stage Approach Toward Hyperspectral Image Super-Resolution
• Coupling Model-Driven and Data-Driven Methods for Remote Sensing Image Restoration and Fusion
• HR-SAR-Net: A Deep Neural Network for Urban Scene Segmentation from High-Resolution SAR Data
• An Interpretable MRI Reconstruction Network with Two-grid-cycle Correction and Geometric Prior Distillation
• Deep Geometric Distillation Network for Compressive Sensing MRI
• Nest-DGIL: Nesterov-optimized Deep Geometric Incremental Learning for CS Image Reconstruction
• FAS-UNet: A Novel FAS-driven Unet to Learn Variational Image Segmentation
• PRISTA-Net: Deep Iterative Shrinkage Thresholding Network for Coded Diffraction Patterns Phase Retrieval
• Physics-Informed DeepMRI: Bridging the Gap from Heat Diffusion to k-Space Interpolation

Cited by in corpus (1)

• Diffusion Models Meet Remote Sensing: Principles, Methods, and Perspectives