Fast Pre-Training Kernel Estimation Network for ISAR Space Target Image Deblurring

In inverse synthetic aperture radar (ISAR) imaging applications, the lack of image clarity often limits their usage in down-streaming tasks such as recognition and component judgment. The super-resolution of ISAR images after imaging needs to consider the uncertainty of the blur kernel and cannot simply use traditional super-resolution (SR) methods. Moreover, ISAR images are scarce, expensive to obtain, and pre-training based on a large number of images is challenging. Therefore, this paper proposes a Single-Image Super-Resolution (SISR) method with generalization ability for different blur kernels, which does not rely on a large amount of image data training for ISAR image super-resolution. A large number of experiments show that the proposed method is superior to the traditional Bicubic algorithm and learning-based DIP, Double-DIP methods, and achieves significantly better performance with less pre-training time.

I. Introduction

Achieving super-resolution for Inverse Synthetic Aperture Radar (ISAR) space target images is vital for subsequent tasks such as target recognition, classification, and segmentation. Nevertheless, obtaining high-resolution images from ISAR images can be challenging due to target non-cooperation and limitations of the radar system which result in low-resolution and blurred images. As a result, developing methods to obtain high-resolution images from low-resolution ISAR images has become an active research topic.