Learning Accurate Features for Super-Resolution Spacecraft ISAR Imaging

Spacecraft Inverse Synthetic Aperture Radar (ISAR) imaging super-resolution aims to enhance the resolution of low-resolution images to produce high-resolution images. However, spacecraft ISAR imaging presents challenges such as sparse, fuzzy boundaries, and the intricate differentiation between background and spacecraft, rendering current methods less effective in achieving satisfactory super-resolution results. In this letter, we propose a sparse and selective feature fusion network for super-resolution spacecraft ISAR images. At the heart of our approach lies a multi-scale residual block featuring the following essential components: (a) parallel multi-resolution streams to extract multi-scale features, (b) trainable top-k selection operator that intelligently retains the most critical attention scores from the keys for each query, enhancing the distinction between background and spacecraft information within the local region, and (c) selective cross fusion to discriminatively determine which low-and high-scale information to retain when aggregating multi-scale features. The resulting tightly interlinked architecture, named as SSNet, learns a set of more accurate features. Extensive experiments on real ISAR images of spacecraft unequivocally illustrate the superior performance of the proposed method compared to state-of-the-art approaches, achieving an impressive 33.27dB. The code are released at https://github.com/Tombs98/SSNet.