Satellite Image Target Super-Resolution With Adversarial Shape Discriminator

Changyeop Shin, Sungho Kim, Youngjung Kim

Abstract: Substantial progress in generative modeling has facilitated the development of perceptual-driven methods for image super-resolution (SR), which shows superior visual quality as rated by human observers. However, we discover that most existing methods are biased to synthesize fake details or enhanced textures and fail to learn representations of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">object shape</i> . They are often misguided to recover the shape of small objects and focus on generating less meaningful high-frequency components. This is problematic when super-resolving satellite imagery since it contains many relatively small and clustered objects in a broad area. In this letter, we propose a new perceptual-driven SR method that has a stronger preference toward shape information. We integrate the scale-space filtering with the discriminator to attenuate high-frequency components in its decision space. It effectively encourages our discriminator to concentrate on structural shape information in differentiating real and fake images. We also devise a cross-scale aggregation network for the generator architecture. Experiments on <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">WorldView</i> data set demonstrate that our method achieves state-of-the-art performance compared to recent perceptual-driven methods.