S2A: Wasserstein GAN with Spatio-Spectral Laplacian Attention for Multi-Spectral Band Synthesis
This work addresses the need for additional high-resolution multi-spectral data products in remote sensing, though it appears incremental by combining existing techniques like attention mechanisms and Wasserstein GANs.
The paper tackled the problem of synthesizing high-resolution multi-spectral satellite imagery using adversarial learning, achieving favorable performance against state-of-the-art methods on datasets from three sensors (LISS-3, LISS-4, WorldView-2) and synthesizing over 4000 high-resolution scenes.
Intersection of adversarial learning and satellite image processing is an emerging field in remote sensing. In this study, we intend to address synthesis of high resolution multi-spectral satellite imagery using adversarial learning. Guided by the discovery of attention mechanism, we regulate the process of band synthesis through spatio-spectral Laplacian attention. Further, we use Wasserstein GAN with gradient penalty norm to improve training and stability of adversarial learning. In this regard, we introduce a new cost function for the discriminator based on spatial attention and domain adaptation loss. We critically analyze the qualitative and quantitative results compared with state-of-the-art methods using widely adopted evaluation metrics. Our experiments on datasets of three different sensors, namely LISS-3, LISS-4, and WorldView-2 show that attention learning performs favorably against state-of-the-art methods. Using the proposed method we provide an additional data product in consistent with existing high resolution bands. Furthermore, we synthesize over 4000 high resolution scenes covering various terrains to analyze scientific fidelity. At the end, we demonstrate plausible large scale real world applications of the synthesized band.