CycleGAN-Based Cloud Removal from a Feature Enhancement Perspective by Transformer

Yiming Huang, Xianping Ma, Xiaokang Zhang, Man-On Pun

Abstract: Cloud removal has attracted significant research attention in various remote sensing applications, such as object detection and semantic segmentation. In this study, the classical cycle-consistent generative adversarial network (CycleGAN) is adopted for suppressing clouds from a feature enhancement perspective by capitalizing on the transformer architecture. Specifically, a transformer-based feature enhancement (TFE) module is proposed to extract high-level cloud-clear features by leveraging the Swin transformer’s capability of building long-range dependencies. As a result, the proposed TFE module can eliminate clouds in remote sensing images while retaining cloud-free regions unchanged. Extensive simulation experiments on the RICE dataset are conducted to substantiate the impressive performance of the proposed TFE model as compared to several existing cloud-removal methods.