Dual-View Prompting for Cloud Removal

Cloud cover significantly impedes the utilization of remote sensing data, limiting the effectiveness of satellite imagery in critical applications such as environmental monitoring and disaster response. While deep learning methods have advanced cloud removal, existing models predominantly focus on spatial-domain feature discrepancies, often overlooking distinctive spectral difference introduced by clouds. To address this gap, we propose a Dual-view Prompting Network (DVPNet) that integrates spatial and frequency information via prompt learning to generate robust guidance features. The core innovation, the Dual-view Prompting Block (DVPB), operates cascadedly: first, a spatial gating module refines features to capture contextual cues; these features are then transformed into the Fourier domain, where a frequency-gating structure and a learnable spectral prompt further calibrate and enhance representations. The holistically refined dual-view prompt is integrated into the decoder through an efficient windowed cross-attention mechanism, enabling precise cloud removal. Extensive experiments on benchmark datasets demonstrate that DVPNet achieves state-of-the-art performance. This work validates the critical role of frequency-domain modeling in cloud removal and establishes a new spatial-frequency collaborative paradigm for remote sensing image restoration. The code will be made available at https://github.com/huangwenwenlili/DVPNet.