Latent Feature Disentanglement Bidirectional Prompting Network for Unsupervised Cloud Removal

Recently, the DisentGAN unsupervised learning framework has made significant progress in remote sensing image cloud removal. However, most existing DisentGAN-based methods fail to effectively disentangle surface and cloud information within the latent space, leading to suboptimal performance in cloud removal. Moreover, the limited feature representation capabilities of existing haze and cloud removal methods frequently result in inadequate restoration of image texture details and colors. To address these issues, we propose a Latent Feature Disentanglement Bidirectional Prompting Network (LFDBP-Net) for unsupervised cloud removal. Specifically, we propose an Unsupervised Latent Feature Disentanglement (ULFD) framework that explicitly separates surface and cloud information by leveraging unpaired cloud-free latent features as priors to pull surface features closer and push cloud features apart, constrained by a bi-halfcycle reconstruction branch. Furthermore, the Bidirectional Prompt-guided Codec Mechanism (BPCM) enables coarse-to-fine feature reconstruction through a two-phase “Look and Think” process, in which the Residual Query State Space Model (RQSSM) modulates encoder-decoder queries using residual-guided historical hidden state to fuse complementary local structures and global context. The BPCM can progressively enhance feature discriminability and semantic expressiveness, thereby improving image textures and colors. Finally, we construct an all-season covered, difficulty-graded cloud removal dataset, named CSRD-CR. Experiments on both our proposed dataset and public datasets demonstrate our LFDBP-Net outperforms several state-of-the-art unsupervised haze and cloud removal methods. The source code and dataset are available at https://github.com/nbhuangzhixuan/LFDBP-Net.