M³-CR: Multiscale Multibranch Mamba for SAR-Assisted Optical Image Thick Cloud Removal

SAR-assisted thick cloud removal from optical remote sensing images has long been a challenging task. Current mainstream methods face challenges in achieving an effective global receptive field, fully using multiscale features, and deeply integrating features from both modalities. To overcome these limitations, we propose the multiscale multibranch Mamba model for SAR-assisted thick cloud removal ( M³-CR). Specifically, we integrate the Mamba model into the task of SAR-assisted cloud removal, effectively modeling global dependencies within the images. Concurrently, a multiscale multibranch structure is introduced to extract and integrate multiscale information, and in combination with a convolutional branch to fully exploit the global and local geographic proximities inherent in remote sensing images. Furthermore, we present a novel feature fusion module leveraging the modal-traversing-2-D selective scan (MTSS2D) to enable deep interaction and integration of features from optical and SAR images. The experimental results on two benchmark databases show that the M³-CR achieves superior performance compared with state-of-the-art cloud removal approaches, while requiring fewer parameters and reduced floating-point operations (FLOPs).