S³Mamba-Pan: Spectral-Spatial-Scale Mamba With Frequency-Decoupled Dual-Stream for Pansharpening

Pansharpening plays a critical role in remote sensing image processing by generating high-resolution multispectral (HRMS) images through the fusion of low-resolution multispectral (LRMS) and high-resolution panchromatic (PAN) images. In recent years, deep learning (DL)-based approaches have significantly advanced fusion performance via end-to-end modeling. However, existing methods still face notable limitations, including insufficient modeling of long-range dependencies, tight coupling between spectral and spatial information that may introduce spectral distortion, and high computational complexity that restricts practical deployment in high-resolution scenarios. To address these issues, we propose spectral-spatial-scale Mamba for pansharpening (S3Mamba-Pan), a frequency-aware state space framework that jointly models spectral structure, spatial texture, and multiscale context in a coordinated yet decoupled manner. The method first extracts a global spectral anchor (GSA) from the LRMS input to guide fusion, then performs waveletbased frequency decoupling to separate low-frequency spectral components from high-frequency spatial details. A dual-stream Mamba architecture conducts parallel state space modeling for spectral correlation learning and PAN-guided texture enhancement, and an adaptive distribution recalibration (ADR) module aligns channel-wise statistics before reconstruction. Experiments on WorldView-3 (WV3), QuickBird (QB), and GaoFen-2 (GF2) demonstrate consistent improvements over representative convolutional neural network (CNN), transformer, and state-space model (SSM)-based baselines under reduced-resolution evaluation. Under full-resolution no-reference assessment on WV3, S3Mamba-Pan achieves D λ 0:0144, Ds 0:0303, and HQNR 0.960, indicating improved spectral fidelity and spatial consistency. Ablation and visualization analyses further corroborate the contribution of each component and provide interpretable evidence for the effectiveness of frequency decoupling and spectral anchoring. Code is available at https://github.com/FreeZS-a/S3Mamba