Progressive Alignment Degradation Learning for Pansharpening

--Deep learning-based pansharpening has been shown to effectively generate high-resolution multispectral (HRMS) images. T o create supervised ground-truth HRMS images, synthetic data generated using the Wald protocol is commonly employed. This protocol assumes that networks trained on artificial low-resolution data will perform equally well on high-resolution data. In this paper, we delve into the Wald protocol and find that its inaccurate approximation of real-world degradation patterns limits the generalization of deep pansharpening models. T o address this issue, we propose the Progressive Alignment Degradation Module (PADM), which uses mutual iteration between two sub-networks, PAlignNet and PDegradeNet, to adaptively learn accurate degradation processes without relying on predefined operators. Building on this, we introduce HFreqdiff, which embeds high-frequency details into a diffusion framework and incorporates CFB and BACM modules for frequency-selective detail extraction and precise reverse process learning. These innovations enable effective integration of high-resolution panchromatic and multispectral images, significantly enhancing spatial sharpness and quality. Experiments and ablation studies demonstrate the proposed method's superior performance compared to state-of-the-art techniques. EMOTE sensing images with high spatial and spectral resolution are in high demand across various fields, including scene classification [1], [2], semantic segmentation [3], [4], and environmental monitoring [5]. However, due to the physical limitations of current sensor technologies, data acquired by a single satellite sensor often fail to meet these high-quality standards.