Pan-Sharpening With Wavelet-Enhanced High-Frequency Information

Pan-sharpening is essentially a panchromatic (PAN)-guided super-resolution process, primarily focused on enhancing multispectral image quality. This methodology intricately incorporates the high-frequency derived from texture-rich PAN images into the low-resolution multispectral (LRMS) counterparts. However, current spatial-domain techniques frequently face challenges in accurately restoring texture details, while frequency-domain methods lack efficient interaction with spatial domains, thus restricting the overall model performance. In response to these challenges, we introduce a novel high-frequency wavelet network that capitalizes on the spatial–frequency interaction and frequency division capabilities inherent in wavelet transform. In particular, our approach consists of two fundamental modules: the wavelet-inspired fusion block (WFB) and the high-frequency enhancement block (HEB). The former is inspired by wavelet lifting schemes, enabling the fusion of frequencies and facilitating information exchange across various subbands. The latter harnesses wavelet’s frequency division attributes to enhance high-frequency information learning. Comprehensive experiments over multiple satellite datasets demonstrate that our approach outperforms state-of-the-art (SOTA) techniques in both quantitative and qualitative assessments. Moreover, our model showcases exceptional generalization capabilities in real-world scenarios. Code is available at https://github.com/alexhe101/WINet.