Pan-sharpening via High-pass Modification Convolutional Neural Network
This work addresses image quality issues in remote sensing for applications like satellite imagery, though it appears incremental as it builds on existing deep learning methods.
The paper tackles spectral distortion and insufficient spatial texture enhancement in pan-sharpening by proposing a high-pass modification convolutional neural network with a perceptual loss function, achieving superior performance compared to state-of-the-art methods both quantitatively and qualitatively.
Most existing deep learning-based pan-sharpening methods have several widely recognized issues, such as spectral distortion and insufficient spatial texture enhancement, we propose a novel pan-sharpening convolutional neural network based on a high-pass modification block. Different from existing methods, the proposed block is designed to learn the high-pass information, leading to enhance spatial information in each band of the multi-spectral-resolution images. To facilitate the generation of visually appealing pan-sharpened images, we propose a perceptual loss function and further optimize the model based on high-level features in the near-infrared space. Experiments demonstrate the superior performance of the proposed method compared to the state-of-the-art pan-sharpening methods, both quantitatively and qualitatively. The proposed model is open-sourced at https://github.com/jiaming-wang/HMB.