Convolution Structure Sparse Coding for Fusion of Panchromatic and Multi-spectral Images

In this paper, we propose a novel image fusion method based on convolution structure sparse coding (CSSC) elaborated to depict the correlation in the MS bands by introducing structural sparsity avoids the partition of the image. 

Recently, sparse coding-based image fusion methods have been developed extensively. First, the proposed method combines convolution sparse coding with the degradation relationship of MS and panchromatic (PAN) images to establish a restoration model. 

Finally, feature maps over the constructed high-spatial-resolution (HR) and low-spatial-resolution (LR) filters are computed by alternative optimization to reconstruct the fused images.  The experimental show that the proposed method can produce better results by visual and numerical evaluation when compared with several well-known fusion methods.