Recently, convolutional neural networks (CNNs) have been introduced to pansharpening for enhancing fusion accuracy and overcoming the drawbacks of the conventional methods. However, most of methods based on CNN fail to distinguish the difference of multispectral bands, and only use a uniform set of convolutional kernels to extract features. In this paper, we design a progressive, band-separated convolutional network architecture for discriminatively learning the features and relation among spectral bands, aiming to address the problem mentioned before. More specifically, the proposed architecture mainly consists of three aspects. First, to accurately preserve the spectral peculiarities, we divide the multispectral input image in terms of its bands into several groups. Second, our original panchromatic and multispectral inputs are filtered by a high-pass operation to further yield more spatial details. Third, we use a spectral fusion module (SFM) for each group and associate them to progressively assemble the whole architecture. It is worth mentioning that the architecture could be integrated into any other competitive CNNs to improve the performance. Both visual and quantitative experiments have demonstrated that our proposed method outperforms recent state-of-the-art pansharpening techniques.

Schematic Diagram of the Proposed Method


Full paper: click here

PyTorch code: click here


  author={Xiao, Shi-Shi and Jin, Cheng and Zhang, Tian-Jing and Ran, Ran and Deng, Liang-Jian},
  booktitle={2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS}, 
  title={Progressive Band-Separated Convolutional Neural Network for Multispectral Pansharpening},