Pansharpening via Frequency-Aware Fusion Network with Explicit Similarity Constraints

TL;DR

This paper introduces FAFNet, a frequency-aware neural network with a novel similarity loss, to improve pansharpening by enhancing spatial details while reducing spectral distortion using wavelet transforms.

Contribution

The paper proposes a new frequency-aware fusion network with a high-frequency feature similarity loss to better integrate spatial details and spectral information in pansharpening.

Findings

Outperforms state-of-the-art methods on multiple datasets.

Effectively enhances spatial details with reduced spectral distortion.

Demonstrates robustness at both reduced and full resolutions.

Abstract

The process of fusing a high spatial resolution (HR) panchromatic (PAN) image and a low spatial resolution (LR) multispectral (MS) image to obtain an HRMS image is known as pansharpening. With the development of convolutional neural networks, the performance of pansharpening methods has been improved, however, the blurry effects and the spectral distortion still exist in their fusion results due to the insufficiency in details learning and the frequency mismatch between MSand PAN. Therefore, the improvement of spatial details at the premise of reducing spectral distortion is still a challenge. In this paper, we propose a frequency-aware fusion network (FAFNet) together with a novel high-frequency feature similarity loss to address above mentioned problems. FAFNet is mainly composed of two kinds of blocks, where the frequency aware blocks aim to extract features in the frequency domain with the help of discrete wavelet transform (DWT) layers, and the frequency fusion blocks reconstruct and transform the features from frequency domain to spatial domain with the assistance of inverse DWT (IDWT) layers. Finally, the fusion results are obtained through a convolutional block. In order to learn the correspondence, we also propose a high-frequency feature similarity loss to constrain the HF features derived from PAN and MS branches, so that HF features of PAN can reasonably be used to supplement that of MS. Experimental results on three datasets at both reduced- and full-resolution demonstrate the superiority of the proposed method compared with several state-of-the-art pansharpening models.