Dual-Branch Multi-Level Feature Aggregation Network for Pansharpening

Dear Editor, In pansharpening task, the most existing deep-learning-based pan-sharpening methods fail to fully utilize different level features, inevitably leading spectral or spatial distortions. To address this challenge, in letter, we propose a dual-branch multi-level feature aggregation network for (DMFANet). The experimental results on WorldView-II (WV-II) and QuickBird (QB) dataset confirmed notable superiority of our method over current state-of-the-art from quantitative qualitative point view. source code is available at https://github.com/Gui-Cheng/DMFANet.