PanBench: Towards High-Resolution and High-Performance Pansharpening

TL;DR

This paper introduces PanBench, a comprehensive high-resolution dataset for pansharpening, and proposes a novel Cascaded Multiscale Fusion Network (CMFNet) that significantly improves the quality of pansharpened images, advancing remote sensing applications.

Contribution

The paper presents PanBench, a large multi-scene dataset for high-resolution pansharpening, and introduces CMFNet, a new deep learning model that achieves superior synthesis performance.

Findings

CMFNet outperforms existing methods in quality metrics.

PanBench enables more robust evaluation across diverse satellite data.

High-resolution data improves the fidelity of pansharpened images.

Abstract

Pansharpening, a pivotal task in remote sensing, involves integrating low-resolution multispectral images with high-resolution panchromatic images to synthesize an image that is both high-resolution and retains multispectral information. These pansharpened images enhance precision in land cover classification, change detection, and environmental monitoring within remote sensing data analysis. While deep learning techniques have shown significant success in pansharpening, existing methods often face limitations in their evaluation, focusing on restricted satellite data sources, single scene types, and low-resolution images. This paper addresses this gap by introducing PanBench, a high-resolution multi-scene dataset containing all mainstream satellites and comprising 5,898 pairs of samples. Each pair includes a four-channel (RGB + near-infrared) multispectral image of 256x256 pixels and a mono-channel panchromatic image of 1,024x1,024 pixels. To achieve high-fidelity synthesis, we propose a Cascaded Multiscale Fusion Network (CMFNet) for Pansharpening. Extensive experiments validate the effectiveness of CMFNet. We have released the dataset, source code, and pre-trained models in the supplementary, fostering further research in remote sensing.