Hyperspectral Pansharpening: Critical Review, Tools and Future Perspectives
Matteo Ciotola, Giuseppe Guarino, Gemine Vivone, Giovanni Poggi, Jocelyn Chanussot, Antonio Plaza, Giuseppe Scarpa
TL;DR
This paper formalizes a reproducible benchmarking framework for hyperspectral pansharpening by assembling a large, diverse PAN+HS dataset from PRISMA, re-implementing a curated set of state-of-the-art methods across CS, MRA, MBO, and DL in a unified PyTorch toolbox, and evaluating them with reduced- and full-resolution metrics. The study systematically analyzes spectral and spatial quality, generalization across datasets and scales, and computational efficiency, revealing strengths in certain classical and DL approaches and highlighting gaps in cross-domain generalization and full-resolution performance. It also emphasizes the limitations of current quality metrics for HS data and provides open-source resources to foster fair comparisons and rapid development of new methods. The work offers practical guidance for researchers and practitioners by delivering a comprehensive, scalable benchmark and a publicly available toolbox to advance HS pansharpening research.
Abstract
Hyperspectral pansharpening consists of fusing a high-resolution panchromatic band and a low-resolution hyperspectral image to obtain a new image with high resolution in both the spatial and spectral domains. These remote sensing products are valuable for a wide range of applications, driving ever growing research efforts. Nonetheless, results still do not meet application demands. In part, this comes from the technical complexity of the task: compared to multispectral pansharpening, many more bands are involved, in a spectral range only partially covered by the panchromatic component and with overwhelming noise. However, another major limiting factor is the absence of a comprehensive framework for the rapid development and accurate evaluation of new methods. This paper attempts to address this issue. We started by designing a dataset large and diverse enough to allow reliable training (for data-driven methods) and testing of new methods. Then, we selected a set of state-of-the-art methods, following different approaches, characterized by promising performance, and reimplemented them in a single PyTorch framework. Finally, we carried out a critical comparative analysis of all methods, using the most accredited quality indicators. The analysis highlights the main limitations of current solutions in terms of spectral/spatial quality and computational efficiency, and suggests promising research directions. To ensure full reproducibility of the results and support future research, the framework (including codes, evaluation procedures and links to the dataset) is shared on https://github.com/matciotola/hyperspectral_pansharpening_toolbox, as a single Python-based reference benchmark toolbox.