Zero-Shot Hyperspectral Pansharpening Using Hysteresis-Based Tuning for Spectral Quality Control

2025-05-22

AI Summary

Hyperspectral image pansharpening faces challenges including high spectral dimensionality, heterogeneous noise, spectral-spatial misalignment, and large spatial resolution ratios—leading to inconsistent spectral fidelity and compromised quality across all bands. To address these issues, we propose a zero-shot, unsupervised pansharpening framework. Our method introduces a hysteresis-based loss scheduling mechanism that dynamically activates or deactivates spatial loss to precisely balance spectral fidelity; incorporates band-wise adaptive weighting and a redefined nonlinear spatial loss; and employs a lightweight network enabling online fine-tuning and joint spectral-spatial optimization. Evaluated on the latest benchmark datasets, our approach achieves superior full-band spectral consistency and fidelity, outperforming state-of-the-art methods. All code and experimental results are publicly released.

Technology Category

• Computer Vision: Learning & Optimization for CV
• Machine Learning: Calibration & Uncertainty Quantification
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Hyperspectral pansharpening has received much attention in recent years due to technological and methodological advances that open the door to new application scenarios. However, research on this topic is only now gaining momentum. The most popular methods are still borrowed from the more mature field of multispectral pansharpening and often overlook the unique challenges posed by hyperspectral data fusion, such as i) the very large number of bands, ii) the overwhelming noise in selected spectral ranges, iii) the significant spectral mismatch between panchromatic and hyperspectral components, iv) a typically high resolution ratio. Imprecise data modeling especially affects spectral fidelity. Even state-of-the-art methods perform well in certain spectral ranges and much worse in others, failing to ensure consistent quality across all bands, with the risk of generating unreliable results. Here, we propose a hyperspectral pansharpening method that explicitly addresses this problem and ensures uniform spectral quality. To this end, a single lightweight neural network is used, with weights that adapt on the fly to each band. During fine-tuning, the spatial loss is turned on and off to ensure a fast convergence of the spectral loss to the desired level, according to a hysteresis-like dynamic. Furthermore, the spatial loss itself is appropriately redefined to account for nonlinear dependencies between panchromatic and spectral bands. Overall, the proposed method is fully unsupervised, with no prior training on external data, flexible, and low-complexity. Experiments on a recently published benchmarking toolbox show that it ensures excellent sharpening quality, competitive with the state-of-the-art, consistently across all bands. The software code and the full set of results are shared online on https://github.com/giu-guarino/rho-PNN.

Problem

• Ensures uniform spectral quality in hyperspectral pansharpening
• Addresses noise and spectral mismatch in hyperspectral data fusion
• Achieves consistent sharpening quality across all spectral bands

Innovation

• Lightweight neural network with adaptive weights
• Hysteresis-like dynamic for spectral loss control
• Redefined spatial loss for nonlinear dependencies