Physics-Guided Deep Unfolding for Blind Cross-Sensor Spectral Super-Resolution via Learning the Spectral Transformation Function

2026-06-04

AI Summary

This work addresses the challenge of spectral super-resolution under blind cross-sensor settings, where existing methods fail due to their reliance on known and fixed spectral response functions, rendering the reconstruction problem ill-posed when sensor characteristics are unknown and variable. To overcome this limitation, we propose PGU-Net, the first framework that jointly learns high-resolution hyperspectral images and a learnable spectral transformation function without prior knowledge of the sensor. Our approach embeds a physical degradation model into a deep unfolding architecture, integrating a differentiable closed-form solver with a learnable proximal network to balance model interpretability and representational capacity. Experiments demonstrate that PGU-Net consistently outperforms state-of-the-art methods on the CAVE, NTIRE 2022, and real-world drone datasets, accurately recovering the spectral transformation function and revealing its intrinsic relationship with land cover types.

Abstract

Hyperspectral imaging provides rich spectral information for quantitative remote sensing, yet hyperspectral sensors remain costly and thus unavailable in many UAV deployments. Spectral super-resolution (SSR) seeks to reconstruct hyperspectral images (HSIs) from multispectral images (MSIs). Most existing SSR methods assume a fixed and known spectral response function (SRF) and are therefore limited to single-sensor settings. In practical cross-sensor scenarios, the spectral degradation from HSI to MSI is unknown and varies with sensor characteristics and scene content, which renders HSI reconstruction ill-posed. This paper proposes a physics-guided deep unfolding network, termed PGU-Net, to address blind cross-sensor SSR by jointly estimating the HSI and a learnable spectral transformation function (STF). PGU-Net unrolls an alternating optimization procedure into an end-to-end trainable architecture with stages, where each stage sequentially updates the HSI and the STF. Both modules combine learnable proximal networks with differentiable closed-form solvers, enabling physical interpretability while retaining strong representation capacity. Experiments on benchmark datasets (CAVE and NTIRE 2022) with multiple SRFs demonstrate accurate recovery of the STF (degradation operator) and improved reconstruction performance over state-of-the-art SSR methods. Furthermore, evaluations on a real UAV cross-sensor dataset (Headwall Nano HSI and DJI P4 Multispectral MSI) verify the effectiveness and robustness of PGU-Net under truly blind conditions, and suggest that the estimated STF may exhibit land-cover-related differences.

Problem

• spectral super-resolution
• blind cross-sensor
• hyperspectral imaging
• spectral transformation function
• ill-posed reconstruction

Innovation

• physics-guided deep unfolding
• blind cross-sensor spectral super-resolution
• spectral transformation function
• end-to-end trainable architecture
• hyperspectral image reconstruction