HADAR-Based Thermal Infrared Hyperspectral Image Restoration

2026-05-13

AI Summary

Thermal infrared hyperspectral imagery is highly susceptible to sensor degradation, yet existing restoration methods often neglect underlying thermophysical principles, compromising reconstruction fidelity. This work proposes HAIR, a novel framework that, for the first time, integrates thermophysical priors into image restoration by leveraging the HADAR rendering equation and an atmospheric downwelling radiative transfer model to formulate a physically grounded temperature–emissivity–texture (TeX) triplet. HAIR employs a TeX decomposition–synthesis strategy augmented with forward-modeled atmospheric references and spectral smoothness constraints to achieve physically consistent spectral calibration and noise-robust restoration. Evaluated on the DARPA Invisible Headlights dataset and laboratory FTIR measurements, HAIR consistently outperforms state-of-the-art methods across denoising, inpainting, spectral calibration, and super-resolution tasks, achieving superior performance in both quantitative accuracy and visual quality.

Abstract

Thermal-infrared (TIR) hyperspectral imagery (HSI) provides critical scene information for various applications. However, its practical utility is severely limited by unique sensor degradations beyond the capabilities of existing restoration methods, which are ignorant of underlying thermal physics. Here, we propose HAIR (HADAR-based Image Restoration) as a physics-driven framework for ground-based TIR-HSI restoration. HAIR utilizes the HADAR rendering equation (HRE) and combines it with the atmospheric downwelling radiative transfer equation (RTE) to model TIR-HSI using temperature, emissivity, and texture (TeX) physical triplets. This physical model leads to a TeX decompose-synthesize strategy that guarantees physical consistency and spatio-spectral noise resilience, in stark contrast to existing approaches. Moreover, our framework uses a forward-modeled atmospheric downwelling reference, along with spectral smoothness of emissivity and blackbody radiation, to enable spectral calibration and generation that would otherwise be elusive. Our extensive experiments on the outdoor DARPA Invisible Headlights dataset and in-lab FTIR measurements show that HAIR consistently outperforms state-of-the-art methods across denoising, inpainting, spectral calibration, and spectral super-resolution, establishing a benchmark in objective accuracy and visual quality.

Problem

• thermal-infrared hyperspectral imagery
• image restoration
• sensor degradation
• thermal physics
• spectral calibration

Innovation

• HADAR
• thermal infrared hyperspectral imaging
• physics-driven restoration
• radiative transfer equation
• spectral calibration