Spectral Compressive Imaging via Chromaticity-Intensity Decomposition
This work addresses the challenge of recovering intrinsic spectral reflectance under varying lighting conditions in hyperspectral imaging, which is incremental as it builds on existing CASSI methods with a novel decomposition approach.
The paper tackled the ill-posed inverse problem in coded aperture snapshot spectral imaging (CASSI) by proposing a chromaticity-intensity decomposition framework to disentangle hyperspectral images into lighting-invariant reflectance and intensity components, achieving superior performance in spectral and chromaticity fidelity on synthetic and real-world datasets.
In coded aperture snapshot spectral imaging (CASSI), the captured measurement entangles spatial and spectral information, posing a severely ill-posed inverse problem for hyperspectral images (HSIs) reconstruction. Moreover, the captured radiance inherently depends on scene illumination, making it difficult to recover the intrinsic spectral reflectance that remains invariant to lighting conditions. To address these challenges, we propose a chromaticity-intensity decomposition framework, which disentangles an HSI into a spatially smooth intensity map and a spectrally variant chromaticity cube. The chromaticity encodes lighting-invariant reflectance, enriched with high-frequency spatial details and local spectral sparsity. Building on this decomposition, we develop CIDNet, a Chromaticity-Intensity Decomposition unfolding network within a dual-camera CASSI system. CIDNet integrates a hybrid spatial-spectral Transformer tailored to reconstruct fine-grained and sparse spectral chromaticity and a degradation-aware, spatially-adaptive noise estimation module that captures anisotropic noise across iterative stages. Extensive experiments on both synthetic and real-world CASSI datasets demonstrate that our method achieves superior performance in both spectral and chromaticity fidelity. Code and models will be publicly available.