USCTNet: A deep unfolding nuclear-norm optimization solver for physically consistent HSI reconstruction
This addresses physically inconsistent HSI reconstruction for computer vision applications, but it is incremental as it builds on existing deep unfolding and regularization techniques.
The paper tackles the ill-posed problem of reconstructing hyperspectral images from a single RGB image by formulating it as a physics-grounded inverse problem with explicit estimation of camera spectral sensitivity and illumination, resulting in consistent improvements in reconstruction accuracy over state-of-the-art methods.
Reconstructing hyperspectral images (HSIs) from a single RGB image is ill-posed and can become physically inconsistent when the camera spectral sensitivity (CSS) and scene illumination are misspecified. We formulate RGB-to-HSI reconstruction as a physics-grounded inverse problem regularized by a nuclear norm in a learnable transform domain, and we explicitly estimate CSS and illumination to define the forward operator embedded in each iteration, ensuring colorimetric consistency. To avoid the cost and instability of full singular-value decompositions (SVDs) required by singular-value thresholding (SVT), we introduce a data-adaptive low-rank subspace SVT operator. Building on these components, we develop USCTNet, a deep unfolding solver tailored to HSI that couples a parameter estimation module with learnable proximal updates. Extensive experiments on standard benchmarks show consistent improvements over state-of-the-art RGB-based methods in reconstruction accuracy. Code: https://github.com/psykheXX/USCTNet-Code-Implementation.git