mlsanityData to 14 Oct 2026

USCTNet: A deep unfolding nuclear-norm optimization solver for physically consistent HSI reconstruction

arXiv 2509.10651 ↗First posted 12 Sep 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 11 of its 22 references that are in the map. First posted on arXiv 12 Sep 2025.

Builds on

11 of 22 references.

References · 11

  1. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,627
  2. 2021Multi-Stage Progressive Image Restorationcited by 816
  3. 2021HINet: Half Instance Normalization Network for Image Restorationcited by 237
  4. 2021Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstructioncited by 110
  5. 2022MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstructioncited by 72
  6. 2020AdaptiveWeighted Attention Network with Camera Spectral Sensitivity Prior for Spectral Reconstruction from RGB Imagescited by 29
  7. 2023Hyperspectral Image Reconstruction via Combinatorial Embedding of Cross-Channel Spatio-Spectral Cluescited by 10
  8. 2022T2LR-Net: An unrolling network learning transformed tensor low-rank prior for dynamic MR image reconstructioncited by 4
  9. 2024Differentiable SVD based on Moore-Penrose Pseudoinverse for Inverse Imaging Problemscited by 3
  10. 2023Learning to Recover Spectral Reflectance from RGB Imagescited by 2
  11. 2025JotlasNet: Joint Tensor Low-Rank and Attention-based Sparse Unrolling Network for Accelerating Dynamic MRIcited by 1

Built on by

Not cited yet.