Deep unfolding Network for Hyperspectral Image Super-Resolution with Automatic Exposure Correction (2403.09096v1)
Abstract: In recent years, the fusion of high spatial resolution multispectral image (HR-MSI) and low spatial resolution hyperspectral image (LR-HSI) has been recognized as an effective method for HSI super-resolution (HSI-SR). However, both HSI and MSI may be acquired under extreme conditions such as night or poorly illuminating scenarios, which may cause different exposure levels, thereby seriously downgrading the yielded HSISR. In contrast to most existing methods based on respective low-light enhancements (LLIE) of MSI and HSI followed by their fusion, a deep Unfolding HSI Super-Resolution with Automatic Exposure Correction (UHSR-AEC) is proposed, that can effectively generate a high-quality fused HSI-SR (in texture and features) even under very imbalanced exposures, thanks to the correlation between LLIE and HSI-SR taken into account. Extensive experiments are provided to demonstrate the state-of-the-art overall performance of the proposed UHSR-AEC, including comparison with some benchmark peer methods.
- “Imaging spectroscopy and the airborne visible/infrared imaging spectrometer (AVIRIS),” RSE, vol. 65, no. 3, pp. 227–248, 1998.
- “Hyperspectral image restoration via iteratively regularized weighted Schatten p𝑝pitalic_p-norm minimization,” IEEE TGRS, vol. 54, no. 8, pp. 4642–4659, 2016.
- “Automatic spectral target recognition in hyperspectral imagery,” IEEE TAES, vol. 39, no. 4, pp. 1232–1249, 2003.
- “Application of hyperspectral remote sensing in mineral identification and mapping,” in IEEE ICCSNT, 2012, pp. 103–106.
- “Hyperspectral image super-resolution via non-local sparse tensor factorization,” in IEEE CVPR, 2017, pp. 5344–5353.
- “Multiband image fusion based on spectral unmixing,” IEEE TGRS, vol. 54, no. 12, pp. 7236–7249, 2016.
- “Low-light hyperspectral image enhancement,” IEEE TGRS, vol. 60, pp. 1–13, 2022.
- “MHF-Net: An interpretable deep network for multispectral and hyperspectral image fusion,” IEEE TPAMI, vol. 44, no. 3, pp. 1457–1473, 2020.
- “Study on convex grating in hyperspectral imaging spectrometers,” in MIPPR, 2009, vol. 7494, pp. 158–164.
- “Coupled nonnegative matrix factorization unmixing for hyperspectral and multispectral data fusion,” IEEE TGRS, vol. 50, no. 2, pp. 528–537, 2011.
- “Hyperspectral image super-resolution via non-negative structured sparse representation,” IEEE TIP, vol. 25, no. 5, pp. 2337–2352, 2016.
- “Hyperspectral image super-resolution via subspace-based low tensor multi-rank regularization,” IEEE TIP, vol. 28, no. 10, pp. 5135–5146, 2019.
- “Deep blind hyperspectral image super-resolution,” IEEE TNNLS, vol. 32, no. 6, pp. 2388–2400, 2020.
- Haidi Ibrahim and Nicholas Sia Pik Kong, “Brightness preserving dynamic histogram equalization for image contrast enhancement,” IEEE TCE, vol. 53, no. 4, pp. 1752–1758, 2007.
- “Properties and performance of a center/surround retinex,” IEEE TIP, vol. 6, no. 3, pp. 451–462, 1997.
- Wenhan Yang Jiaying Liu Chen Wei, Wenjing Wang, “Deep retinex decomposition for low-light enhancement,” in BMVC, 2018.
- “Uretinex-net: Retinex-based deep unfolding network for low-light image enhancement,” in IEEE CVPR, 2022, pp. 5901–5910.
- “Exposurediffusion: Learning to expose for low-light image enhancement,” in IEEE CVPR, 2023, pp. 12438–12448.
- “LIME: Low-light image enhancement via illumination map estimation,” IEEE TIP, vol. 26, no. 2, pp. 982–993, 2016.
- “EFINet: Restoration for Low-Light Images via Enhancement-Fusion Iterative Network,” IEEE TCSVT, vol. 32, no. 12, pp. 8486–8499, 2022.
- “Learning a low tensor-train rank representation for hyperspectral image super-resolution,” IEEE TNNLS, vol. 30, no. 9, pp. 2672–2683, 2019.
- “Model-guided deep hyperspectral image super-resolution,” IEEE TIP, vol. 30, pp. 5754–5768, 2021.