Self-supervised Deep Hyperspectral Inpainting with the Sparsity and Low-Rank Considerations
This addresses data loss and noise issues in hyperspectral imaging for practical applications, though it appears incremental as it builds on existing plug-and-play methods.
The authors tackled hyperspectral image inpainting by introducing two self-supervised algorithms, LRS-PnP and LRS-PnP-DIP, which achieved state-of-the-art performance with visually and qualitatively superior results.
Hyperspectral images are typically composed of hundreds of narrow and contiguous spectral bands, each containing information about the material composition of the imaged scene. However, these images can be affected by various sources of noise, distortions, or data losses, which can significantly degrade their quality and usefulness. To address these problems, we introduce two novel self-supervised Hyperspectral Images (HSI) inpainting algorithms: Low Rank and Sparsity Constraint Plug-and-Play (LRS-PnP), and its extension LRS-PnP-DIP, which features the strong learning capability, but is still free of external training data. We conduct the stability analysis under some mild assumptions which guarantees the algorithm to converge. It is specifically very helpful for the practical applications. Extensive experiments demonstrate that the proposed solution is able to produce visually and qualitatively superior inpainting results, achieving state-of-the-art performance. The code for reproducing the results is available at \url{https://github.com/shuoli0708/LRS-PnP-DIP}.