Hyperspectral image inpainting based on low-rank representation: A case study on Tiangong-1 data

Abstract

Hyperspectral images (HSIs) cover hundreds of narrow spectral bands, thus yielding high spectral resolution, enabling precise identification of different materials. However, the existence of dead pixels in the light sensors produces a number of irrelevant measurements, which may compromise the usefulness of HSIs. In this paper, a new hyperspectral inpainting method, named HyInpaint, is proposed. The original HSI is represented on a low dimensional subspace and its estimation is formalized with respect to the subspace representation coefficients on a given basis. The coefficients are estimated by minimizing an objective function which, in addition to the data term, contains a regularizer based on the Criminisi's inpainting method. The optimization is carried out by an instance of the alternating direction method of multipliers (ADMM), adopting the plug-and-play methodology. The effectiveness of the proposed HyInpaint approach is illustrated on Tiangong-1 hyperspectral visible near infrared (VNIR) wavebands data.