A sheared low-rank model for oblique stripe removal

Abstract

Stripe noise removal from remote sensing imagery is a key preprocessing step for many applications, such as urban planning, military, and environmental monitoring. Two significant priors of the stripe are low-rankness and group sparsity, which play a central role in many destriping methods. However, for oblique stripes, these two priors are no longer explicitly applicable. To overcome this difficulty, we propose a novel sheared decomposition framework for oblique stripe removal. The main idea is to perform a shear operation on the observed image, so that the oblique stripe is transformed to nearly vertical lines. For the stripe component, we characterize the low-rankness and group sparsity priors in the sheared domain. For the image component, we characterize the smoothness prior in the original domain by unidirectional total variation (UTV), which can preserve the strong edges and geometric features while suppressing stripes. To solve the proposed model, we design an efficient alternating direction method of multipliers (ADMM) algorithm with guaranteed convergence. Experiments using simulated and real data show that the proposed method can remove the oblique stripe effectively and outperform the state-of-the-art methods qualitatively and quantitatively.