CPAD: Component Pixel-Aware Multispectral Image Destriping

Abstract

Stripe noise removal of Multispectral images (MSIs) is a challenging topic and has attracted substantial research attention in remote sensing areas. Existing destriping methods mainly concentrate on patch-based model representation, which ignores the heterogeneous components across the degraded MSIs and poorly utilizes the prior knowledge of the image cubes of the MSIs on high-level perception. In this paper, we present a component pixel-aware MSIs destriping method. Intuitively, the image cube of the MSIs is divided into three different components (the jump, transition, and gentle components) based on the gradients of each pixel. Then, three different regularization operators are adopted adaptively for different components in a pixel-level manner. In addition, to properly depict the stripe cube of the MSIs, we exploit the non-convex non-smooth iteratively reweight nuclear norm. By incorporating both improved terms, our proposed method can estimate the component-variant linear representation coefficients and model the structural information of both the stripe cube and image cube. The alternating direction method of multipliers (ADMM) is adopted to solve the proposed method. Evaluating various destriping performance measurements, the algorithm proposed in this paper outperforms other state-of-the-art methods under extensive experiments on synthetic and real datasets.