STAR-Net: An Interpretable Model-Aided Network for Remote Sensing Image Denoising

TL;DR

This paper introduces STAR-Net, an interpretable deep learning model for remote sensing image denoising that effectively captures non-local self-similarity and automatically learns regularization parameters, outperforming existing methods.

Contribution

The paper proposes a novel model-aided network combining low-rank priors with deep unrolling, enhancing interpretability and robustness in RSI denoising.

Findings

STAR-Net outperforms state-of-the-art methods on synthetic and real datasets.

STAR-Net-S improves robustness against non-Gaussian noise.

The model automatically learns regularization parameters, reducing manual tuning.

Abstract

Remote sensing image (RSI) denoising is an important topic in the field of remote sensing. Despite the impressive denoising performance of RSI denoising methods, most current deep learning-based approaches function as black boxes and lack integration with physical information models, leading to limited interpretability. Additionally, many methods may struggle with insufficient attention to non-local self-similarity in RSI and require tedious tuning of regularization parameters to achieve optimal performance, particularly in conventional iterative optimization approaches. In this paper, we first propose a novel RSI denoising method named sparse tensor-aided representation network (STAR-Net), which leverages a low-rank prior to effectively capture the non-local self-similarity within RSI. Furthermore, we extend STAR-Net to a sparse variant called STAR-Net-S to deal with the interference caused by non-Gaussian noise in original RSI for the purpose of improving robustness. Different from conventional iterative optimization, we develop an alternating direction method of multipliers (ADMM)-guided deep unrolling network, in which all regularization parameters can be automatically learned, thus inheriting the advantages of both model-based and deep learning-based approaches and successfully addressing the above-mentioned shortcomings. Comprehensive experiments on synthetic and real-world datasets demonstrate that STAR-Net and STAR-Net-S outperform state-of-the-art RSI denoising methods.