Real-world imagery does not always exhibit good visibility and clean content, but often suffers from various kinds of degradations (e.g., noise, blur, rain drops, fog, color distortion, etc.), which severely affect vision-driven tasks (e.g., image classification, target recognition, and tracking, etc.). Thus, restoring the true scene from such degraded images is of significance. In recent years, a large body of deep learning-based image processing works has been exploited due to the advances in deep neural networks. This paper aims to make a comprehensive review of real-world image restoration algorithms and beyond. More specifically, this review provides overviews of critical benchmark datasets, image quality assessment methods, and four major categories of deep learning-based image restoration methods, i.e., based on convolutional neural network (CNN), generative adversarial network (GAN), Transformer, and multi-layer perceptron (MLP). The paper highlights the latest developments and advances in each category of network architecture to provide an up-to-date overview. Moreover, the representative state-of-the-art image restoration methods are compared visually and numerically. Finally, for real-world image restoration, the current situations are objectively assessed, challenges are discussed, and future directions and trends are presented.

Amnestic mild cognitive impairment (aMCI) is the transitional, heterogeneous continuum from normal elderly to Alzheimer's disease (AD). Previous studies have shown that brain functional activity in the default mode network (DMN) is impaired in aMCI patients with saliently cognitive and memory decline. However, the effective connectivity among the spatially isolated, but functionally related areas within the DMN in aMCI patients remains largely unknown. The present study examined dysfunctional connectivity of the DMN by combining an independent component analysis (ICA) approach with multivariate Granger causality analysis (mGCA) in 18 aMCI patients and 18 age-matched cognitively normal elderly. Results from mGCA showed decreased effective connectivity occurred among the middle temporal gyrus (MTG), hippocampus (HC) and fusiform gyrus (FG), as well as between the precuneus/posterior cingulate cortex (PreCN/PCC) and HC in patients with aMCI. Such an impaired connectivity was also correlated with patients’ cognitive performance of the auditory verbal learning. Moreover, enhanced effective connectivity within frontal cortex emerged, which may maintain memory functions after attenuated connections within DMN activity. These findings may elucidate the dysfunctional processes in brain networks of aMCI patients, highlighting the importance of connectivity changes in the pathophysiology of aMCI. (JINS, 2013, 19, 1–10)