IEEE Journal of Selected Topics in Signal Processing

The papers in this special issue focus on deep learning for image/video restoration and compression. The huge success of deep-learning–based approaches in computer vision has inspired research in learned solutions to classic image/video processing problems, such as denoising, deblurring, dehazing, deraining, super-resolution (SR), and compression. Hence, learning-based methods have emerged as a promising nonlinear signal-processing framework for image/ video restoration and compression.

The papers in this special issue focus on deep learning for image/video restoration and compression. The huge success of deep-learning–based approaches in computer vision has inspired research in learned solutions to classic image/video processing problems, such as denoising, deblurring, dehazing, deraining, super-resolution (SR), and compression. Hence, learning-based methods have emerged as a promising nonlinear signal-processing framework for image/ video restoration and compression.

Dynamic range limitations in signal processing often lead to clipping, or saturation, in signals. The task of audio declipping is estimating the original audio signal, given its clipped measurements, and has attracted much interest in recent years. Audio declipping algorithms often make assumptions about the underlying signal, such as sparsity or low-rankness, and about the measurement system.

The papers from this special section focus on the restoration of udio content, in particular speech and music from degraded observations. This is a challenging and long-standing problem in audio processing. In particular this holds for severe degradations and incomplete observations, which are regularly encountered in practice. The papers in this section have been organized to gather contributions that would serve both as a comprehensive primer on the stateof- the-art, and a showcase of current developments within the field.

In magnetic resonance imaging (MRI), several images can be obtained using different imaging settings (e.g. T1, T2, DWI, and Flair). These images have similar anatomical structures but are with different contrasts, which provide a wealth of information for diagnosis.

Recently, deep neural network (DNN) based methods for low-dose CT have been investigated to achieve excellent performance in both image quality and computational speed. However, almost all methods using DNNs for low-dose CT require clean ground truth data with full radiation dose to train the DNNs. In this work, we attempt to train DNNs for low-dose CT reconstructions with reduced tube current by investigating unsupervised training of DNNs for denoising sensor measurements or sinograms without full-dose ground truth images.

Regularization by denoising (RED) is an image reconstruction framework that uses an image denoiser as a prior. Recent work has shown the state-of-the-art performance of RED with learned denoisers corresponding to pre-trained convolutional neural nets (CNNs). In this work, we propose to broaden the current denoiser-centric view of RED by considering priors corresponding to networks trained for more general artifact-removal.

One challenging aspect in face anti-spoofing (or presentation attack detection, PAD) refers to the difficulty of collecting enough and representative attack samples for an application-specific environment. In view of this, we tackle the problem of training a robust PAD model with limited data in an application-specific domain.