Deep neural networks have provided state-of-the-art solutions for problems such as image
denoising, which implicitly rely on a prior probability model of natural images. Two recent …

The performance of objective image quality assessment (IQA) models has been evaluated
primarily by comparing model predictions to human quality judgments. Perceptual datasets …

Many state-of-the-art image restoration approaches do not scale well to larger images, such
as megapixel images common in the consumer segment. Computationally expensive …

Learning good image priors is of utmost importance for the study of vision, computer vision
and image processing applications. Learning priors and optimizing over whole images can …

We review the evolution of the nonparametric regression modeling in imaging from the local
Nadaraya-Watson kernel estimate to the nonlocal means and further to transform-domain …

Deep convolutional networks often append additive constant (" bias") terms to their
convolution operations, enabling a richer repertoire of functional mappings. Biases are also …

Over the last decade, the number of digital images captured per day has increased
exponentially, due to the accessibility of imaging devices. The visual quality of photographs …

What makes an image appear realistic? In this work, we are answering this question from a
data-driven perspective by learning the perception of visual realism directly from large …

Prior probability models are a fundamental component of many image processing problems,
but density estimation is notoriously difficult for high-dimensional signals such as …

Deep convolutional neural networks (CNNs) for image denoising are typically trained on
large datasets. These models achieve the current state of the art, but they do not generalize …