Single image super-resolution (SISR), which aims to reconstruct a high-resolution (HR)
image from a low-resolution (LR) observation, has been an active research topic in the area …

Abstract Single Image Super Resolution (SISR) is a process to obtain a high pixel density
and refined details from a low resolution (LR) image to get upscaled and sharper high …

We describe an approach for incorporating prior knowledge into machine learning
algorithms. We aim at applications in physics and signal processing in which we know that …

We propose a deep reparametrization of the maximum a posteriori formulation commonly
employed in multi-frame image restoration tasks. Our approach is derived by introducing a …

Recently, the application of satellite remote sensing images is becoming increasingly
popular, but the observed images from satellite sensors are frequently in low-resolution …

Video superresolution (SR) techniques are of essential usages for high-resolution display
devices due to the current lack of high-resolution videos. Although many algorithms have …

Capturing ground truth data to benchmark super-resolution (SR) is challenging. Therefore,
current quantitative studies are mainly evaluated on simulated data artificially sampled from …

This paper addresses the robust reconstruction problem of a sparse signal from compressed
measurements. We propose a robust formulation for sparse reconstruction that employs the …

The suppression of streak artifacts in computed tomography with a limited-angle
configuration is challenging. Conventional analytical algorithms, such as filtered …

To make the face hallucination process robust to impulse noise, a new outlier elimination
based iterative neighbor representation (OEINR) algorithm is proposed in this work. The …