In this paper, we take a new look at real-world image super-resolution (real-SR) from a multi-
task learning perspective. We demonstrate that the conventional formulation of real-SR can …

We study the behavior of deterministic methods for solving inverse problems in imaging.
These methods are commonly designed to achieve two goals:(1) attaining high perceptual …

Recently developed deep neural network methods have achieved remarkable performance
in the Super Resolution (SR) problem when applied to Low Resolution (LR) images that are …

Abstract Real-world Super-Resolution (SR) has been traditionally tackled by first learning a
specific degradation model that resembles the noise and corruption artifacts in low …

Modulating image restoration level aims to generate a restored image by altering a factor
that represents the restoration strength. Previous works mainly focused on optimizing the …

Real-world image super-resolution (SR) tasks often do not have paired datasets limiting the
application of supervised techniques. As a result, the tasks are usually approached by …

Real-world image super-resolution (SR) tasks often do not have paired datasets, which
limits the application of supervised techniques. As a result, the tasks are usually approached …

Current super-resolution methods rely on the bicubic down-sampling assumption in order to
develop the ill-posed reconstruction of the low-resolution image. Not surprisingly, these …

Self-supervised learning is crucial for super-resolution because ground-truth images are
usually unavailable for real-world settings. Existing methods derive self-supervision from low …

Although single image super-resolution (SR) has achieved great success, super-resolving
the real-world Ultra-High-Resolution (UHR) image remains a challenging issue. Confronted …