Data augmentation is an effective way to improve the performance of deep networks.
Unfortunately, current methods are mostly developed for high-level vision tasks (eg …

By benefiting from perceptual losses, recent studies have improved significantly the
performance of the super-resolution task, where a high-resolution image is resolved from its …

Owe to the powerful generative priors the pre-trained text-to-image (T2I) diffusion models
have become increasingly popular in solving the real-world image super-resolution …

Deep learning techniques have been successfully applied in many areas of computer vision,
including low-level image restoration problems. For image super-resolution, several models …

Deep convolutional neural networks (CNNs) have pushed forward the frontier of super-
resolution (SR) research. However, current CNN models exhibit a major flaw: they are …

Transformer has recently gained considerable popularity in low-level vision tasks, including
image super-resolution (SR). These networks utilize self-attention along different …

In recent years, single image super-resolution (SISR) methods using deep convolution
neural network (CNN) have achieved impressive results. Thanks to the powerful …

Most of the existing learning-based single image super-resolution (SISR) methods are
trained and evaluated on simulated datasets, where the low-resolution (LR) images are …

Abstract Deep Convolutional Neural Networks (CNNs) have achieved remarkable results on
Single Image Super-Resolution (SISR). Despite considering only a single degradation …

Deep neural networks have exhibited promising performance in image super-resolution
(SR) by learning a nonlinear mapping function from low-resolution (LR) images to high …