For image super-resolution (SR) bridging the gap between the performance on synthetic
datasets and real-world degradation scenarios remains a challenge. This work introduces a …

Most existing convolution neural network (CNN) based super-resolution (SR) methods
generate their paired training dataset by artificially synthesizing low-resolution (LR) images …

Most current super-resolution methods rely on low and high resolution image pairs to train a
network in a fully supervised manner. However, such image pairs are not available in real …

Deep Convolution Neural Networks (CNN) have achieved significant performance on single
image super-resolution (SR) recently. However, existing CNN-based methods use artificially …

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 …

Image super-resolution methods have made significant strides with deep learning
techniques and ample training data. However, they face challenges due to inherent …

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 …

In this paper, we present a large-scale Diverse Real-world image Super-Resolution dataset,
ie, DRealSR, as well as a divide-and-conquer Super-Resolution (SR) network, exploring the …

Recently, deep convolutional neural network (CNN) have achieved promising performance
for single image super-resolution (SISR). However, they usually extract features on a single …

Conventional supervised super-resolution (SR) approaches are trained with massive
external SR datasets but fail to exploit desirable properties of the given test image. On the …