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

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 …

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 …

Abstract Generative Adversarial Networks (GANs) have been widely used to recover vivid
textures in image super-resolution (SR) tasks. In particular one discriminator is utilized to …

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 …

Current CNN-based super-resolution (SR) methods process all locations equally with
computational resources being uniformly assigned in space. However, since missing details …

Reference-based image super-resolution (RefSR) has shown promising success in
recovering high-frequency details by utilizing an external reference image (Ref). In this task …

Single-image super-resolution (SISR) networks trained with perceptual and adversarial
losses provide high-contrast outputs compared to those of networks trained with distortion …

How to generate the ground-truth (GT) image is a critical issue for training realistic image
super-resolution (Real-ISR) models. Existing methods mostly take a set of high-resolution …