We present a novel approach to leverage prior knowledge encapsulated in pre-trained text-
to-image diffusion models for blind super-resolution. Specifically, by employing our time …

Image restoration is a long-standing low-level vision problem that aims to restore high-
quality images from low-quality images (eg, downscaled, noisy and compressed images) …

Recently, GAN has successfully contributed to making single-image super-resolution (SISR)
methods produce more realistic images. However, natural images have complex distribution …

The rapid development of deep learning provides a better solution for the end-to-end
reconstruction of hyperspectral image (HSI). However, existing learning-based methods …

Image reconstruction and synthesis have witnessed remarkable progress thanks to the
development of generative models. Nonetheless, gaps could still exist between the real and …

Blind image super-resolution (SR), aiming to super-resolve low-resolution images with
unknown degradation, has attracted increasing attention due to its significance in promoting …

Existing blind image super-resolution (SR) methods mostly assume blur kernels are spatially
invariant across the whole image. However, such an assumption is rarely applicable for real …

Normalizing flows have recently demonstrated promising results for low-level vision tasks.
For image super-resolution (SR), it learns to predict diverse photo-realistic high-resolution …

Synthetic high-resolution (HR)\& low-resolution (LR) pairs are widely used in existing super-
resolution (SR) methods. To avoid the domain gap between synthetic and test images, most …

A key challenge of real-world image super-resolution (SR) is to recover the missing details
in low-resolution (LR) images with complex unknown degradations (\eg, downsampling …