Exploiting diffusion prior for real-world image super-resolution
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 …
to-image diffusion models for blind super-resolution. Specifically, by employing our time …
Swinir: Image restoration using swin transformer
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) …
quality images from low-quality images (eg, downscaled, noisy and compressed images) …
Content-aware local gan for photo-realistic super-resolution
Recently, GAN has successfully contributed to making single-image super-resolution (SISR)
methods produce more realistic images. However, natural images have complex distribution …
methods produce more realistic images. However, natural images have complex distribution …
Hdnet: High-resolution dual-domain learning for spectral compressive imaging
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 …
reconstruction of hyperspectral image (HSI). However, existing learning-based methods …
Focal frequency loss for image reconstruction and synthesis
Image reconstruction and synthesis have witnessed remarkable progress thanks to the
development of generative models. Nonetheless, gaps could still exist between the real and …
development of generative models. Nonetheless, gaps could still exist between the real and …
Blind image super-resolution: A survey and beyond
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 …
unknown degradation, has attracted increasing attention due to its significance in promoting …
Mutual affine network for spatially variant kernel estimation in blind image super-resolution
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 …
invariant across the whole image. However, such an assumption is rarely applicable for real …
Hierarchical conditional flow: A unified framework for image super-resolution and image rescaling
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 …
For image super-resolution (SR), it learns to predict diverse photo-realistic high-resolution …
Learning the degradation distribution for blind image super-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 …
resolution (SR) methods. To avoid the domain gap between synthetic and test images, most …
Real-world blind super-resolution via feature matching with implicit high-resolution priors
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 …
in low-resolution (LR) images with complex unknown degradations (\eg, downsampling …