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 …

Perceiving the similarity between images has been a long-standing and fundamental
problem underlying various visual generation tasks. Predominant approaches measure the …

Learning single image deraining (SID) networks from an unpaired set of clean and rainy
images is practical and valuable as acquiring paired real-world data is almost infeasible …

Abstract Non-Local Attention (NLA) brings significant improvement for Single Image Super-
Resolution (SISR) by leveraging intrinsic feature correlation in natural images. However …

Guided depth map super-resolution (GDSR), as a hot topic in multi-modal image processing,
aims to upsample low-resolution (LR) depth maps with additional information involved in …

Infrared and visible image fusion targets to provide an informative image by combining
complementary information from different sensors. Existing learning-based fusion …

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 …

Blind image deblurring (BID) remains a challenging and significant task. Benefiting from the
strong fitting ability of deep learning, paired data-driven supervised BID methods have …

Contrastive learning has achieved remarkable success on various high-level tasks, but there
are fewer contrastive learning-based methods proposed for low-level tasks. It is challenging …

Generative adversarial networks (GANs) have achieved great success in image translation
and manipulation. However, high-fidelity image generation with faithful style control remains …