This work aims to learn a high-quality text-to-video (T2V) generative model by leveraging a
pre-trained text-to-image (T2I) model as a basis. It is a highly desirable yet challenging task …

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 …

Unconditional human image generation is an important task in vision and graphics, enabling
various applications in the creative industry. Existing studies in this field mainly focus on …

We show that pre-trained Generative Adversarial Networks (GANs), eg, StyleGAN, can be
used as a latent bank to improve the restoration quality of large-factor image super …

Reference-based image super-resolution (RefSR) aims to exploit auxiliary reference (Ref)
images to super-resolve low-resolution (LR) images. Recently, RefSR has been attracting …

Abstract We present Reference-guided Super-Resolution Neural Radiance Field (RefSR-
NeRF) that extends NeRF to super resolution and photorealistic novel view synthesis …

Unpaired medical image enhancement (UMIE) aims to transform a low-quality (LQ) medical
image into a high-quality (HQ) one without relying on paired images for training. While most …

One key challenge of exemplar-guided image generation lies in establishing fine-grained
correspondences between input and guided images. Prior approaches, despite the …

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 …

Generative models operate at fixed resolution, even though natural images come in a variety
of sizes. As high-resolution details are downsampled away and low-resolution images are …