Diffusion-based image super-resolution (SR) methods are mainly limited by the low
inference speed due to the requirements of hundreds or even thousands of sampling steps …

Deep convolutional neural networks can effectively improve the performance of single-
image super-resolution reconstruction. Deep networks tend to achieve better performance …

High-fidelity information, such as 4K quality videos and photographs, is increasing as high-
speed internet access becomes more widespread and less expensive. Even though camera …

In this paper, we take a new look at real-world image super-resolution (real-SR) from a multi-
task learning perspective. We demonstrate that the conventional formulation of real-SR can …

Consistency and realness have always been the two critical issues of image super-
resolution. While the realness has been dramatically improved with the use of GAN prior, the …

Blind image super-resolution (Blind-SR) aims to recover a high-resolution (HR) image from
its corresponding low-resolution (LR) input image with unknown degradations. Most of the …

This paper explores training efficient VGG-style super-resolution (SR) networks with the
structural re-parameterization technique. The general pipeline of re-parameterization is to …

With the development of generative adversarial networks (GANs), recent face restoration
(FR) methods often utilize pre-trained GAN models (ie,, StyleGAN2) as prior to generate rich …

Abstract 360deg omnidirectional images have gained research attention due to their
immersive and interactive experience, particularly in AR/VR applications. However, they …

Image restoration is a critical task in low-level computer vision, aiming to restore high-quality
images from degraded inputs. Various models, such as convolutional neural networks …