Humans can naturally and effectively find salient regions in complex scenes. Motivated by
this observation, attention mechanisms were introduced into computer vision with the aim of …

Astounding results from Transformer models on natural language tasks have intrigued the
vision community to study their application to computer vision problems. Among their salient …

Since convolutional neural networks (CNNs) perform well at learning generalizable image
priors from large-scale data, these models have been extensively applied to image …

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) …

Transformer-based methods have shown impressive performance in low-level vision tasks,
such as image super-resolution. However, we find that these networks can only utilize a …

Though many attempts have been made in blind super-resolution to restore low-resolution
images with unknown and complex degradations, they are still far from addressing general …

In this paper, we present Uformer, an effective and efficient Transformer-based architecture
for image restoration, in which we build a hierarchical encoder-decoder network using the …

We present SR3, an approach to image Super-Resolution via Repeated Refinement. SR3
adapts denoising diffusion probabilistic models (Ho et al. 2020),(Sohl-Dickstein et al. 2015) …

Image restoration tasks demand a complex balance between spatial details and high-level
contextualized information while recovering images. In this paper, we propose a novel …

As the computing power of modern hardware is increasing strongly, pre-trained deep
learning models (eg, BERT, GPT-3) learned on large-scale datasets have shown their …