Single image super-resolution (SISR), which aims to reconstruct a high-resolution (HR)
image from a low-resolution (LR) observation, has been an active research topic in the area …

Deep convolutional networks–based super-resolution is a fast-growing field with numerous
practical applications. In this exposition, we extensively compare more than 30 state-of-the …

Previous works have shown that increasing the window size for Transformer-based image
super-resolution models (eg, SwinIR) can significantly improve the model performance but …

Video restoration aims to restore high-quality frames from low-quality frames. Different from
single image restoration, video restoration generally requires to utilize temporal information …

Video restoration aims at restoring multiple high-quality frames from multiple low-quality
frames. Existing video restoration methods generally fall into two extreme cases, ie, they …

A recurrent structure is a popular framework choice for the task of video super-resolution.
The state-of-the-art method BasicVSR adopts bidirectional propagation with feature …

Dynamic neural network is an emerging research topic in deep learning. Compared to static
models which have fixed computational graphs and parameters at the inference stage …

Video super-resolution (VSR) approaches tend to have more components than the image
counterparts as they need to exploit the additional temporal dimension. Complex designs …

Optical-flow-based and kernel-based approaches have been extensively explored for
temporal compensation in satellite Video Super-Resolution (VSR). However, these …

Video restoration tasks, including super-resolution, deblurring, etc, are drawing increasing
attention in the computer vision community. A challenging benchmark named REDS is …