… The task of super-resolution can be split into the groups of single image superresolution and
multi-frame or video super-resolution methods. Single image super-resolution is one of the …

… Video super-resolution (VSR) aims to restore a photorealistic high-resolution (HR) video
frame from both its … The goal of video super-resolution (VSR) is to reconstruct a high-…

… state-ofthe-art super-resolution approaches. Results on both … VAE can achieve good
photo-realistic perceptual quality closer … and video signal processing, and image and video super-…

… is not photorealistic as defined by Ferwerda [15]. In this work we propose a super-resolution …
An example photo-realistic image that was superresolved with a 4× upscaling factor is …

… Previous CNN-based video super-resolution approaches need to align multiple frames to …
Analysis and experiments show the suitability of this layer in video SR. The final end-to-end, …

… photorealistic text-to-video generation. We train a cascade of three models consisting of a
base latent video diffusion model, and two video super-resolution … two super resolution stages. …

… that optical flow acts in video super-resolution, in this work… super-resolution (ie, why we
require super-resolution); the concept of video super-resolution (ie, what is video super-resolution…

… To handle these requirements and improve the recent models, we propose a photo-realistic …
To overcome such an issue, we adopt adversarial training to build photo-realistic CARN (…

… [10] were the firsts to use a GAN network and feature losses for learning to superresolve
images, which produced images with a previously unseen photorealistic quality. …

… We show that temporal adversarial learning is the key to achieving photorealistic and temporally
… Quantifying the temporal coherence for video super-resolution tasks has also not been …