FSR: A general frequency-oriented framework to accelerate image super-resolution networks
Deep neural networks (DNNs) have witnessed remarkable achievement in image super-
resolution (SR), and plenty of DNN-based SR models with elaborated network designs have …
resolution (SR), and plenty of DNN-based SR models with elaborated network designs have …
Classsr: A general framework to accelerate super-resolution networks by data characteristic
We aim at accelerating super-resolution (SR) networks on large images (2K-8K). The large
images are usually decomposed into small sub-images in practical usages. Based on this …
images are usually decomposed into small sub-images in practical usages. Based on this …
Lightweight multi-scale residual networks with attention for image super-resolution
H Liu, F Cao, C Wen, Q Zhang - Knowledge-Based Systems, 2020 - Elsevier
In recent years, constructing various deep convolutional neural networks (CNNs) for single-
image super-resolution (SISR) tasks has made significant progress. Despite their high …
image super-resolution (SISR) tasks has made significant progress. Despite their high …
CFGN: A lightweight context feature guided network for image super-resolution
Convolutional neural networks (CNNs) have recently been widely and successfully applied
in the image computer vision community, and obtained great advances in single image …
in the image computer vision community, and obtained great advances in single image …
Restore globally, refine locally: A mask-guided scheme to accelerate super-resolution networks
Single image super-resolution (SR) has been boosted by deep convolutional neural
networks with growing model complexity and computational costs. To deploy existing SR …
networks with growing model complexity and computational costs. To deploy existing SR …
Gated multiple feedback network for image super-resolution
The rapid development of deep learning (DL) has driven single image super-resolution (SR)
into a new era. However, in most existing DL based image SR networks, the information …
into a new era. However, in most existing DL based image SR networks, the information …
MDCN: Multi-scale dense cross network for image super-resolution
Convolutional neural networks have been proven to be of great benefit for single-image
super-resolution (SISR). However, previous works do not make full use of multi-scale …
super-resolution (SISR). However, previous works do not make full use of multi-scale …
A hybrid network of cnn and transformer for lightweight image super-resolution
J Fang, H Lin, X Chen, K Zeng - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
Recently, a number of CNN based methods have made great progress in single image
super-resolution. However, these existing architectures commonly build massive number of …
super-resolution. However, these existing architectures commonly build massive number of …
FilterNet: Adaptive information filtering network for accurate and fast image super-resolution
Deep convolutional neural network (CNN) approaches have achieved impressive
performance for image super-resolution (SR). The main issue of image SR is to effectively …
performance for image super-resolution (SR). The main issue of image SR is to effectively …
Reparameterized residual feature network for lightweight image super-resolution
W Deng, H Yuan, L Deng, Z Lu - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
In order to solve the problem of deploying super-resolution technology on resource-limited
devices, this paper explores the differences in performance and efficiency between …
devices, this paper explores the differences in performance and efficiency between …