CoT-MISR:Marrying Convolution and Transformer for Multi-Image Super-Resolution
Not on the map. Why?
Abstract (arXiv)
As a method of image restoration, image super-resolution has been extensively studied at first. How to transform a low-resolution image to restore its high-resolution image information is a problem that researchers have been exploring. In the early physical transformation methods, the high-resolution pictures generated by these methods always have a serious problem of missing information, and the edges and details can not be well recovered. With the development of hardware technology and mathematics, people begin to use in-depth learning methods for image super-resolution tasks, from direct in-depth learning models, residual channel attention networks, bi-directional suppression networks, to tr networks with transformer network modules, which have gradually achieved good results. In the research of multi-graph super-resolution, thanks to the establishment of multi-graph super-resolution dataset, we have experienced the evolution from convolution model to transformer model, and the quality of super-resolution has been continuously improved. However, we find that neither pure convolution nor pure tr network can make good use of low-resolution image information. Based on this, we propose a new end-to-end CoT-MISR network. CoT-MISR network makes up for local and global information by using the advantages of convolution and tr. The validation of dataset under equal parameters shows that our CoT-MISR network has reached the optimal score index.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 59 references that are in the map. First posted on arXiv 12 Mar 2023.
Builds on
25 of 59 references.
References · 25
- 2017Attention Is All You Needcited by 60,361
- 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
- 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,264
- 2017Deep Mutual Learningcited by 628
- 2016Accelerating the Super-Resolution Convolutional Neural Networkcited by 394
- 2020Learning Texture Transformer Network for Image Super-Resolutioncited by 347
- 2017DualGAN: Unsupervised Dual Learning for Image-to-Image Translationcited by 310
- 2018Deep Back-Projection Networks For Super-Resolutioncited by 225
- 2016Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensationcited by 156
- 2019Feedback Network for Image Super-Resolutioncited by 155
- 2016Dual Learning for Machine Translationcited by 148
- 2018Unsupervised Image Super-Resolution using Cycle-in-Cycle Generative Adversarial Networkscited by 133
13 more
- 2020Closed-loop Matters: Dual Regression Networks for Single Image Super-Resolutioncited by 90
- 2020Improving Multispectral Pedestrian Detection by Addressing Modality Imbalance Problemscited by 83
- 2018Wide Activation for Efficient and Accurate Image Super-Resolutioncited by 65
- 2020HighRes-net: Recursive Fusion for Multi-Frame Super-Resolution of Satellite Imagerycited by 42
- 2017Dual Supervised Learningcited by 33
- 2019DeepSUM: Deep neural network for Super-resolution of Unregistered Multitemporal imagescited by 30
- 2020Multi-image Super Resolution of Remotely Sensed Images using Residual Feature Attention Deep Neural Networkscited by 22
- 2021Permutation invariance and uncertainty in multitemporal image super-resolutioncited by 18
- 2019Super-Resolution of PROBA-V Images Using Convolutional Neural Networkscited by 17
- 2019Deep Learning for Multiple-Image Super-Resolutioncited by 15
- 20183DSRnet: Video Super-resolution using 3D Convolutional Neural Networkscited by 12
- 2018Unsupervised Degradation Learning for Single Image Super-Resolutioncited by 9
- 2019Image quality assessment for determining efficacy and limitations of Super-Resolution Convolutional Neural Network (SRCNN)cited by 7
Built on by
Not cited yet.