Single image super-resolution reconstruction based on multi-scale feature mapping adversarial network

2020 ◽  
Vol 166 ◽  
pp. 107251
Author(s):  
Dengwen Zhou ◽  
Ran Duan ◽  
Lijuan Zhao ◽  
Xiaoliang Chai
Keyword(s):  
Super Resolution ◽  
Single Image ◽  
Feature Mapping ◽  
Scale Feature ◽  
Multi Scale ◽  
Adversarial Network ◽  
Image Super Resolution ◽  
Single Image Super Resolution

Compressed multi-scale feature fusion network for single image super-resolution

2018 ◽  
Vol 146 ◽  
pp. 50-60 ◽  
Author(s):  
Xinxia Fan ◽  
Yanhua Yang ◽  
Cheng Deng ◽  
Jie Xu ◽  
Xinbo Gao
Keyword(s):  
Feature Fusion ◽  
Super Resolution ◽  
Single Image ◽  
Scale Feature ◽  
Multi Scale ◽  
Image Super Resolution ◽  
Single Image Super Resolution

scholarly journals Single image super resolution based on multi-scale structure and non-local smoothing

2021 ◽  
Vol 2021 (1) ◽  
Author(s):  
Wenyi Wang ◽  
Jun Hu ◽  
Xiaohong Liu ◽  
Jiying Zhao ◽  
Jianwen Chen
Keyword(s):  
Super Resolution ◽  
Principal Component ◽  
Feature Mapping ◽  
Multi Scale ◽  
Non Local ◽  
Image Super Resolution ◽  
Gaussian Blur ◽  
Single Image Super Resolution ◽  
Global And Local ◽  
Bicubic Interpolation

AbstractIn this paper, we propose a hybrid super-resolution method by combining global and local dictionary training in the sparse domain. In order to present and differentiate the feature mapping in different scales, a global dictionary set is trained in multiple structure scales, and a non-linear function is used to choose the appropriate dictionary to initially reconstruct the HR image. In addition, we introduce the Gaussian blur to the LR images to eliminate a widely used but inappropriate assumption that the low resolution (LR) images are generated by bicubic interpolation from high-resolution (HR) images. In order to deal with Gaussian blur, a local dictionary is generated and iteratively updated by K-means principal component analysis (K-PCA) and gradient decent (GD) to model the blur effect during the down-sampling. Compared with the state-of-the-art SR algorithms, the experimental results reveal that the proposed method can produce sharper boundaries and suppress undesired artifacts with the present of Gaussian blur. It implies that our method could be more effect in real applications and that the HR-LR mapping relation is more complicated than bicubic interpolation.

scholarly journals TWIST-GAN: Towards Wavelet Transform and Transferred GAN for Spatio-Temporal Single Image Super Resolution

2021 ◽  
Vol 12 (6) ◽  
pp. 1-20
Author(s):  
Fayaz Ali Dharejo ◽  
Farah Deeba ◽  
Yuanchun Zhou ◽  
Bhagwan Das ◽  
Munsif Ali Jatoi ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Super Resolution ◽  
Generative Adversarial Networks ◽  
Single Image ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Image Super Resolution ◽  
Spatio Temporal ◽  
Single Image Super Resolution

Single Image Super-resolution (SISR) produces high-resolution images with fine spatial resolutions from a remotely sensed image with low spatial resolution. Recently, deep learning and generative adversarial networks (GANs) have made breakthroughs for the challenging task of single image super-resolution (SISR) . However, the generated image still suffers from undesirable artifacts such as the absence of texture-feature representation and high-frequency information. We propose a frequency domain-based spatio-temporal remote sensing single image super-resolution technique to reconstruct the HR image combined with generative adversarial networks (GANs) on various frequency bands (TWIST-GAN). We have introduced a new method incorporating Wavelet Transform (WT) characteristics and transferred generative adversarial network. The LR image has been split into various frequency bands by using the WT, whereas the transfer generative adversarial network predicts high-frequency components via a proposed architecture. Finally, the inverse transfer of wavelets produces a reconstructed image with super-resolution. The model is first trained on an external DIV2 K dataset and validated with the UC Merced Landsat remote sensing dataset and Set14 with each image size of 256 × 256. Following that, transferred GANs are used to process spatio-temporal remote sensing images in order to minimize computation cost differences and improve texture information. The findings are compared qualitatively and qualitatively with the current state-of-art approaches. In addition, we saved about 43% of the GPU memory during training and accelerated the execution of our simplified version by eliminating batch normalization layers.

Sign in / Sign up

Export Citation Format

Share Document