Filters








9,574 Hits in 4.9 sec

Learning Texture Transformer Network for Image Super-Resolution [article]

Fuzhi Yang, Huan Yang, Jianlong Fu, Hongtao Lu, Baining Guo
2020 arXiv   pre-print
In this paper, we propose a novel Texture Transformer Network for Image Super-Resolution (TTSR), in which the LR and Ref images are formulated as queries and keys in a transformer, respectively.  ...  We study on image super-resolution (SR), which aims to recover realistic textures from a low-resolution (LR) image.  ...  To address these problems, we propose a novel Texture Transformer Network for Image Super-Resolution (TTSR).  ... 
arXiv:2006.04139v2 fatcat:jkaohnhydjegdfja7fpkhp5eoq

Super-Resolution reconstruction method of remote sensing image based on multi-feature fusion

Zhi-Xing Huang, Chang-Wei Jing
2020 IEEE Access  
Among many methods, the super-resolution reconstruction method based on generative adversarial networks has obvious advantages over previous network models in reconstructing image texture details.  ...  Aiming at the problem of whether the texture details of the reconstructed image are accurate and clear, we propose a super-resolution reconstruction method combining wavelet transform and generative adversarial  ...  This method takes advantage of the advantages of wavelet transform and generative adversarial networks in the super-resolution field, so that the reconstructed image has better texture information and  ... 
doi:10.1109/access.2020.2967804 fatcat:hktuogb2rzes5gwtfkloi6iq7y

Fine Perceptive GANs for Brain MR Image Super-Resolution in Wavelet Domain [article]

Senrong You and Yong Liu and Baiying Lei and Shuqiang Wang
2020 arXiv   pre-print
Then each sub-band generative adversarial network (sub-band GAN) conquers the super-resolution procedure of each single sub-band image.  ...  In addition, inverse discrete wavelet transformation (IDWT) is integrated into model for taking the reconstruction of whole image into account.  ...  For example, Cherukuri [8] enhanced deep MR image super-resolution by a deep network that exploits a low-rank structure and a sharpness prior of MR images.  ... 
arXiv:2011.04145v1 fatcat:cn4vax73o5b3pdk6n2cne23ney

Super-resolution of geosynchronous synthetic aperture radar images using dialectical GANs

Yuanhao Li, Dongyang Ao, Corneliu Octavian Dumitru, Cheng Hu, Mihai Datcu
2019 Science China Information Sciences  
Acknowledgements We thank the Alaska Satellite Facility for the ALOS PALSAR images.  ...  Although deep learning has produced remarkable super-resolution results for optical images, little attention has been paid to super-resolution for SAR images [7] .  ...  Di-GANs generate super-resolution images (SRIs) by intelligently learning the texture of input style images while simultaneously preserving the information conveyed by the input content images rather than  ... 
doi:10.1007/s11432-018-9668-6 fatcat:uol4v2zr2vbrnfq4vk7wgfg6oy

Crop Leaf Disease Image Super-Resolution and Identification with Dual Attention and Topology Fusion Generative Adversarial Network

Qiang Dai, Xi Cheng, Yan Qiao, Youhua Zhang
2020 IEEE Access  
This network can effectively transform unclear images into clear and high-resolution images.  ...  INDEX TERMS Crop leaf disease, attention, generative adversarial networks, super-resolution, identification. 55724 This work is licensed under a Creative Commons Attribution 4.0 License.  ...  for image super-resolution tasks.  ... 
doi:10.1109/access.2020.2982055 fatcat:byx6nmhyb5hx3jj6vqwj4kvjtm

Learning wavelet coefficients for face super-resolution

Liu Ying, Sun Dinghua, Wang Fuping, Lim Keng Pang, Chiew Tuan Kiang, Lai Yi
2020 The Visual Computer  
To overcome this problem, we propose a novel deep neural network to predict the super-resolution wavelet coefficients in order to obtain clearer facial images.  ...  Finally, image edge features from canny detector are applied to enhance super-resolution images during training.  ...  Introduction Face Super-Resolution (SR) is an important subset of image super-resolution technology for public security.  ... 
doi:10.1007/s00371-020-01925-2 fatcat:lqnjva6ttrgk7cxinwcbo5gupi

Learned Multi-View Texture Super-Resolution [article]

Audrey Richard, Ian Cherabier, Martin R. Oswald, Vagia Tsiminaki, Marc Pollefeys, Konrad Schindler
2020 arXiv   pre-print
We map that inverse problem into a block of suitably designed neural network layers, and combine it with a standard encoder-decoder network for learned single-image super-resolution.  ...  We present a super-resolution method capable of creating a high-resolution texture map for a virtual 3D object from a set of lower-resolution images of that object.  ...  Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright annotation thereon.  ... 
arXiv:2001.04775v1 fatcat:eo2xo6frrvcwfkute62h73yx5u

A Frequency Domain Constraint for Synthetic and Real X-ray Image Super Resolution [article]

Qing Ma, Jae Chul Koh, WonSook Lee
2021 arXiv   pre-print
Our goal is to generate high-resolution synthetic X-ray images in real-time by upsampling low-resolution images with deep learning-based super-resolution methods.  ...  To the best of our knowledge, this is the first paper utilizing the frequency domain for the loss functions in the field of super-resolution.  ...  Yang, F., Yang, H., Fu, J., Lu, H., Guo, B.: Learning Texture Transformer Network for Image Super-Resolution. arXiv:2006.04139 [cs]. (2020). 14.  ... 
arXiv:2105.06887v2 fatcat:54lwabxhynhpbhhxpivoxk2npq

Recent trends in image processing and pattern recognition

K. C. Santosh, Sameer K. Antani
2020 Multimedia tools and applications  
In "Super Resolution of Single Depth Image based on Multi-dictionary Learning with Edge Feature Regularization," authors focused on super resolution based on multi-dictionary learning with edge regularization  ...  In "Super-Resolution Quality Criterion (SRQC): A Super-Resolution Image Quality Assessment Metric," authors reported the importance of SRQC in assessing image quality.  ... 
doi:10.1007/s11042-020-10093-3 fatcat:z2wzbhk4qbd3vpsyuzm4pdlque

Perceptual Extreme Super Resolution Network with Receptive Field Block [article]

Taizhang Shang, Qiuju Dai, Shengchen Zhu, Tong Yang, Yandong Guo
2020 arXiv   pre-print
Perceptual Extreme Super-Resolution for single image is extremely difficult, because the texture details of different images vary greatly.  ...  To tackle this difficulty, we develop a super resolution network with receptive field block based on Enhanced SRGAN. We call our network RFB-ESRGAN. The key contributions are listed as follows.  ...  For image super-resolution, VDSR [17] reveals that increasing network depth shows a significant improvement in SISR.  ... 
arXiv:2005.12597v1 fatcat:4tjretl65nc2hm5uzx5tua652u

Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform [article]

Xintao Wang, Ke Yu, Chao Dong, Chen Change Loy
2018 arXiv   pre-print
Despite that convolutional neural networks (CNN) have recently demonstrated high-quality reconstruction for single-image super-resolution (SR), recovering natural and realistic texture remains a challenging  ...  This is made possible through a novel Spatial Feature Transform (SFT) layer that generates affine transformation parameters for spatial-wise feature modulation.  ...  [42] propose context-constrained super-resolution by learning from texturally similar training segments. Timofte et al.  ... 
arXiv:1804.02815v1 fatcat:xbj24rdj2rcprmg63vf5fqlh5y

A Review of Deep Learning Based Image Super-resolution Techniques [article]

Fangyuan Zhu
2022 arXiv   pre-print
in the field of image super-resolution, and reports the latest progress of image super-resolution technology based on depth learning method.  ...  With the development of deep learning, image super-resolution technology based on deep learning method is emerging.  ...  [7] First applied the deep learning method to the field of image super-resolution, proposed a three-layer convolution neural network model for image super-resolution reconstruction, described it as  ... 
arXiv:2201.10521v1 fatcat:ul5sxm3ssfagbc6nzpfvgzhowi

TWIST-GAN: Towards Wavelet Transform and Transferred GAN for Spatio-Temporal Single Image Super Resolution [article]

Fayaz Ali Dharejo, Farah Deeba, Yuanchun Zhou, Bhagwan Das, Munsif Ali Jatoi, Muhammad Zawish, Yi Du, Xuezhi Wang
2021 arXiv   pre-print
Recently, deep learning and generative adversarial networks(GANs) have made breakthroughs for the challenging task of single image super-resolution (SISR).  ...  Single Image Super-resolution (SISR) produces high-resolution images with fine spatial resolutions from aremotely sensed image with low spatial resolution.  ...  EXPERIMENT Train the network via Transfer learning The super-resolution of deep-learning spatio-temporal remote sensing images has more problems than the natural one.  ... 
arXiv:2104.10268v1 fatcat:oznne3a7xjhbtej6wgkdf3og7i

Unsupervised Remote Sensing Super-Resolution via Migration Image Prior [article]

Jiaming Wang, Zhenfeng Shao, Tao Lu, Xiao Huang, Ruiqian Zhang, Yu Wang
2021 arXiv   pre-print
First, random noise maps are fed into a designed generative adversarial network (GAN) for reconstruction.  ...  To improve image resolution, numerous approaches based on training low-high resolution pairs have been proposed to address the super-resolution (SR) task.  ...  Super-resolution (SR) aims to reconstruct the high spatial resolution (HSR) image from observed low spatial resolution (LSR) images [1] , which breaks the limitations of the imaging system for the best  ... 
arXiv:2105.03579v2 fatcat:lxbdymxcwvcbbigisumkgm246y

Clustering-Oriented Multiple Convolutional Neural Networks for Single Image Super-Resolution

Peng Ren, Wenjian Sun, Chunbo Luo, Amir Hussain
2017 Cognitive Computation  
for image super-resolution tend to exploit an indiscriminate scheme for processing one whole image.  ...  We then train K convolutional neural networks for super-resolution based on the K clusters of patches separately, such that the multiple convolutional neural networks comprehensively capture the patch  ...  Ethical Standards Funding: This study was funded by National Natural Science Foundation of China (No. 61671481) and Qingdao Applied Fundamental Research (No. 16-5-1-11-jch), the Fundamental Research Funds for  ... 
doi:10.1007/s12559-017-9512-2 fatcat:2rw33efvjrh53lw4dejxochyy4
« Previous Showing results 1 — 15 out of 9,574 results