350 Hits in 2.0 sec

ESRGAN+ : Further Improving Enhanced Super-Resolution Generative Adversarial Network [article]

Nathanaël Carraz Rakotonirina, Andry Rasoanaivo
2020 arXiv   pre-print
Enhanced Super-Resolution Generative Adversarial Network (ESRGAN) is a perceptual-driven approach for single image super resolution that is able to produce photorealistic images.  ...  We have designed a novel block to replace the one used by the original ESRGAN. Moreover, we introduce noise inputs to the generator network in order to exploit stochastic variation.  ...  Enhanced Super-Resolution Generative Adversarial Network (ESRGAN) [5] improves SRGAN by introducing an architecture composed of Residual-in-Residual Dense Blocks (RRDB) without Batch Normalization (BN  ... 
arXiv:2001.08073v1 fatcat:d6klhqrmefbhteei3dgrqib3dm

ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks [article]

Xintao Wang, Ke Yu, Shixiang Wu, Jinjin Gu, Yihao Liu, Chao Dong, Chen Change Loy, Yu Qiao, Xiaoou Tang
2018 arXiv   pre-print
The Super-Resolution Generative Adversarial Network (SRGAN) is a seminal work that is capable of generating realistic textures during single image super-resolution.  ...  To further enhance the visual quality, we thoroughly study three key components of SRGAN - network architecture, adversarial loss and perceptual loss, and improve each of them to derive an Enhanced SRGAN  ...  This work is supported by SenseTime Group Limited, the General Research Fund sponsored by the Research Grants Council of the Hong Kong SAR (CUHK 14241716, 14224316. 14209217), National Natural Science  ... 
arXiv:1809.00219v2 fatcat:eejjfjahnrbv5kk74uuongykpq

Image Super Resolution using Enhanced Super Resolution Generative Adversarial Network

Raj Sarode, Samiksha Varpe, Omkar Kolte, Leena Ragha, M.D. Patil, V.A. Vyawahare
2022 ITM Web of Conferences  
Introducing ESRGAN, an Advanced Optical Genetically Modified (GAN) network of high-resolution image (SR).  ...  Aside from enhancing the accuracy and speed of single picture modification utilizing fast and in-depth convolutional emotional networks, one significant challenge remains mostly commonly unaddressed, namely  ...  Here we are going to employ the Generative Adversarial Networks (GANs) technique. Particularly ESRGAN (Enhanced Super-Resolution Generative Adversarial Networks).  ... 
doi:10.1051/itmconf/20224403054 fatcat:fna2firmi5cbbd2fiov6o4ioja

High-fidelity reconstruction of turbulent flow from spatially limited data using enhanced super-resolution generative adversarial network [article]

Mustafa Z. Yousif, Linqi Yu, HeeChang Lim
2021 arXiv   pre-print
A multi-scale enhanced super-resolution generative adversarial network with a physics-based loss function is introduced as a model to reconstruct the high-resolution flow fields.  ...  This demonstrates that using high-fidelity training data with physics-guided generative adversarial network-based models can be practically efficient in reconstructing high-resolution turbulent flow fields  ...  In terms of experimental studies, Deng et al. 20 applied a super-resolution GAN (SRGAN) 21 and enhanced SRGAN (ESRGAN) 22 to reconstruct high-resolution flow fields using PIV measurements of flow  ... 
arXiv:2109.04250v2 fatcat:v6ombdpu65cq7gbezrzjd2dg6e

COVID-19 Identification from Low-Quality Computed Tomography Using a Modified Enhanced Super-Resolution Generative Adversarial Network Plus and Siamese Capsule Network

Grace Ugochi Nneji, Jianhua Deng, Happy Nkanta Monday, Md Altab Hossin, Sandra Obiora, Saifun Nahar, Jingye Cai
2022 Healthcare  
We have reported about a technique named the modified enhanced super resolution generative adversarial network for a better high resolution of computed tomography images.  ...  Furthermore, in contrast to the fashion of increasing network depth and complexity to beef up imaging performance, we incorporated a Siamese capsule network that extracts distinct features for COVID-19  ...  The modified enhanced super-resolution generative adversarial network used in this study generates super-resolution CT images (SR) from low-resolution CT images of which distinct information can be extracted  ... 
doi:10.3390/healthcare10020403 pmid:35207017 pmcid:PMC8871692 fatcat:7jq4ovgycjcatjizlob3emajfy

A-ESRGAN: Training Real-World Blind Super-Resolution with Attention U-Net Discriminators [article]

Zihao Wei, Yidong Huang, Yuang Chen, Chenhao Zheng, Jinnan Gao
2021 arXiv   pre-print
However, the limitation brought by current generative adversarial network structures is still significant: treating pixels equally leads to the ignorance of the image's structural features, and results  ...  Blind image super-resolution(SR) is a long-standing task in CV that aims to restore low-resolution images suffering from unknown and complex distortions.  ...  Therefore, scholars proposed to use generative adversarial networks(GANs) to solve image super-resolution challenges.  ... 
arXiv:2112.10046v1 fatcat:py5qunh5pbcblhbwsfkgirktp4

Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data [article]

Xintao Wang, Liangbin Xie, Chao Dong, Ying Shan
2021 arXiv   pre-print
Though many attempts have been made in blind super-resolution to restore low-resolution images with unknown and complex degradations, they are still far from addressing general real-world degraded images  ...  In this work, we extend the powerful ESRGAN to a practical restoration application (namely, Real-ESRGAN), which is trained with pure synthetic data.  ...  Networks and Training ESRGAN generator. We adopt the same generator (SR network) as ESRGAN [50] , i.e., a deep network with several residual-in-residual dense blocks (RRDB), as shown in Fig. 4 .  ... 
arXiv:2107.10833v2 fatcat:ugjldtqi2baxrj77xirkfhjdde

Target Detection Method for Low-Resolution Remote Sensing Image Based on ESRGAN and ReDet

Yuwu Wang, Guobing Sun, Shengwei Guo
2021 Photonics  
The TDoSR method uses the Enhanced Super-Resolution Generative Adversarial Network (ESRGAN) to perform defogging and super-resolution reconstruction of foggy low-resolution remote sensing images.  ...  In this paper, we propose a Target Detection on Super-Resolution Reconstruction (TDoSR) method to solve the problem of low target recognition rates in low-resolution remote sensing images under foggy conditions  ...  In response, Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network (SRGAN) [7] applied the Generative Adversarial Network (GAN) [8] to solve the problem of super-resolution  ... 
doi:10.3390/photonics8100431 fatcat:skk7gsryovdljknaj6szyohiqe


Z. Wu, P. Ma
2020 The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
In this study, we propose a novel two-step ESRGAN-based DEM SR method to effectively recover high-resolution DEM from the original version.  ...  Firstly, we pretrain an ESRGAN with a large number of natural images. Based on it, we transfer the learnt knowledge into the DEM problem and fine-tune the DEM SR network.  ...  Flowchart of the proposed method Algorithm 1 ESRGAN-based DEM SR network Input: The low-resolution DEM Output: The high-resolution DEM 1: Pretrain the enhanced super-resolution generative adversarial  ... 
doi:10.5194/isprs-archives-xliii-b3-2020-351-2020 fatcat:dvqekieruvbk3mengx4aianr3i

Model Specialization for the Use of ESRGAN on Satellite and Airborne Imagery

Étienne Clabaut, Myriam Lemelin, Mickaël Germain, Yacine Bouroubi, Tony St-Pierre
2021 Remote Sensing  
The use of enhanced super-resolution generative adversarial networks (ERSGAN), a specific type of deep learning architecture, allows the spatial resolution of remote sensing images to be increased by "  ...  In this study, we show that ESRGAN create better quality images when trained on thematically classified images than when trained on a wide variety of examples.  ...  GANs provide a powerful framework for generating real-looking images with high quality, as is the case in [13] , through enhanced super-resolution generative adversarial networks (ESRGAN).  ... 
doi:10.3390/rs13204044 fatcat:qcb73hebizhtjclaiu2vvkbnmq

Enhancing Precision with an Ensemble Generative Adversarial Network for Steel Surface Defect Detectors (EnsGAN-SDD)

Fityanul Akhyar, Elvin Nur Furqon, Chih-Yang Lin
2022 Sensors  
Initially, the ensemble of enhanced super-resolution generative adversarial networks (ESRGAN) was proposed for the preprocessing stage to generate a more detailed contour of the original steel image.  ...  To solve these problems, we propose incorporating super-resolution technique, sequential feature pyramid network, and boundary localization.  ...  To the best of our knowledge, enhanced super resolution generative adversarial networks (ESRGAN) is a state-of-the-art model for super resolution [9] , which is a recent innovation in machine learning  ... 
doi:10.3390/s22114257 pmid:35684877 fatcat:tnq26abo6rc5xpcjovet25g7ya

3D MRI Reconstruction Based on 2D Generative Adversarial Network Super-Resolution

Hongtao Zhang, Yuki Shinomiya, Shinichi Yoshida
2021 Sensors  
We utilize a receiving field block enhanced super-resolution generative adversarial network (RFB-ESRGAN), which is superior to other super-resolution technologies in terms of texture and frequency information  ...  The traditional super-resolution reconstruction method based on MRI generally states an optimization problem in terms of prior information.  ...  Obtain high-resolution MRI slices through receiving field block enhanced super-resolution generative adversarial network (RFB-ESRGAN).  ... 
doi:10.3390/s21092978 pmid:33922811 fatcat:q437frw4f5c2vnd75ituvr2wry

WiSoSuper: Benchmarking Super-Resolution Methods on Wind and Solar Data [article]

Rupa Kurinchi-Vendhan, Björn Lütjens, Ritwik Gupta, Lucien Werner, Dava Newman
2021 arXiv   pre-print
We provide a thorough and extensible benchmark of leading deep learning-based super-resolution techniques, including the enhanced super-resolution generative adversarial network (ESRGAN) and an enhanced  ...  Recently, machine learning-based models, specifically the physics-informed resolution-enhancing generative adversarial network (PhIREGAN), have outperformed traditional downscaling methods.  ...  neural network (CNN)-and generative adversarial network (GAN)-based super-resolution techniques to a task from the physical sciences; • and a novel publicly available machine learning-ready dataset for  ... 
arXiv:2109.08770v2 fatcat:en4fokb57zervivhuzz5yn7d2u

Super-resolution of sea surface temperature with convolutional neural network- and generative adversarial network-based methods

Tomoki Izumi, Motoki Amagasaki, Kei Ishida, Masato Kiyama
2022 Journal of Water and Climate Change  
In this paper, we perform the super-resolution of sea surface temperature data with the enhanced super-resolution generative adversarial network (ESRGAN), which is a deep neural network-based single-image  ...  super-resolution (SISR) method that uses a generative adversarial network (GAN).  ...  The enhanced super-resolution GAN (ESRGAN) (Xintao et al. 2018 ) is an improved version of the SRGAN, which was the first GAN for SISR.  ... 
doi:10.2166/wcc.2022.291 fatcat:hvcvj4mw5jft3mlfqwcnbouzqi

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

Taizhang Shang, Qiuju Dai, Shengchen Zhu, Tong Yang, Yandong Guo
2020 arXiv   pre-print
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.  ...  First, for the purpose of extracting multi-scale information and enhance the feature discriminability, we applied receptive field block (RFB) to super resolution.  ...  Enhanced superresolution generative adversarial networks (ESRGAN) [29] was proposed to further improve the performance of deep learning based SISR model.  ... 
arXiv:2005.12597v1 fatcat:4tjretl65nc2hm5uzx5tua652u
« Previous Showing results 1 — 15 out of 350 results