Filters








772 Hits in 6.4 sec

Super Resolution for Noisy Images Using Convolutional Neural Networks

Zaid Bin Mushtaq, Shoaib Mohd Nasti, Chaman Verma, Maria Simona Raboca, Neerendra Kumar, Samiah Jan Nasti
2022 Mathematics  
Furthermore, residual neural network training with improved preprocessing creates an efficient and versatile single-image super-resolution network.  ...  In this paper, a single-image super-resolution network model based on convolutional neural networks is proposed by combining conventional autoencoder and residual neural network approaches.  ...  The foundation for the convolutional neural network for single-image super-resolution is a paper titled "Learning a Deep Convolutional Network for Image Super-Resolution" (SRCNN) [16] , by C.  ... 
doi:10.3390/math10050777 fatcat:w24o4fbrhfgw7a7wqryd4gjuda

Single-frame super-resolution for remote sensing images based on improved deep recursive residual network

Jiali Tang, Jie Zhang, Dan Chen, Najla Al-Nabhan, Chenrong Huang
2021 EURASIP Journal on Image and Video Processing  
AbstractSingle-frame image super-resolution (SISR) technology in remote sensing is improving fast from a performance point of view.  ...  In this paper, an Improved Deep Recursive Residual Network (IDRRN) super-resolution model is proposed to decrease the difficulty of network training.  ...  Super-resolution convolutional neural network (SRCNN ) [22] has begun the era of deep convolutional neural networks dealing with super-resolution problems.  ... 
doi:10.1186/s13640-021-00560-8 fatcat:cqarqwxdsnb5tpaj5w4gfzauzy

Accurate Image Super-Resolution Using Very Deep Convolutional Networks [article]

Jiwon Kim, Jung Kwon Lee, Kyoung Mu Lee
2016 arXiv   pre-print
We present a highly accurate single-image super-resolution (SR) method. Our method uses a very deep convolutional network inspired by VGG-net used for ImageNet classification simonyan2015very.  ...  With very deep networks, however, convergence speed becomes a critical issue during training. We propose a simple yet effective training procedure.  ...  We find a single convolutional network is sufficient for multi-scalefactor super-resolution.  ... 
arXiv:1511.04587v2 fatcat:fxgxwjb2wrfitbtxvw55blkdkq

IMPACT OF DEEP LEARNING-BASED SUPER-RESOLUTION ON BUILDING FOOTPRINT EXTRACTION

H. He, K. Gao, W. Tan, L. Wang, S. N. Fatholahi, N. Chen, M. A. Chapman, J. Li
2022 The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
a pre-trained Residual Feature Aggregation Network (RFANet).  ...  Specifically, we first super-resolve the Massachusetts Building Dataset using bicubic interpolation, a pre-trained Super-Resolution CNN (SRCNN), a pre-trained Residual Channel Attention Network (RCAN),  ...  To further improve the performance of single-image super-resolution, different methods were proposed with more complex architectures and more parameters (He et al., 2021) .  ... 
doi:10.5194/isprs-archives-xliii-b1-2022-31-2022 fatcat:rjn7yubl4vbglng5ntwfy2dkve

Accurate Image Super-Resolution Using Very Deep Convolutional Networks

Jiwon Kim, Jung Kwon Lee, Kyoung Mu Lee
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
We present a highly accurate single-image superresolution (SR) method. Our method uses a very deep convolutional network inspired by VGG-net used for ImageNet classification [19] .  ...  With very deep networks, however, convergence speed becomes a critical issue during training. We propose a simple yet effective training procedure.  ...  We find a single convolutional network is sufficient for multi-scalefactor super-resolution.  ... 
doi:10.1109/cvpr.2016.182 dblp:conf/cvpr/KimLL16a fatcat:pefvx5x75bazvbgnl7l32wwuwy

Learning Spectral and Spatial Features Based on Generative Adversarial Network for Hyperspectral Image Super-Resolution

Ruituo Jiang, Xu Li, Ang Gao, Lixin Li, Hongying Meng, Shigang Yue, Lei Zhang
2019 IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium  
A generative adversarial network for HSIs super-resolution (HSRGAN) is proposed in this paper.  ...  Super-resolution (SR) of hyperspectral images (HSIs) aims to enhance the spatial/spectral resolution of hyperspectral imagery and the super-resolved results will benefit many remote sensing applications  ...  A generative adversarial network for super-resolution (SRGAN) [4] is proposed to reconstruct a more realistic image with finer texture details.  ... 
doi:10.1109/igarss.2019.8900228 dblp:conf/igarss/JiangLGLMYZ19 fatcat:tzsb6osp25bktnvn5mawswjsza

AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results [article]

Kai Zhang, Martin Danelljan, Yawei Li, Radu Timofte, Jie Liu, Jie Tang, Gangshan Wu, Yu Zhu, Xiangyu He, Wenjie Xu, Chenghua Li, Cong Leng (+73 others)
2020 arXiv   pre-print
This paper reviews the AIM 2020 challenge on efficient single image super-resolution with focus on the proposed solutions and results.  ...  The challenge task was to super-resolve an input image with a magnification factor x4 based on a set of prior examples of low and corresponding high resolution images.  ...  A Teams and affiliations  ... 
arXiv:2009.06943v1 fatcat:2s7k5wsgsjgo5flnqaby26cn64

PNEN: Pyramid Non-Local Enhanced Networks [article]

Feida Zhu, Chaowei Fang, Kai-Kuang Ma
2020 arXiv   pre-print
We integrate it into two existing methods for image denoising and single image super-resolution, achieving consistently improved performance.  ...  Existing neural networks proposed for low-level image processing tasks are usually implemented by stacking convolution layers with limited kernel size.  ...  A CNN based pipeline is proposed for joint image filtering (e.g., RGB and depth images) in [1] . Deep neural networks have been extensively applied in image super-resolution and image denoising.  ... 
arXiv:2008.09742v1 fatcat:nf3vtbjxxbcgtjgato2qrjaffi

Super-Resolution for Overhead Imagery Using DenseNets and Adversarial Learning [article]

Marc Bosch and Christopher M. Gifford and Pedro A. Rodriguez
2017 arXiv   pre-print
We propose a GAN-based architecture using densely connected convolutional neural networks (DenseNets) to be able to super-resolve overhead imagery with a factor of up to 8x.  ...  Recent advances in Generative Adversarial Learning allow for new modalities of image super-resolution by learning low to high resolution mappings.  ...  In [17] , authors proposed a GAN-based algorithm using neural networks with deep convolution layers to model the low-tohigh resolution mappings.  ... 
arXiv:1711.10312v1 fatcat:6pl6vuwkvvgnxafjiqxp7ia5s4

Real-Time Environment Monitoring Using a Lightweight Image Super-Resolution Network

Qiang Yu, Feiqiang Liu, Long Xiao, Zitao Liu, Xiaomin Yang
2021 International Journal of Environmental Research and Public Health  
Deep-learning (DL)-based methods are of growing importance in the field of single image super-resolution (SISR).  ...  With the help of these extra feature maps, the network can extract more useful information from low resolution (LR) images to reconstruct the desired high resolution (HR) images.  ...  Almost at the same time, Shi et al. proposed real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network (ESPCN) [19] for building a direct mapping from  ... 
doi:10.3390/ijerph18115890 pmid:34072625 fatcat:uppdcdsv25h23lwq5buktnyrru

Multi-modal Spectral Image Super-Resolution [chapter]

Fayez Lahoud, Ruofan Zhou, Sabine Süsstrunk
2019 Lecture Notes in Computer Science  
Recent advances have shown the great power of deep convolutional neural networks (CNN) to learn the relationship between low and high-resolution image patches.  ...  Furthermore, color images are usually taken at a higher resolution than spectral images, so we make use of color images as another modality to improve the super-resolution network.  ...  Related Work Single-image super-resolution corresponds is about upscaling a single low-resolution image to a higher spatial resolution.  ... 
doi:10.1007/978-3-030-11021-5_3 fatcat:mah5rje3jne57advb7elzf3z7m

Learning Filter Basis for Convolutional Neural Network Compression [article]

Yawei Li, Shuhang Gu, Luc Van Gool, Radu Timofte
2019 arXiv   pre-print
Convolutional neural networks (CNNs) based solutions have achieved state-of-the-art performances for many computer vision tasks, including classification and super-resolution of images.  ...  Usually the success of these methods comes with a cost of millions of parameters due to stacking deep convolutional layers.  ...  SR-ResNet is a middle-level network with 1.5M parameters while EDSR is quite a huge network with 43M parameters but much higher PSNR accuracy.  ... 
arXiv:1908.08932v2 fatcat:jtm3j6licfflbf5wmewbh4qbva

Fusing multi-scale information in convolution network for MR image super-resolution reconstruction

Chang Liu, Xi Wu, Xi Yu, YuanYan Tang, Jian Zhang, JiLiu Zhou
2018 BioMedical Engineering OnLine  
Recently, learningbased super-resolution methods, such as sparse coding and super-resolution convolution neural network, have achieved promising reconstruction results in scene images.  ...  Methods: To investigate the different edge responses using different convolution kernel sizes, this study employs a multi-scale fusion convolution network (MFCN) to perform super-resolution for MRI images  ...  Acknowledgements The authors would like to thank all participants for the valuable discussions regarding the content of this article.  ... 
doi:10.1186/s12938-018-0546-9 pmid:30144798 pmcid:PMC6109361 fatcat:byzevyibdjcptolxpx6j6jzasm

Lightweight Image Super-Resolution with Information Multi-distillation Network

Zheng Hui, Xinbo Gao, Yunchu Yang, Xiumei Wang
2019 Proceedings of the 27th ACM International Conference on Multimedia - MM '19  
In recent years, single image super-resolution (SISR) methods using deep convolution neural network (CNN) have achieved impressive results.  ...  To process real images with any sizes, we develop an adaptive cropping strategy (ACS) to super-resolve block-wise image patches using the same well-trained model.  ...  Single image super-resolution With the rapid development of deep learning, numerous methods based on convolutional neural network (CNN) have been the mainstream in SISR.  ... 
doi:10.1145/3343031.3351084 dblp:conf/mm/HuiGYW19 fatcat:uw3jwnrrjbccrbsfmd3uld72bi

Semi-Dense Depth Interpolation using Deep Convolutional Neural Networks

Ilya Makarov, Vladimir Aliev, Olga Gerasimova
2017 Proceedings of the 2017 ACM on Multimedia Conference - MM '17  
We present an end-to-end learnable residual convolutional neural network architecture that achieves fast interpolation of semi-dense depth maps with different sparse depth distributions: uniform, sparse  ...  We also propose a loss function combining classical mean squared error with perceptual loss widely used in intensity image super-resolution and style transfer tasks.  ...  ACKNOWLEDGMENTS The work was supported by the Russian Science Foundation under grant 17-11-01294 and performed at National Research University Higher School of Economics, Russia.  ... 
doi:10.1145/3123266.3123360 dblp:conf/mm/MakarovAG17 fatcat:iyzs6n5t4vb5rkjgtt2ivczm6y
« Previous Showing results 1 — 15 out of 772 results