Accelerating the Super-Resolution Convolutional Neural Network

Chao Dong, Chen Change Loy, Xiaoou Tang · European Conference on Computer Vision · 2016

Summary

This paper aims at accelerating the current SRCNN, and proposes a compact hourglass-shape CNN structure for faster and better SR, and presents the parameter settings that can achieve real-time performance on a generic CPU while still maintaining good performance.

Type: preprint
Published: 2016-08-01
Cited by: 3,492
References: 30
Access: Open access
DOI: https://doi.org/10.48550/arxiv.1608.00367
arXiv: https://arxiv.org/abs/1608.00367
OpenAlex: https://openalex.org/W2950016100
Semantic Scholar: https://api.semanticscholar.org/CorpusID:13271756

Keywords

Computer science, Convolutional neural network, Deconvolution, Interpolation (computer graphics), Feature (linguistics)

References

Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet ClassificationKaiming He, Xiangyu Zhang, Shaoqing Ren — 2015
Image Super-Resolution Using Deep Convolutional NetworksChao Dong, Chen Change Loy, Kaiming He — 2014
Learning to generate chairs with convolutional neural networksAlexey Dosovitskiy, Jost Tobias Springenberg, Thomas Brox — 2014
Fully convolutional networks for semantic segmentationJonathan Long, Evan Shelhamer, Trevor Darrell — 2014
Single image super-resolution from transformed self-exemplarsJia‐Bin Huang, Abhishek Singh, Narendra Ahuja — 2015
Fast and accurate image upscaling with super-resolution forestsSamuel Schulter, Christian Leistner, Horst Bischof — 2015
Low-Complexity Single-Image Super-Resolution based on Nonnegative Neighbor EmbeddingMarco Bevilacqua, Aline Roumy, Christine Guillemot — 2012
Fast Direct Super-Resolution by Simple FunctionsChih-Yuan Yang, Ming–Hsuan Yang — 2013
Accelerating Very Deep Convolutional Networks for Classification and DetectionXiangyu Zhang, Jianhua Zou, Kaiming He — 2015
Image Super-Resolution Via Sparse RepresentationJianchao Yang, John Wright, Thomas S. Huang — 2010
A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statisticsDavid Martín, Charless C. Fowlkes, Doron Tal — 2001
Deep Convolutional Neural Network for Image DeconvolutionXu Li, Jimmy Ren, Ce Liu — 2014
An information fidelity criterion for image quality assessment using natural scene statisticsHamid R. Sheikh, Alan C. Bovik, Gustavo de Veciana — 2005
Single-Image Super-Resolution Using Sparse Regression and Natural Image PriorKwang In Kim, Younghee Kwon — 2010
Anchored Neighborhood Regression for Fast Example-Based Super-ResolutionRadu Timofte, Vincent De, Luc Van Gool — 2013
Caffe: Convolutional Architecture for Fast Feature EmbeddingYangqing Jia, Evan Shelhamer, Jeff Donahue — 2014
Exploiting Linear Structure Within Convolutional Networks for Efficient EvaluationEmily Denton, Wojciech Zaremba, Joan Bruna — 2014
Deeply-Recursive Convolutional Network for Image Super-ResolutionJiwon Kim, Jung Kwon Lee, Kyoung Mu Lee — 2015
Accurate Image Super-Resolution Using Very Deep Convolutional NetworksJiwon Kim, Jung Kwon Lee, Kyoung Mu Lee — 2015
Future Data and Security EngineeringNam Thoai, Antunes, Pedro, Makoto Takizawa — 2014

Cited by

Intelligent Data Engineering and Automated Learning – IDEAL 2020: 21st International Conference, Guimaraes, Portugal, November 4–6, 2020, Proceedings, Part IIAnalide, Cesar, Novais, Paulo, Camacho, David — 2020
Bidirectional Recurrent Convolutional Networks for Multi-Frame Super-ResolutionYan Huang, Wei Wang, Liang Wang — 2015
FAST: Free Adaptive Super-Resolution via Transfer for Compressed VideosZhengdong Zhang, Vivienne Sze — 2016
End-to-End Image Super-Resolution via Deep and Shallow Convolutional NetworksYifan Wang, Lijun Wang, Hongyu Wang — 2016
Is the deconvolution layer the same as a convolutional layer?Wenzhe Shi, José Caballero, Lucas Theis — 2016
Not Afraid of the Dark: NIR-VIS Face Recognition via Cross-Spectral Hallucination and Low-Rank EmbeddingJosé Lezama, Qiang Qiu, Guillermo Sapiro — 2016
Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion CompensationJosé Caballero, Christian Ledig, Andrew P. Aitken — 2016
EnhanceNet: Single Image Super-Resolution Through Automated Texture SynthesisMehdi S. M. Sajjadi, Bernhard Schölkopf, Michael Hirsch — 2016
Image De-Raining Using a Conditional Generative Adversarial NetworkHe Zhang, Vishwanath A. Sindagi, Vishal M. Patel — 2017
Convolutional Neural Network-Based Block Up-Sampling for Intra Frame CodingYue Li, Dong Liu, Houqiang Li — 2017
Super resolution reconstruction of medical image based on adaptive quad-tree decompositionJingqi Song, Hui Liu, Kai Deng — 2017
Convolutional Low-Resolution Fine-Grained ClassificationDingding Cai, Ke Chen, Yanlin Qian — 2017
Single Image Super Resolution - When Model Adaptation MattersYudong Liang, Radu Timofte, Jinjun Wang — 2017
Deep Laplacian Pyramid Networks for Fast and Accurate Super-ResolutionWei‐Sheng Lai, Jia‐Bin Huang, Narendra Ahuja — 2017
Convolutional Neural Pyramid for Image ProcessingXiaoyong Shen, Ying-Cong Chen, Xin Tao — 2017
Video Super-Resolution via Bidirectional Recurrent Convolutional NetworksYan Huang, Wei Wang, Liang Wang — 2018
Conditional CycleGAN for Attribute Guided Face Image GenerationYongyi Lu, Yu‐Wing Tai, Chi–Keung Tang — 2017
Anatomically Constrained Neural Networks (ACNNs): Application to Cardiac Image Enhancement and SegmentationOzan Oktay, Enzo Ferrante, Konstantinos Kamnitsas — 2017
Structure-Preserving Image Super-Resolution via Contextualized Multitask LearningYukai Shi, Keze Wang, Chongyu Chen — 2017
Super-Resolution for Remote Sensing Images via Local–Global Combined NetworkSen Lei, Zhenwei Shi, Zhengxia Zou — 2017

Accelerating the Super-Resolution Convolutional Neural Network

Summary

Keywords

References

Cited by

Related papers