Abstract
Single-image super-resolution (SISR) methods based on convolutional neural networks (CNN) have shown great potential in the literature. However, most deep CNN models don’t have direct access to subsequent layers, seriously hindering the information flow. Furthermore, they fail to make full use of the hierarchical features from different low-level layers, thereby resulting in relatively low accuracy. In this article, we present a new SISR CNN, called SymSR, which incorporates symmetrical nested residual connections to improve both the accuracy and the execution speed. SymSR takes a larger image region for contextual spreading. It symmetrically combines multiple short paths for the forward propagation to improve the accuracy and for the backward propagation of gradient flow to accelerate the convergence speed. Extensive experiments based on open challenge datasets show the effectiveness of symmetrical residual connections. Compared with four other state-of-the-art super-resolution CNN methods, SymSR is superior in both accuracy and runtime.
- Eirikur Agustsson and Radu Timofte. 2017. Ntire 2017 challenge on single image super-resolution: Dataset and study. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Vol. 3. 2.Google Scholar
Cross Ref
- Yoshua Bengio, Patrice Simard, and Paolo Frasconi. 1994. Learning long-term dependencies with gradient descent is difficult. IEEE Transactions on Neural Networks 5, 2 (1994), 157--166. Google Scholar
Digital Library
- Marco Bevilacqua, Aline Roumy, Christine Guillemot, and Marie Line Alberi-Morel. 2012. Low-complexity single-image super-resolution based on nonnegative neighbor embedding. In Proceedings of the 23rd British Machine Vision Conference (BMVC'12). 135.1--135.10.Google Scholar
Cross Ref
- Marco Bevilacqua, Aline Roumy, Christine Guillemot, and Marie-Line Alberi Morel. 2013. Super-resolution using neighbor embedding of back-projection residuals. In 18th International Conference on Digital Signal Processing (DSP’13). IEEE, 1--8.Google Scholar
Cross Ref
- Chao Dong, Chen Change Loy, Kaiming He, and Xiaoou Tang. 2016. Image super-resolution using deep convolutional networks. IEEE Transactions on Pattern Analysis and Machine Intelligence 38, 2 (2016), 295--307. Google Scholar
Digital Library
- Gilad Freedman and Raanan Fattal. 2011. Image and video upscaling from local self-examples. ACM Transactions on Graphics (TOG) 30, 2 (2011), 12. Google Scholar
Digital Library
- Daniel Glasner, Shai Bagon, and Michal Irani. 2009. Super-resolution from a single image. In IEEE 12th International Conference on Computer Vision. IEEE, 349--356.Google Scholar
Cross Ref
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In IEEE Conference on Computer Vision and Pattern Recognition. 770--778.Google Scholar
Cross Ref
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Identity mappings in deep residual networks. In European Conference on Computer Vision. Springer, 630--645.Google Scholar
Cross Ref
- Jia-Bin Huang, Abhishek Singh, and Narendra Ahuja. 2015. Single image super-resolution from transformed self-exemplars. In IEEE Conference on Computer Vision and Pattern Recognition. 5197--5206.Google Scholar
Cross Ref
- Kui Jia, Xiaogang Wang, and Xiaoou Tang. 2013. Image transformation based on learning dictionaries across image spaces. IEEE Transactions on Pattern Analysis and Machine Intelligence 35, 2 (2013), 367--380. Google Scholar
Digital Library
- Yangqing Jia, Evan Shelhamer, Jeff Donahue, Sergey Karayev, Jonathan Long, Ross Girshick, Sergio Guadarrama, and Trevor Darrell. 2014. Caffe: Convolutional architecture for fast feature embedding. In 22nd ACM International Conference on Multimedia. ACM, 675--678. Google Scholar
Digital Library
- Jiwon Kim, Jung Kwon Lee, and Kyoung Mu Lee. 2016. Accurate image super-resolution using very deep convolutional networks. In IEEE Conference on Computer Vision and Pattern Recognition. 1646--1654.Google Scholar
Cross Ref
- Jiwon Kim, Jung Kwon Lee, and Kyoung Mu Lee. 2016. Deeply-recursive convolutional network for image super-resolution. In IEEE Conference on Computer Vision and Pattern Recognition. 1637--1645.Google Scholar
Cross Ref
- Wei-Sheng Lai, Jia-Bin Huang, Narendra Ahuja, and Ming-Hsuan Yang. 2017. Deep Laplacian pyramid networks for fast and accurate super-resolution. In IEEE Conference on Computer Vision and Pattern Recognition. 624--632.Google Scholar
Cross Ref
- Yann LeCun, Léon Bottou, Yoshua Bengio, and Patrick Haffner. 1998. Gradient-based learning applied to document recognition. Proc. IEEE 86, 11 (1998), 2278--2324.Google Scholar
Cross Ref
- Christian Ledig, Lucas Theis, Ferenc Huszár, Jose Caballero, Andrew Cunningham, Alejandro Acosta, Andrew Aitken, Alykhan Tejani, Johannes Totz, Zehan Wang, et al. 2016. Photo-realistic single image super-resolution using a generative adversarial network. arXiv preprint (2016).Google Scholar
- Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical Image Computing and Computer-assisted Intervention. Springer, 234--241.Google Scholar
Cross Ref
- Samuel Schulter, Christian Leistner, and Horst Bischof. 2015. Fast and accurate image upscaling with super-resolution forests. In IEEE Conference on Computer Vision and Pattern Recognition. 3791--3799.Google Scholar
Cross Ref
- Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014).Google Scholar
- Abhishek Singh and Narendra Ahuja. 2014. Super-resolution using sub-band self-similarity. In Asian Conference on Computer Vision. Springer, 552--568.Google Scholar
- Christian Szegedy, Sergey Ioffe, Vincent Vanhoucke, and Alexander A. Alemi. 2017. Inception-v4, inception-resnet and the impact of residual connections on learning. In AAAI, Vol. 4. 12. Google Scholar
Digital Library
- Ying Tai, Jian Yang, Xiaoming Liu, and Chunyan Xu. 2017. MemNet: A persistent memory network for image restoration. (2017), 4549--4557.Google Scholar
- Radu Timofte, Vincent De, and Luc Van Gool. 2013. Anchored neighborhood regression for fast example-based super-resolution. In IEEE International Conference on Computer Vision (ICCV’13). IEEE, 1920--1927. Google Scholar
Digital Library
- Radu Timofte, Vincent De Smet, and Luc Van Gool. 2014. A+: Adjusted anchored neighborhood regression for fast super-resolution. In Asian Conference on Computer Vision. Springer, 111--126.Google Scholar
- Du Tran, Lubomir Bourdev, Rob Fergus, Lorenzo Torresani, and Manohar Paluri. 2015. Learning spatiotemporal features with 3D convolutional networks. In IEEE International Conference on Computer Vision (ICCV’15). IEEE, 4489--4497. Google Scholar
Digital Library
- Chih-Yuan Yang and Ming-Hsuan Yang. 2013. Fast direct super-resolution by simple functions. In IEEE International Conference on Computer Vision (ICCV’13). IEEE, 561--568. Google Scholar
Digital Library
- Jianchao Yang, John Wright, Thomas S. Huang, and Yi Ma. 2010. Image super-resolution via sparse representation. IEEE Transactions on Image Processing 19, 11 (2010), 2861--2873. Google Scholar
Digital Library
- Lequan Yu, Xin Yang, Hao Chen, Jing Qin, and Pheng-Ann Heng. 2017. Volumetric ConvNets with mixed residual connections for automated prostate segmentation from 3D MR images. In AAAI. 66--72. Google Scholar
Digital Library
- Sergey Zagoruyko and Nikos Komodakis. 2016. Wide residual networks. arXiv preprint arXiv:1605.07146 (2016).Google Scholar
- Roman Zeyde, Michael Elad, and Matan Protter. 2010. On single image scale-up using sparse-representations. In International Conference on Curves and Surfaces. Springer, 711--730. Google Scholar
Digital Library
- Y. Zhang, L. Sun, C. Yan, X. Ji, and Q. Dai. 2018. Adaptive residual networks for high-quality image restoration. IEEE Transactions on Image Processing PP, 99 (2018), 1--1.Google Scholar
Index Terms
Symmetrical Residual Connections for Single Image Super-Resolution
Recommendations
Single image super-resolution via self-similarity and low-rank matrix recovery
We propose a novel single-image super resolution (SISR) approach using self-similarity of image and the low-rank matrix recovery (LRMR). The method performs multiple upsampling steps with relatively small magnification factors to recover a desired high ...
Single Image Super-Resolution Based on Local Self-Similarity
ACPR '13: Proceedings of the 2013 2nd IAPR Asian Conference on Pattern RecognitionSingle image super-resolution, namely increasing the resolution from only one coarse-resolution image, is a fundamental problem in computer vision. Although it has been extensively studied for decades, super-resolving a real-world image still remains ...
A Single Image Super-Resolution Algorithm Based on Dense Residual Convolutional Network
AbstractSingle image super-resolution via convolutional neural network (CNN) has demonstrated superior performance. In this paper, we propose a deep CNN model named super-resolution dense residual convolutional network (SRDCR) with the goal of ...






Comments