Hierarchical Recursive Network for Single Image Super Resolution

Super Resolution (SR) technique aims to reconstruct the high resolution (HR) image from the observed low resolution (LR) one, which is a significant application in our daily life. In this paper, we propose a novel structure named hier-archical recursive network (HRN), which consists of several sub networks and will reconstruct the HR progressively. In each sub network, the LR feature map will be used as input, the contextual information will be explored and the predicted residuals together with the transposed convolutional outputs will be fused to the finer one. Besides, our network can generate multi-scale HR images with a single model and thus is potentially useful in practical applications. Extensive experi-mental results show that our proposed method can achieve the state-of-the-art performance.

[1]  Kyoung Mu Lee,et al.  Deeply-Recursive Convolutional Network for Image Super-Resolution , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Thomas S. Huang,et al.  Deep Networks for Image Super-Resolution with Sparse Prior , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[3]  Charless C. Fowlkes,et al.  Contour Detection and Hierarchical Image Segmentation , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Kyoung Mu Lee,et al.  Accurate Image Super-Resolution Using Very Deep Convolutional Networks , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Michael Elad,et al.  On Single Image Scale-Up Using Sparse-Representations , 2010, Curves and Surfaces.

[6]  Narendra Ahuja,et al.  Single image super-resolution from transformed self-exemplars , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Chih-Yuan Yang,et al.  Single-Image Super-Resolution: A Benchmark , 2014, ECCV.

[8]  Aline Roumy,et al.  Low-Complexity Single-Image Super-Resolution based on Nonnegative Neighbor Embedding , 2012, BMVC.

[9]  Thomas S. Huang,et al.  Image Super-Resolution Via Sparse Representation , 2010, IEEE Transactions on Image Processing.

[10]  Thomas B. Moeslund,et al.  Super-resolution: a comprehensive survey , 2014, Machine Vision and Applications.

[11]  Xiaoou Tang,et al.  Accelerating the Super-Resolution Convolutional Neural Network , 2016, ECCV.

[12]  Xiaoou Tang,et al.  Image Super-Resolution Using Deep Convolutional Networks , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Narendra Ahuja,et al.  Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Kiyoharu Aizawa,et al.  Sketch-based manga retrieval using manga109 dataset , 2015, Multimedia Tools and Applications.

[15]  Yun Fu,et al.  Residual Dense Network for Image Restoration , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.