Single Image Super Resolution - When Model Adaptation Matters

In the recent years impressive advances were made for single image super-resolution. Deep learning is behind a big part of this success. Deep(er) architecture design and external priors modeling are the key ingredients. The internal contents of the low resolution input image is neglected with deep modeling despite the earlier works showing the power of using such internal priors. In this paper we propose a novel deep convolutional neural network carefully designed for robustness and efficiency at both learning and testing. Moreover, we propose a couple of model adaptation strategies to the internal contents of the low resolution input image and analyze their strong points and weaknesses. By trading runtime and using internal priors we achieve 0.1 up to 0.3dB PSNR improvements over best reported results on standard datasets. Our adaptation especially favors images with repetitive structures or under large resolutions. Moreover, it can be combined with other simple techniques, such as back-projection or enhanced prediction, for further improvements.

[1]  Jian Sun,et al.  Identity Mappings in Deep Residual Networks , 2016, ECCV.

[2]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Kun Li,et al.  Video super-resolution using an adaptive superpixel-guided auto-regressive model , 2016, Pattern Recognit..

[4]  Andrea Vedaldi,et al.  MatConvNet: Convolutional Neural Networks for MATLAB , 2014, ACM Multimedia.

[5]  Stefan Harmeling,et al.  Learning How to Combine Internal and External Denoising Methods , 2013, GCPR.

[6]  Michal Irani,et al.  Super-resolution from a single image , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[7]  Hong Chang,et al.  Super-resolution through neighbor embedding , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[8]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[9]  Deqing Sun,et al.  A Bayesian approach to adaptive video super resolution , 2011, CVPR 2011.

[10]  Jacques-Olivier Lachaud,et al.  Geometric Total Variation for Image Vectorization, Zooming and Pixel Art Depixelizing , 2019, ACPR.

[11]  Junping Zhang,et al.  Super-resolution of human face image using canonical correlation analysis , 2010, Pattern Recognit..

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

[13]  Jian Yang,et al.  MemNet: A Persistent Memory Network for Image Restoration , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

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

[15]  Jian Yang,et al.  Image Super-Resolution via Deep Recursive Residual Network , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[17]  Yun Fu,et al.  Residual Dense Network for Image Super-Resolution , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[18]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[20]  Luc Van Gool,et al.  Anchored Neighborhood Regression for Fast Example-Based Super-Resolution , 2013, 2013 IEEE International Conference on Computer Vision.

[21]  Raanan Fattal,et al.  Image and video upscaling from local self-examples , 2011, TOGS.

[22]  Yao Zhao,et al.  Simultaneous color-depth super-resolution with conditional generative adversarial networks , 2019, Pattern Recognit..

[23]  Hao Shen,et al.  Joint learning sparsifying linear transformation for low-resolution image synthesis and recognition , 2017, Pattern Recognit..

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

[25]  Pascal Getreuer,et al.  Image Interpolation with Geometric Contour Stencils , 2011, Image Process. Line.

[26]  Grgoire Montavon,et al.  Neural Networks: Tricks of the Trade , 2012, Lecture Notes in Computer Science.

[27]  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).

[28]  Xiaoou Tang,et al.  Learning a Deep Convolutional Network for Image Super-Resolution , 2014, ECCV.

[29]  Yongwei Nie,et al.  Video super-resolution via pre-frame constrained and deep-feature enhanced sparse reconstruction , 2020, Pattern Recognit..

[30]  Luc Van Gool,et al.  Seven Ways to Improve Example-Based Single Image Super Resolution , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[31]  Michal Irani,et al.  Internal statistics of a single natural image , 2011, CVPR 2011.

[32]  Shun-ichi Amari,et al.  Natural Gradient Works Efficiently in Learning , 1998, Neural Computation.

[33]  Adam Finkelstein,et al.  PatchMatch: a randomized correspondence algorithm for structural image editing , 2009, SIGGRAPH 2009.

[34]  Kanter,et al.  Eigenvalues of covariance matrices: Application to neural-network learning. , 1991, Physical review letters.

[35]  Michal Irani,et al.  Motion Analysis for Image Enhancement: Resolution, Occlusion, and Transparency , 1993, J. Vis. Commun. Image Represent..

[36]  Michal Irani,et al.  Improving resolution by image registration , 1991, CVGIP Graph. Model. Image Process..

[37]  Dinggang Shen,et al.  Brain atlas fusion from high-thickness diagnostic magnetic resonance images by learning-based super-resolution , 2017, Pattern Recognit..

[38]  Zhe L. Lin,et al.  Fast Image Super-Resolution Based on In-Place Example Regression , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[39]  Tapani Raiko,et al.  Deep Learning Made Easier by Linear Transformations in Perceptrons , 2012, AISTATS.

[40]  Michal Irani,et al.  "Zero-Shot" Super-Resolution Using Deep Internal Learning , 2017, CVPR.

[41]  R. Keys Cubic convolution interpolation for digital image processing , 1981 .

[42]  Christian Ledig,et al.  Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[43]  Lingfeng Wang,et al.  Ensemble based deep networks for image super-resolution , 2017, Pattern Recognit..

[44]  Jitendra Malik,et al.  A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[45]  Eric Dubois,et al.  Image up-sampling using total-variation regularization with a new observation model , 2005, IEEE Transactions on Image Processing.

[46]  Luc Van Gool,et al.  A+: Adjusted Anchored Neighborhood Regression for Fast Super-Resolution , 2014, ACCV.

[47]  Zhenyue Zhang,et al.  Locally affine patch mapping and global refinement for image super-resolution , 2011, Pattern Recognit..

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

[49]  Horst Bischof,et al.  Fast and accurate image upscaling with super-resolution forests , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[50]  Thomas S. Huang,et al.  Image super-resolution as sparse representation of raw image patches , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[51]  Kyoung Mu Lee,et al.  Enhanced Deep Residual Networks for Single Image Super-Resolution , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[52]  P. V. Arun,et al.  Convolutional network architectures for super-resolution/sub-pixel mapping of drone-derived images , 2019, Pattern Recognit..

[53]  Lei Zhang,et al.  Nonlocally Centralized Sparse Representation for Image Restoration , 2013, IEEE Transactions on Image Processing.