Learning Structral coherence Via Generative Adversarial Network for Single Image Super-Resolution

Among the major remaining challenges for single image super resolution (SISR) is the capacity to recover coherent images with global shapes and local details conforming to human vision system. Recent generative adversarial network (GAN) based SISR methods have yielded overall realistic SR images, however, there are always unpleasant textures accompanied with structural distortions in local regions. To target these issues, we introduce the gradient branch into the generator to preserve structural information by restoring high-resolution gradient maps in SR process. In addition, we utilize a U-net based discriminator to consider both the whole image and the detailed per-pixel authenticity, which could encourage the generator to maintain overall coherence of the reconstructed images. Moreover, we have studied objective functions and LPIPS perceptual loss is added to generate more realistic and natural details. Experimental results show that our proposed method outperforms state-of-the-art perceptual-driven SR methods in perception index (PI), and obtains more geometrically consistent and visually pleasing textures in natural image restoration.

[1]  Tieniu Tan,et al.  Meta-SR: A Magnification-Arbitrary Network for Super-Resolution , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Seon Joo Kim,et al.  Investigating Loss Functions for Extreme Super-Resolution , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

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

[4]  Kyung-Ah Sohn,et al.  Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New Strategy , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

[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]  Seong Joon Oh,et al.  CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[8]  Li Fei-Fei,et al.  Perceptual Losses for Real-Time Style Transfer and Super-Resolution , 2016, ECCV.

[9]  Jie Zhou,et al.  Structure-Preserving Super Resolution With Gradient Guidance , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Radu Timofte,et al.  2018 PIRM Challenge on Perceptual Image Super-resolution , 2018, ArXiv.

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

[12]  Luc Van Gool,et al.  Deep Unfolding Network for Image Super-Resolution , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Eirikur Agustsson,et al.  NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

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

[15]  Bernt Schiele,et al.  A U-Net Based Discriminator for Generative Adversarial Networks , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

[17]  Alexia Jolicoeur-Martineau,et al.  The relativistic discriminator: a key element missing from standard GAN , 2018, ICLR.

[18]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[19]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[20]  Chao Dong,et al.  Recovering Realistic Texture in Image Super-Resolution by Deep Spatial Feature Transform , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[21]  Yu Qiao,et al.  ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks , 2018, ECCV Workshops.

[22]  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.

[23]  Chang Dong Yoo,et al.  Fast and Efficient Image Quality Enhancement via Desubpixel Convolutional Neural Networks , 2018, ECCV Workshops.

[24]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

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

[26]  J. DiCarlo,et al.  Using goal-driven deep learning models to understand sensory cortex , 2016, Nature Neuroscience.

[27]  Alexei A. Efros,et al.  The Unreasonable Effectiveness of Deep Features as a Perceptual Metric , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.