Structure-Preserving Super Resolution With Gradient Guidance
Authors:
Top Cited Papers
- 1 June 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 7766-7775
Abstract
Structures matter in single image super resolution (SISR). Recent studies benefiting from generative adversarial network (GAN) have promoted the development of SISR by recovering photo-realistic images. However, there are always undesired structural distortions in the recovered images. In this paper, we propose a structure-preserving super resolution method to alleviate the above issue while maintaining the merits of GAN-based methods to generate perceptual-pleasant details. Specifically, we exploit gradient maps of images to guide the recovery in two aspects. On the one hand, we restore high-resolution gradient maps by a gradient branch to provide additional structure priors for the SR process. On the other hand, we propose a gradient loss which imposes a second-order restriction on the super-resolved images. Along with the previous image-space loss functions, the gradient-space objectives help generative networks concentrate more on geometric structures. Moreover, our method is model-agnostic, which can be potentially used for off-the-shelf SR networks. Experimental results show that we achieve the best PI and LPIPS performance and meanwhile comparable PSNR and SSIM compared with state-of-the-art perceptual-driven SR methods. Visual results demonstrate our superiority in restoring structures while generating natural SR images.Keywords
All Related Versions
This publication has 37 references indexed in Scilit:
- Accurate Image Super-Resolution Using Very Deep Convolutional Networks2016
- Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network2016
- Modeling deformable gradient compositions for single-image super-resolution2015
- Image and video upscaling from local self-examplesACM Transactions on Graphics, 2011
- Image Super-Resolution Via Sparse RepresentationIEEE Transactions on Image Processing, 2010
- Single-Image Super-Resolution Using Sparse Regression and Natural Image PriorIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- Image upsampling via imposed edge statisticsACM Transactions on Graphics, 2007
- A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics2002
- Example-based super-resolutionIEEE Computer Graphics and Applications, 2002
- Improving resolution by image registrationCVGIP: Graphical Models and Image Processing, 1991