Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Structure-Preserving Super Resolution with Gradient Guidance

About

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.

Cheng Ma, Yongming Rao, Yean Cheng, Ce Chen, Jiwen Lu, Jie Zhou• 2020

Related benchmarks

TaskDatasetResultRank
Image Super-resolutionSet5--
507
Super-ResolutionSet14 (test)
PSNR26.86
246
Super-ResolutionBSD100
PSNR24.16
149
Super-ResolutionDIV2K
PSNR28.19
101
Super-ResolutionBSD100 4x (test)
PSNR24.16
56
Super-ResolutionManga109 (test)
PSNR28.561
46
Super-ResolutionGeneral100
LPIPS0.0863
25
Super-ResolutionUrban100
PSNR23.24
12
Super-ResolutionSet14
PSNR26.564
12
Super-ResolutionBSD100
PSNR25.546
12
Showing 10 of 17 rows

Other info

Code

Follow for update