TL;DR
This paper introduces a structure-preserving super-resolution method that enhances geometric accuracy in generated images by using gradient guidance and a learnable neural structure extractor, improving upon existing GAN-based approaches.
Contribution
It proposes a novel gradient-guided super-resolution framework with a neural structure extractor and self-supervised learning, significantly reducing structural distortions in SR images.
Findings
Outperforms state-of-the-art perceptual SR methods on benchmark datasets.
Effectively preserves geometric structures in super-resolved images.
Achieves higher LPIPS, PSNR, and SSIM scores.
Abstract
Structures matter in single image super-resolution (SISR). Benefiting from generative adversarial networks (GANs), recent studies have promoted the development of SISR by recovering photo-realistic images. However, there are still undesired structural distortions in the recovered images. In this paper, we propose a structure-preserving super-resolution (SPSR) method to alleviate the above issue while maintaining the merits of GAN-based methods to generate perceptual-pleasant details. Firstly, we propose SPSR with gradient guidance (SPSR-G) by exploiting 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 to impose a second-order restriction on the super-resolved images, which helps generative…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsJigsaw
