Structure-Preserving Super Resolution With Gradient Guidance

By Cheng Ma, Yongming Rao, Yean Cheng, Ce Chen, Jiwen Lu, Jie Zhou. Computer Vision and Pattern Recognition, 2020

388 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/c9287de07ff689cfaf700a5b1999f7fbb2707275

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Yulun Zhang
2. Yapeng Tian
3. Luc Van Gool
4. Radu Timofte
5. Lei Zhang
6. Wenming Yang
7. Xing Wu
8. Bin Xia

Citations in the corpus

• DiffIR: Efficient Diffusion Model for Image Restoration (2023, methodology): “1 (b) show the performance and MultAdds comparsion of DiffIRS2 with SOTA GAN-based SR methods: SFTGAN [64], SRGAN [34], ESRGAN [65], USRGAN [80], SPSR [42], and BebyGAN [37].”