Frequency Consistent Adaptation for Real World Super Resolution

Authors

  • Xiaozhong Ji National Key Lab for Novel Software Technology, Nanjing University
  • Guangpin Tao National Key Lab for Novel Software Technology, Nanjing University
  • Yun Cao Tencent Youtu Lab
  • Ying Tai Tencent Youtu Lab
  • Tong Lu National Key Lab for Novel Software Technology, Nanjing University
  • Chengjie Wang Tencent Youtu Lab
  • Jilin Li Tencent Youtu Lab
  • Feiyue Huang Tencent Youtu Lab

Keywords:

Low Level & Physics-based Vision

Abstract

Recent deep-learning based Super-Resolution (SR) methods have achieved remarkable performance on images with known degradation. However, these methods always fail in real-world scene, since the Low-Resolution (LR) images after the ideal degradation (e.g., bicubic down-sampling) deviate from real source domain. The domain gap between the LR images and the real-world images can be observed clearly on frequency density, which inspires us to explicitly narrow the undesired gap caused by incorrect degradation. From this point of view, we design a novel Frequency Consistent Adaptation (FCA) that ensures the frequency domain consistency when applying existing SR methods to the real scene. We estimate degradation kernels from unsupervised images and generate the corresponding LR images. To provide useful gradient information for kernel estimation, we propose Frequency Density Comparator (FDC) by distinguishing the frequency density of images on different scales. Based on the domain-consistent LR-HR pairs, we train easy-implemented Convolutional Neural Network (CNN) SR models. Extensive experiments show that the proposed FCA improves the performance of the SR model under real-world setting achieving state-of-the-art results with high fidelity and plausible perception, thus providing a novel effective framework for real-world SR application.

Downloads

Published

2021-05-18

How to Cite

Ji, X., Tao, G., Cao, Y., Tai, Y., Lu, T., Wang, C., Li, J., & Huang, F. (2021). Frequency Consistent Adaptation for Real World Super Resolution. Proceedings of the AAAI Conference on Artificial Intelligence, 35(2), 1664-1672. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16259

Issue

Section

AAAI Technical Track on Computer Vision I