Frequency Consistent Adaptation for Real World Super Resolution

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 realworld SR application.

Authors

• Xiaozhong Ji
• Guangpin Tao
• Yun Cao
• Ying Tai State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, China School of Intelligence Science and Technology, Nanjing University, Suzhou, China
• Tong Lu National Key Lab for Novel Software Technology, Nanjing University, Nanjing, China
• Chengjie Wang Tencent Youtu Lab Shanghai Jiao Tong University
• Jilin Li
• Feiyue Huang

Keywords

No keywords are indexed for this paper.