Frequency Consistent Adaptation for Real World Super Resolution
This work provides an effective framework for improving the performance of existing SR models in real-world applications by addressing the domain gap caused by incorrect degradation kernels, which is a problem for users seeking practical SR solutions.
This paper addresses the failure of existing Super-Resolution (SR) methods in real-world scenarios due to the domain gap between synthetically degraded low-resolution (LR) images and real-world images. The authors propose a Frequency Consistent Adaptation (FCA) framework that narrows this gap by ensuring frequency domain consistency, leading to state-of-the-art results in real-world SR with high fidelity and plausible perception.
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 explictly 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.