Authors
Xintao Wang, Liangbin Xie, Chao Dong, Ying Shan
Applied Research Center (ARC), Tencent PCG; Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences; University of Chinese Academy of Sciences; Shanghai AI Laboratory
Portals
Summary
In this work, we aim to extend the powerful ESRGAN to restore general real-world LR images by synthesizing training pairs with a more practical degradation process.
Abstract
Though many attempts have been made in blind super-resolution to restore low-resolution images with unknown and complex degradations, they are still far from addressing general real-world degraded images. In this work, we extend the powerful ESRGAN to a practical restoration application (namely, Real-ESRGAN), which is trained with pure synthetic data. Specifically, a high-order degradation modeling process is introduced to better simulate complex real-world degradations. We also consider the common ringing and overshoot artifacts in the synthesis process. In addition, we employ a U-Net discriminator with spectral normalization to increase discriminator capability and stabilize the training dynamics. Extensive comparisons have shown its superior visual performance than prior works on various real datasets. We also provide efficient implementations to synthesize training pairs on the fly.
Contribution
- We propose a high-order degradation process to model practical degradations, and utilize sinc filters to model common ringing and overshoot artifacts
- We employ several essential modifications (e.g., U-Net discriminator with spectral normalization) to increase discriminator capability and stabilize the training dynamics
- Real-ESRGAN trained with pure synthetic data is able to restore most real-world images and achieve better visual performance than previous works, making it more practical in real-world applications
Related Works
The image super-resolution; Degradation models