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.

本研究将 ESRGAN 应用于实际的纹理恢复应用中，在处理复杂的真实世界退化图像时，引入高阶退化建模过程，并考虑到常见的环绕和过冲伪影，采用具有谱归一化的 U-Net 鉴别器来增强鉴别器的能力和稳定训练动力学， 并提供了实时生成训练样本的高效实现。

Real-ESRGAN: 使用纯合成数据进行实际世界盲超分辨率训练

Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure  Synthetic Data

Among the major remaining challenges for generative adversarial networks
(GANs) is the capacity to synthesize globally and locally coherent images with
object shapes and textures indistinguishable from real images. To target this
issue we propose an alternative U-Net based discriminator architecture,
borrowing the insights from the segmentation literature. The proposed U-Net
based architecture allows to provide detailed per-pixel feedback to the
generator while maintaining the global coherence of synthesized images, by
providing the global image feedback as well. Empowered by the per-pixel
response of the discriminator, we further propose a per-pixel consistency
regularization technique based on the CutMix data augmentation, encouraging the
U-Net discriminator to focus more on semantic and structural changes between
real and fake images. This improves the U-Net discriminator training, further
enhancing the quality of generated samples. The novel discriminator improves
over the state of the art in terms of the standard distribution and image
quality metrics, enabling the generator to synthesize images with varying
structure, appearance and levels of detail, maintaining global and local
realism. Compared to the BigGAN baseline, we achieve an average improvement of
2.7 FID points across FFHQ, CelebA, and the newly introduced COCO-Animals
dataset. The code is available at this https URL

该研究通过提出基于 U-Net 鉴别器的架构以及基于 CutMix 数据增广的像素一致性规则技术提高了生成对抗网络的合成图像的全局和局部连贯性，并在标准分布和图像质量指标方面优于已有研究成果，与 BigGAN 基线相比，能够在 FFHQ、CelebA 和新引入的 COCO-Animals 数据集上实现平均 2.7 FID 分数的提升。