Generative adversarial network (GAN) is one of the most prevalent generative models that can synthesise realistic high-frequency details. However, a mismatch between the input and the output may arise when GAN is directly applied to image super-resolution. To alleviate this issue, the authors adopted a conditional GAN (cGAN) in this study. The cGAN discriminator attempted to guess whether the unknown high-resolution (HR) image was produced by the generator with the aid of the original low-resolution (LR) image. They propose a novel discriminator that only penalises at the scale of the patch and, thus, has relatively few parameters to train. The generator of cGAN is an encoder–decoder with skip connections to shuttle the shared low-level information directly across the network. To better maintain the low-frequency information and recover the high-frequency information, they designed a generator loss function combining adversarial loss term and L1 loss term. The former term is beneficial to the synthesis of fine-grained textures, while the latter is responsible for learning the overall structure of the LR input. The experiments revealed that the proposed method could generate HR images with richer details and less over-smoothness.

中文翻译：

---

基于条件生成对抗网络的图像超分辨率

生成对抗网络（GAN）是最流行的生成模型之一，可以合成现实的高频细节。但是，当GAN直接应用于图像超分辨率时，可能会在输入和输出之间出现不匹配的情况。为了缓解这个问题，作者在本研究中采用了条件GAN（cGAN）。cGAN鉴别器试图猜测发生器是否借助原始的低分辨率（LR）图像生成了未知的高分辨率（HR）图像。他们提出了一种新颖的鉴别器，该鉴别器仅在补丁的规模上是惩罚性的，因此具有相对较少的要训练的参数。cGAN的生成器是一个编码器-解码器，具有跳过连接，可直接在网络上穿梭共享的底层信息。为了更好地维护低频信息并恢复高频信息，他们设计了一种将对抗性损失项和L1损失项组合在一起的发电机损失函数。前一个术语有助于细粒度纹理的合成，而后者则负责学习LR输入的整体结构。实验表明，该方法可以生成细节更丰富，平滑度较小的HR图像。