【Bringing Old Photos Back to Life】Mapping(mapping_net)映射网络

随着深度学习的出现，人们可以利用卷积神经网络强大的表示能力，即学习来解决各种低级图像恢复问题[5, 6, 7, 8, 9, 10, 11, 12] 来自大量合成图像的特定任务的映射 

2.The mapping between the two latent spaces is then learned with the synthetic image pairs, which restores the corrupted images to clean ones.

然后使用合成图像对学习两个潜在空间之间的映射，将损坏的图像恢复为干净的图像。 

3.Restoration via latent space translation :In order to mitigate the domain gap, we formulate the old photo restoration as an image translation problem, where we treat clean images and old photos as images from distinct domains and we wish to learn the mapping in between.

通过潜在空间转换进行恢复：为了减少域间隙，我们将旧照片恢复制定为图像转换问题，我们将干净的图像和旧照片视为来自不同领域的图像，我们希望学习它们之间的映射。 

4.Then,we learn the mapping that restores the corrupted images to clean ones in the latent space.

然后，我们学习将损坏的图像恢复到潜在空间中干净的图像的映射。

5.VAEs with two-stage training (VAEs-TS): the two VAEs are first trained separately and the latent mapping is learned thereafter with the two VAEs (not fixed);

两阶段训练的VAE（VAEs-TS）：首先分别训练两个VAE，然后用两个VAE学习潜在映射（不固定）；