深度学习将灰度图着色_使用DeOldify着色和还原灰度图像和视频

深度学习将灰度图着色

Image colorization is an engaging topic in the field of image-to-image translation. Even though color photography was invented in 1907, It didn’t become popular for the average person until the 1960s because of its expensiveness and inaccessibility. All the photography and videography up until then was done on Black & White. Colorizing these images was impossible—until the DeOldify deep learning model came to life.

图像着色是图像到图像翻译领域中的一个引人入胜的话题。 尽管彩色摄影是在1907年发明的，但由于价格昂贵且难以获得，直到1960年代才在普通人中流行。 直到那时所有的摄影和录像都是在黑白上完成的。 为这些图像着色是不可能的-直到DeOldify深度学习模型问世。

什么是DeOldify？ (What is DeOldify?)

DeOldify is an open-source deep learning model created by Jason Antic, used to add high-quality colorization to grayscale images with amazing results. Simply put, the goal of this deep learning model is to colorize, restore, and give new life to old images and film footage.

DeOldify是由Jason Antic创建的开源深度学习模型，用于为灰度图像添加高质量的着色效果。 简而言之，这种深度学习模型的目标是对旧图像和胶片进行着色，还原并赋予新生命。

Before we get started on the installation, let’s see an example of how it might look when we use DeOldify to colorize old film footage.

在开始安装之前，让我们看一个示例，该示例说明使用DeOldify对旧电影胶片进行着色时的外观。

Example of Colorized Dream Speech 1963

彩色梦致演讲实例(1963年)

The old version of DeOldify used GANs (Generative Adversarial Networks), a network architecture that includes repetitive interaction between two complementary neural networks: a generator and discriminator. The pre-trained generator model does the task of adding colors to the recognized objects, and the discriminator does the task of “criticizing” the generator’s choice of color.

DeOldify的旧版本使用GANs(生成对抗网络) ，该网络体系结构包括两个互补神经网络(生成器和鉴别器)之间的重复交互。 预先训练的生成器模型执行将颜色添加到已识别对象的任务，而鉴别器执行“批评”生成器的颜色选择的任务。

After the introduction of NoGAN training (covered in more details below) and combining it with GAN training, DeOldify was able to produce more stable and colorful images.

在引入NoGAN培训(在下面更详细地介绍)并将其与GAN培训相结合之后，DeO