译语翻译分享-AI 修复是如何给黑白影像上色的？

AI 修复是如何给黑白影像上色的？

How does AI repair color black and white images?

 

Technical Principle

AI 上色的原理是什么？那我们就需要介绍一种深度学习网络架构了，它就是 GAN（这里不是粗话）。GAN 不是干饭人的干，而是生成对抗网络（英语：Generative Adversarial Network，简称 GAN）。当然，太复杂的技术讲解可能会让读者迷惑，于是我找到一张很直白的原理图。

What is the principle of AI coloring? Then we need to introduce a deep learning network architecture, which is GAN (not foul language here). GAN is not the job of a fan, but a generative adversarial network (English: Generative Adversarial Network, referred to as GAN). Of course, too complicated technical explanations may confuse readers, so I found a very straightforward schematic.

GAN 网络分两部分，一个是生成器（Generator），一个是鉴别器（Discriminator）。生成器通过对图像上色，然后交给鉴别器。鉴别器判断这一个图片看起来真不真，如果觉得假，鉴别器会返回「修改意见」，让生成器重新试试，直到鉴别器觉得足够真了。如果你觉得还不好懂，我再打个比方，这就好像美术老师指导学生画画的过程，一开始学生画出来的不够好，老师指出，学生尝试改改，老师再检查，再给意见，直到老师满意。

The GAN network is divided into two parts, one is the generator and the other is the discriminator. The generator colors the image and then passes it to the discriminator. The discriminator judges that this picture looks true or not. If it feels false, the discriminator will return the "modification opinion" and let the generator try again until the discriminator feels it is true enough. If you think it’s not easy to understand, let me make an analogy. It’s like the process of an art teacher instructing students to draw. At the beginning, the students did not draw well enough. The teacher pointed out that the students tried to make changes, the teacher would check again, and then give comments. Until the teacher is satisfied.

这就是一张图的上色过程。而视频是一帧帧画面组成的，给视频上色可以理解为通过这个网络架构给视频里的每一帧上色。不过没有这么简单，毕竟视频一秒钟几十帧，一帧帧上色有点慢，而且每一帧之前可能会出现上色效果不一致。所以有的架构会针对细节调整。例如 DeOldify 采用了 NoGAN（一种新型 GAN 训练模型），用来解决之前 DeOldify 模型中出现的一些关键问题。例如如视频中闪烁的物体

This is the coloring process of a picture. The video is composed of frames, and coloring the video can be understood as coloring each frame in the video through this network architecture. But it is not that simple. After all, the video has dozens of frames per second, and the coloring of one frame is a bit slow, and the coloring effect may be inconsistent before each frame. So some architectures will be adjusted for details. For example, DeOldify uses NoGAN (a new type of GAN training model) to solve some of the key problems in the previous DeOldify model. E.g. flashing objects in the video

一般来说，给人上色会更接近实际情况些。因为人的肤色比较有限，判别器里已经学习过人脸的颜色可能是哪些，转换成灰度图像后对应什么颜色值，所以 AI 不太可能会给黑白的人像涂成绿色脸。

Generally speaking, coloring people will be closer to the actual situation. Because human skin color is relatively limited, the discriminator has already learned what the color of the face may be, and what color value it corresponds to after converting it into a grayscale image, so it is unlikely that AI will paint a black and white portrait with a green face.

 

From website: https://daily.zhihu.com/