The scene completion part means that from this highly incomplete depth information, the algorithm reconstructs the geometry for the entirety of the room.

场景补全的意思是可以从这张大量信息缺失的深度图中还原出房间的完整景象。

So our brains use these strange shapes to infer depth information, which in our rectilinear world is almost always correct.

因此, 我们的大脑使用这些奇怪的形状来推断深度信息。在我们的直线世界中，这几乎总是正确的。

So in my case, I could take the depth information and the texture detail from my 3D scans and use it to literally reskin reality.

以我自己的情况为例，我可以使用 3D 扫描的深度和材质信息为现实世界重新涂装。

It took scientists a while to realize that having two eyes gives us depth information, because it’s not the only depth cue that we have.

科学家们花了一段时间才意识到， 拥有两只眼睛可以为我们提供深度信息，因为它不是我们拥有的唯一深度线索。

Here, the input is a bunch of RGB-D images, which are photographs endowed with depth information, and the output can be a full 3D reconstruction of a scene, and much, much more, which we'll see in a moment.

这里输入的是一些 RGB-D 图片，即携带深度信息的照片，而我们得到的输出会是一个场景的全三维重建以及很多很多其他的东西，这些我们待会将看到。

Using machine learning, we can detect when there's a person in the frame and capture rich depth information automatically, so you can turn it into a stunning portrait right away or later on in the Photos app.

使用机器学习， 我们可以检测画面中何时有人， 并自动捕获丰富的深度信息，因此您可以立即或稍后在“照片” 应用程序中将其变成令人惊叹的肖像。