How we’re making even more 3D video available on YouTube
Last year we kicked off a beta feature that let creators convert YouTube videos into 3D with a click, and since then you’ve converted hundreds of thousands of your videos to 3D. Today we’re expanding the beta to all of you by adding automatic 3D conversion for short-form videos uploaded in 1080p. Meaning, you can select 3D viewing in the Quality settings (click on the gear icon) on the YouTube player, then pop on your 3D glasses and see YouTube in another dimension. Here’s one of our favorites:
How it works
To give you more dimension on 3D, here’s some background how the conversion technology works at YouTube. Since last September we’ve been constantly improving the underlying technology, which now uses several techniques:
- We use a combination of video characteristics such as color, spatial layout and motion to estimate a depth map for each frame of a monoscopic video sequence
- We use machine learning from the growing number of true 3D videos on YouTube to learn video depth characteristics and apply them in depth estimation
- The generated depth map and the original monoscopic frame create a stereo 3D left-right pair, that a stereo display system needs to display a video as 3D
With this broader knowledge of 3D conversion, we then apply cloud computing scalability to make conversion possible across even more videos on YouTube. Breaking up a video into tiny chunks of data and processing them in parallel on Google’s cloud infrastructure lets us process these videos, while still producing the quality you expect.