YouTube fills out 3D video capability for user-generated content | News | Rapid TV News
By continuing to use this site you consent to the use of cookies on your device as described in our privacy policy unless you have disabled them. You can change your cookie settings at any time but parts of our site will not function correctly without them. [Close]

YouTube has added automatic 3D conversion for short-form videos uploaded in 1080p.

The functionality is a follow-on from a beta feature that let creators convert YouTube videos into 3D with a click, which has resulted in hundreds of thousands of 3D videos that have been shared. Now, the beta has been rolled out to everyone. Users simply select 3D viewing in the quality settings on the YouTube player.

In terms of the underlying conversion technology, YouTube uses 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. Machine learning from the growing number of true 3D videos on YouTube helps the system 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.

Then, YouTube applies cloud computing scalability to break up a video into tiny chunks of data and process them in parallel.

The process was laid out by Deb Mukherjee, technical staff, and Chen Wu, software engineer, in the official YouTube blog.