News for hackers. Stuff that matters.

A comment on Production-Level Facial Capture Using Deep Convolutional Neural Networks. Parent comment

Re:Production-Level Facial Capture Using Deep Convolutional ... by ungaro on Friday August 04, 2017 @05:06AM (#14927336)
how can you play with this without any data?

"The training data used for the deep neural network was generated using Remedy Entertainment’s in-house capture pipeline based on a cutting edge commercial DI4D PRO system [Dimensional Imaging 2016] that employs nine video cameras."

[ Parent | on HN ]
Re:Production-Level Facial Capture Using Deep Convolutional ... by JabavuAdams on Friday August 04, 2017 @09:50AM (#14928619)
There are lots of sources for mocap data if you know people in the film, games, or entertainment industry.
[ Parent | on HN ]
Re:Production-Level Facial Capture Using Deep Convolutional ... by bitL on Friday August 04, 2017 @06:04AM (#14927526)
You can always take tested ideas and apply to your own rig. The pioneering work was done by NVidia already, you see the results and it's up to you how much inspiration can you take from their work.
[ Parent | on HN ]