Facebook’s new AR avatars can mimic a musician’s movements using sound

Facebook has revealed an augmented reality research project that can mimic a musician’s movements.

The company has teamed up with the University of Stanford and the University of Washington on a project called ‘Audio to Body Dynamics.’

The project was revealed at the Computer Vision and Pattern Recognition conference in Salt Lake City, Utah.

The team started this project to see if human movement could be predicted and recreated from music.

Based on some of the animations, it looks like the team still has a ways to go since the finger movements aren’t perfect yet.

The team created an LSTM network that was trained on piano and violin videos on the internet. An LTSM network is part of a neural network.

The team stated that they’re trying to get closer to reproducing the exact finger movements of a real musician, but this is all they have so far.

This technology is really interesting to think about. It could have a lot of other uses in the future specifically in video games where developers could use similar technologies to make non-playable characters move more realistically.

Source: YouTube Via: Engadget

The post Facebook’s new AR avatars can mimic a musician’s movements using sound appeared first on MobileSyrup.

from MobileSyrup https://ift.tt/2MLFUXX