Our Blog

Disney Research shows a new robust facial capture system

Mike Seymour wrote an in depth article on FXGuide about an anatomically-constrained local model for monocular face capture that was done by Disney Research in Zurich. See the full article here:

The process takes into account a local deformation subspace, as well as an anatomical bone structure. Through a small set of training shapes it can be constrained to 2D motion data. This method allows for many applications, including high quality motion capture from sparse facial markers or sketch based manipulation from artist input. It can even reconstruct high quality motion capture based on single camera input such as a mobile phone.

The method itself seems to outperform the traditional global blend shape method and is better at tracking the face position correctly. 

The video that explains the process  can be seen here:


 

Tags:

Show Comments (0)

This is a unique website which will require a more modern browser to work! Please upgrade today!