Neural Rigging for Articulated Characters (RigNet)

2 posts / 0 new
Last post
goncaloperes's picture
Neural Rigging for Articulated Characters (RigNet)

Hey everyone! smiley


Hope you are doing well.

Just found a an end-to-end automated method for producing animation rigs from input character models.  This may save lots of time in character animation.

Given an input 3D model representing an articulated character, RigNet predicts a skeleton that matches the animator expectations in joint placement and topology. It also estimates surface skin weights based on the predicted skeleton.

The method is based on a deep architecture that directly operates on the mesh representation without making assumptions on shape class and structure. The architecture is trained on a large and diverse collection of rigged models, including their mesh, skeletons and corresponding skin weights.







Gonçalo Peres

Public - accessible to all site users
Edited by: goncaloperes on 2020/05/10 - 07:33
babelx3d's picture
The concept looks interesting

The concept looks interesting!

We will look at the code when available.