Neural Rigging for Articulated Characters (RigNet)

Hey everyone!

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.

Project: https://zhan-xu.github.io/rig-net/

Paper:https://people.cs.umass.edu/~zhanxu/papers/RigNet.pdf

Code:  https://github.com/zhan-xu/RigNet

Best,

Gonçalo Peres