RigNet: neural rigging for articulated characters

RigNet Fig. 1. Given a 3D character mesh, RigNet produces an animation skeleton and skin weights tailored to the articulation structure of the input character. From left to right: input examples of test 3D meshes, predicted skeletons for each of them (joints are shown in green and bones in blue), and resulting skin deformations under different skeletal poses. Please see also our supplementary video: https://youtu.be/J90VETgWIDg

We present RigNet, an end-to-end automated method for producing animation rigs from input character models. 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. Our 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. Our evaluation is three-fold: we show better results than prior art when quantitatively compared to animator rigs; qualitatively we show that our rigs can be expressively posed and animated at multiple levels of detail; and finally, we evaluate the impact of various algorithm choices on our output rigs. 1