SkinningNet: Two-Stream Graph Convolutional Neural Network for Skinning Prediction of Synthetic Characters

TL;DR

SkinningNet is an innovative end-to-end two-stream graph neural network that predicts skinning weights for synthetic characters, effectively handling diverse mesh topologies without prior assumptions.

Contribution

The paper introduces SkinningNet, a novel architecture that jointly learns mesh-skeleton relationships using multi-aggregator graph convolutions, surpassing existing methods.

Findings

Outperforms current state-of-the-art skinning methods

Effectively generalizes to unseen mesh topologies

Demonstrates superior accuracy in skinning weight prediction

Abstract

This work presents SkinningNet, an end-to-end Two-Stream Graph Neural Network architecture that computes skinning weights from an input mesh and its associated skeleton, without making any assumptions on shape class and structure of the provided mesh. Whereas previous methods pre-compute handcrafted features that relate the mesh and the skeleton or assume a fixed topology of the skeleton, the proposed method extracts this information in an end-to-end learnable fashion by jointly learning the best relationship between mesh vertices and skeleton joints. The proposed method exploits the benefits of the novel Multi-Aggregator Graph Convolution that combines the results of different aggregators during the summarizing step of the Message-Passing scheme, helping the operation to generalize for unseen topologies. Experimental results demonstrate the effectiveness of the contributions of our novel architecture, with SkinningNet outperforming current state-of-the-art alternatives.