SkinningNet: Two-Stream Graph Convolutional Neural Network for Skinning Prediction of Synthetic Characters
This addresses the problem of automating skinning in computer graphics for animators, but it is incremental as it builds on existing graph neural network methods.
The paper tackles the problem of predicting skinning weights for synthetic characters from mesh and skeleton inputs without assumptions on shape class or structure, and the result is that SkinningNet outperforms current state-of-the-art alternatives.
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.