CA-CGNet: Component-Aware Capsule Graph Neural Network for Non-Rigid Shape Correspondence

Abstract

3D non-rigid shape correspondence is significant but challenging in computer graphics, computer vision, and related fields. Although some deep neural networks have achieved encouraging results in shape correspondence, due to the complexity of the local deformation of non-rigid shapes, the ability of these networks to identify the spatial changes of objects is still insufficient. In this paper, we design a Component-aware Capsule Graph Network (CA-CGNet) to further address the features of embedding space based on the component constraints. Specifically, the dynamic clustering strategy is used to classify the features of patches produced by over-segmentation in order to further reduce noise interference. Moreover, aiming at the problem that existing routing ignores the embedding relationship between capsules, we propose a component-aware capsule graph routing to fully describe the relationship between capsules, which regards capsules as nodes in the graph network and constrains nodes through component information. Then, a knowledge distillation strategy is introduced to improve the convergence speed of the network by decreasing the parameters while maintaining accuracy. Finally, a component pair constraint is added to the functional map, and the component-based semantic loss function is proposed, which can compute isomeric in both direct and symmetric directions. The experimental results show that CA-CGNet improves by 10.21% compared with other methods, indicating the accuracy, generalization, and efficiency of our method on the FAUST, SCAPE, TOSCA, and KIDS datasets.