Contemporary approaches to solving various problems that require analyzing three-dimensional (3D) meshes and point clouds have adopted the use of deep learning algorithms that directly process 3D data such as point coordinates, normal vectors and vertex connectivity information. Our work proposes one such solution to the problem of positioning body and finger animation skeleton joints within 3D models of human bodies. Due to scarcity of annotated real human scans, we resort to generating synthetic samples while varying their shape and pose parameters. Similarly to the state-of-the-art approach, our method computes each joint location as a convex combination of input points. Given only a list of point coordinates and normal vector estimates as input, a dynamic graph convolutional neural network is used to predict the coefficients of the convex combinations. By comparing our method with the state-of-the-art, we show that it is possible to achieve significantly better results with a simpler architecture, especially for finger joints. Since our solution requires fewer precomputed features, it also allows for shorter processing times.

翻译：当代解决各类需分析三维网格与点云问题的方法已普遍采用深度学习算法，这些算法直接处理三维数据，如点坐标、法向量和顶点连接信息。本研究针对三维人体模型中身体与手指动画骨骼关节的定位问题，提出了一种基于此类技术的解决方案。由于带标注的真实人体扫描数据稀缺，我们通过生成合成样本并改变其形状与姿态参数来解决此问题。与现有先进方法类似，我们的方法将每个关节位置计算为输入点的凸组合。仅以点坐标列表和法向量估计值作为输入，采用动态图卷积神经网络预测凸组合的系数。通过与现有最优方法的比较，我们证明采用更简洁的网络架构即可取得显著更优的结果，尤其在手指关节定位方面。由于本方案所需预计算特征更少，还能实现更短的处理时间。