Learning Localization of Body and Finger Animation Skeleton Joints on Three-Dimensional Models of Human Bodies

TL;DR

This paper introduces a deep learning method for accurately localizing body and finger joints in 3D human models, using synthetic data and a simpler neural network architecture to improve efficiency and accuracy.

Contribution

It presents a novel approach that uses a dynamic graph convolutional neural network to predict joint positions from 3D point data, outperforming existing methods especially for finger joints.

Findings

Achieved better joint localization accuracy than state-of-the-art methods.

Reduced processing time due to fewer precomputed features.

Effective use of synthetic data to train the model.

Abstract

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.