From Methods to Applications: A Review of Deep 3D Human Motion Capture

Motion capture technology is crucial in various applications like animation, virtual reality and sports analysis. With the development of deep learning methods, significant progress has been experienced in this field, producing cost-effective and user-friendly solutions for various applications. This paper provides a comprehensive review of deep learning-based human motion capture techniques. Our review aims to bridge the gap between academic research and practical applications, providing valuable insights and guidance for researchers and practitioners in deep learning-based human motion capture. Our study puts forth a new application-oriented taxonomy that comprehensively summarises five fundamental routes of motion capture technology. In addition to that, we also delve into the research priorities linked with each route, following the structure of “hardware requirements - technical routes - datasets - evaluation metrics” and extending the necessary criteria for transferring traditional motion capture systems to deep learning-based ones. Meanwhile, for the motion capture technology, the current state of the art is reviewed, the challenges are identified, and the future directions of the research are outlined.

I. Introduction

Human motion capture has been an essential and active research topic for years. For instance, motion capture widely used in human-computer interaction [1], virtual reality and extended reality environments [2], [3], creative industries and fashion [4], animation generation [5], medicine and psychology [6], robotics and autonomous driving [7], and video monitoring and security [8]. It enables the accurate recording and analysis of human movements, facilitating the creation of realistic animation, the performance evaluation and human-computer interaction. Traditional motion capture systems, such as marker-based and markerless optical systems, have shown remarkable results but suffer from certain limitations like high cost, complex setup and dependency on controlled environments. In recent years, deep learning has emerged as a promising solution to overcome the limitations of traditional methods, enabling more accessible, flexible, and efficient motion capture systems.