PoseAugment: Generative Human Pose Data Augmentation with Physical Plausibility for IMU-based Motion Capture

TL;DR

PoseAugment introduces a VAE-based and physically constrained data augmentation pipeline that generates diverse, physically plausible human poses to improve IMU-based motion capture accuracy, reducing data collection needs.

Contribution

This work presents a novel pose augmentation method combining VAE and physical optimization to generate high-quality, diverse, and physically plausible poses for IMU-based motion capture.

Findings

Outperforms previous augmentation methods in motion capture accuracy

Generates diverse and physically plausible pose data

Reduces data collection burden for IMU-based systems

Abstract

The data scarcity problem is a crucial factor that hampers the model performance of IMU-based human motion capture. However, effective data augmentation for IMU-based motion capture is challenging, since it has to capture the physical relations and constraints of the human body, while maintaining the data distribution and quality. We propose PoseAugment, a novel pipeline incorporating VAE-based pose generation and physical optimization. Given a pose sequence, the VAE module generates infinite poses with both high fidelity and diversity, while keeping the data distribution. The physical module optimizes poses to satisfy physical constraints with minimal motion restrictions. High-quality IMU data are then synthesized from the augmented poses for training motion capture models. Experiments show that PoseAugment outperforms previous data augmentation and pose generation methods in terms of motion capture accuracy, revealing a strong potential of our method to alleviate the data collection burden for IMU-based motion capture and related tasks driven by human poses.