用生成模型加物理约束，扩充动作捕捉数据并提升精度。
PoseAugment: Generative Human Pose Data Augmentation with Physical Plausibility for IMU-based Motion Capture
- 用变分自编码器生成多样且真实的动作姿态
- 通过物理优化确保动作符合人体运动规律
- 适合需要高质量动作数据的可穿戴设备研究者
基于惯性传感器的人体动作捕捉面临数据稀缺问题，而有效的数据增强极具挑战，因需同时捕捉人体的物理关系与约束，且保持数据分布与质量。我们提出PoseAugment，一个融合变分自编码器（VAE）姿态生成与物理优化的新型流程。给定一组动作序列，VAE模块生成无限数量的高保真、多样化姿态，同时维持原始数据分布；物理模块对生成姿态进行优化，以最小化运动限制满足物理约束。随后从增强的姿态中合成高质量的IMU数据用于训练动作捕捉模型。实验表明，PoseAugment在动作捕捉准确率上优于以往的数据增强与姿态生成方法，展现出缓解基于IMU动作捕捉及相关任务数据采集负担的强大潜力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。