视频人体姿态噪声会放大千倍影响关节力矩估计，该研究提出有效抑制方法。
How Noisy Poses Break Inverse Dynamics: Analysis and Mitigation for Video-Based Joint Torque Estimation
- 构建可微分的SMPL动力学模块，实现端到端梯度计算
- 发现姿态噪声经数值微分放大约1000倍，近端关节敏感度是远端10倍
- 前置低通滤波可显著降低噪声放大，适合动作分析与运动康复研究
单目3D人体姿态估计技术已能精确追踪身体运动，但将其转换为物理量（如关节力矩）仍面临挑战，主要因姿态噪声在逆动力学计算中被大幅放大。本文系统分析了姿态估计噪声在逆动力学流程中的传播机制。关键发现包括：(1) 通过数值微分计算关节力矩时，姿态噪声会被放大约1000倍；(2) 近端关节（脊柱、骨盆）对噪声的敏感度最高可达远端关节（手腕、手部）的10倍；(3) 在微分前进行低通滤波可显著缓解噪声放大。为此，本文提出SMPL-Dynamics，一个针对SMPL人体模型的全可微分逆动力学模块，无需外部物理模拟器即可支持端到端梯度计算。实验表明，基于该模块的可微姿态优化可将力矩误差降低93%，而姿态变化极小。
原文摘要 · Abstract (English)
Recent advances in monocular 3D human pose estimation enable accurate body tracking from video. However, translating these kinematic estimates into physical quantities, such as joint torques, remains challenging due to noise amplification through inverse dynamics. In this work, we provide a systematic analysis of how pose estimation noise propagates through the inverse dynamics pipeline. We present three key findings: (1) pose noise is amplified by approximately 1,000x when computing joint torques via numerical differentiation, (2) proximal joints (spine, hips) are up to 10x more sensitive to noise than distal joints (wrists, hands), and (3) low-pass filtering before differentiation substantially reduces this amplification. To enable this analysis, we develop SMPL-Dynamics, a fully differentiable inverse dynamics module for the SMPL body model that requires no external physics simulators. Our module supports end-to-end gradient computation, and we demonstrate this through differentiable pose refinement, which reduces torque error by 93% with negligible change in pose.
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。