跳到正文
arXiv cs.AI· Joonwoo Kwon, Yufei Zhang, Xiaoming Liu, Zijun Cui·· 23 小时前AI 评分27

ForceBody:带扭矩不确定性的力配对参数化人体运动数据集

ForceBody: Force-Paired Parametric Body Motion with Torque Uncertainty

AI 导读

ForceBody 是首个将真实力监督引入参数化人体表示的数据集,并为每个样本提供扭矩不确定性标注。它把 SKEL 人体模型与地面反作用力、逆动力学关节扭矩配对,覆盖 140 名受试者的 10,386 次运动试验(9.7M 帧、26.9 小时),扭矩标签经蒙特卡洛采样附带逐帧逐关节不确定性。

正文 · 原文

View PDF HTML (experimental)

Abstract:Forces and torques drive human motion, central to biomechanics, robotics, and physics-aware animation, yet they are often absent from learning-based motion pipelines for body reconstruction and generation. Some motion datasets provide force annotations, but the paired motion sequences are incompatible with the parametric body models used in modern learning pipelines. In addition, existing datasets typically obtain joint torques through inverse dynamics, which is inherently sensitive to the quality of the input kinematics; however, they do not quantify the reliability of these torque estimates. We close this gap with ForceBody, the first dataset to bring ground truth force supervision into a parametric body representation, shipped with per-sample torque uncertainty. ForceBody pairs the SKEL body model with ground reaction forces and inverse-dynamics joint torques across 10,386 motion trials (9.7M frames, 26.9 hours) from 140 subjects. Each torque label is paired with a per-frame, per-joint uncertainty annotation obtained by Monte Carlo sampling through the inverse dynamics pipeline. We benchmark six architectures (MLP, Conv1D, LSTM, GRU, Mamba2, Transformer) on ground reaction force and joint torque prediction from SKEL motion. As one example use of the released uncertainty, finetuning a Transformer with per-sample uncertainty weighting reduces the MAE of joint torque estimation by 5%. Code and data are at this https URL.
Comments: Accepted at NeurIPS 2026 Evaluations & Datasets Track
Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
Cite as: arXiv:2611.22769 [cs.CV]
  (or arXiv:2611.22769v1 [cs.CV] for this version)
  https://doi.org/10.48550/arXiv.2611.22769

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Joonwoo Kwon [view email]
[v1] Tue, 17 Nov 2026 13:35:10 UTC (40,115 KB)

来源:arXiv cs.AI · arxiv.org