{
  "paper_id": "9fb794ef27d06a8081383ad402d817c5",
  "paper_title": "LiDAR-aid Inertial Poser: Large-scale Human Motion Capture by Sparse Inertial and LiDAR Sensors",
  "paper_authors": [
    "Yiming Ren",
    "Chengfeng Zhao",
    "Yannan He",
    "Peishan Cong",
    "Han Liang",
    "Jingyi Yu",
    "Lan Xu",
    "Yuexin Ma"
  ],
  "publication_date": "",
  "publication_venue": "IEEE Transactions on Visualization and Computer Graphics",
  "abstract": "We propose a multi-sensor fusion method for capturing challenging 3D human motions with accurate consecutive local poses and global trajectories in large-scale scenarios, only using single LiDAR and 4 IMUs, which are set up conveniently and worn lightly. Specifically, to fully utilize the global geometry information captured by LiDAR and local dynamic motions captured by IMUs, we design a two-stage pose estimator in a coarse-to-fine manner, where point clouds provide the coarse body shape and IMU measurements optimize the local actions. Furthermore, considering the translation deviation caused by the view-dependent partial point cloud, we propose a pose-guided translation corrector. It predicts the offset between captured points and the real root locations, which makes the consecutive movements and trajectories more precise and natural. Moreover, we collect a LiDAR-IMU multi-modal mocap dataset, LIPD, with diverse human actions in long-range scenarios. Extensive quantitative and qualitative experiments on LIPD and other open datasets all demonstrate the capability of our approach for compelling motion capture in large-scale scenarios, which outperforms other methods by an obvious margin. We will release our code and captured dataset to stimulate future research.",
  "keywords": [
    "Human motion capture",
    "shape modeling",
    "virtual reality",
    "sensor fusion"
  ],
  "paper_institutions": [],
  "output_language": "zh",
  "provider": "doubao",
  "model": "ark-code-latest",
  "prompt_template": "simple",
  "extracted_at": "2026-08-16T19:47:14.727424Z",
  "template_tag": "simple",
  "summary": "### 摘要\n本论文提出了一种名为LiDAR-aid Inertial Poser（LIP）的多传感器融合方法，用于在大规模场景中精确捕捉具有挑战性的3D人体运动，包括局部姿态和全局轨迹。该方法仅使用一台LiDAR和四个IMU传感器，轻便且易于部署。针对LiDAR点云提供的全局几何信息与IMU提供的局部动态信息，设计了由粗到精的两阶段姿态估计器：第一阶段从点云中提取粗骨骼和根朝向，第二阶段融合IMU测量细化关节位置并通过IK求解关节旋转。同时，为解决视点相关部分点云引起的平移偏差，提出姿态引导的平移校正模块，学习点云中心与真实根位置之间的偏移。此外，论文收集了首个LiDAR-IMU多模态动作捕捉数据集LIPD，包含多样化的运动和大范围场景。实验在LIPD及其他公开数据集上进行，定量和定性结果均表明LIP在精度上显著优于现有方法，验证了其在大型场景中动作捕捉的有效性。\n\n### 关键要点\n- 提出首个仅用单LiDAR和4个IMU的多模态人体动作捕捉方法，实现大规模场景中的高精度局部姿态与全局轨迹估计。\n- 设计两阶段粗到细姿态估计模块：第一阶段用PointNet-GRU从点云回归粗关节和根朝向，第二阶段融合IMU数据通过关节映射估计器和逆运动学求解器细化姿态。\n- 引入姿态引导的平移校正模块，学习点云平均位置与真实根坐标之间的偏移，消除视点导致的平移偏差，提升轨迹自然性和准确性。\n- 构建LIPD数据集，包含15名表演者、约30种动作、62341帧真实点云和IMU数据，并提供SMPL参数和RGB图像，支持大规模场景下的多模态研究。\n- 在TotalCapture、DIP-IMU、LiDARHuman26M及LIPD上，LIP的MPJPE、Mesh Err、Ang Err和CD指标均优于LiDARCap和TransPose，例如在LIPD上MPJPE降低至48.9mm，CD降至3.2cm。\n- 消融实验验证了粗到细融合策略优于直接数据级或特征级融合，且关节映射估计器（JE）和姿态引导（PG）模块均显著提升精度。\n- 输入配置实验表明，LiDAR+4 IMU在轻量性（比12 IMU少8个传感器）与精度（比纯LiDAR低10mm MPJPE）之间达到最佳平衡。\n- 方法对LiDAR种类（如RS-LiDAR-M1、OUSTER-0/1）和IMU（如Xsens Dot、Noitom）具有泛化能力，且在6-25米距离范围内表现稳定。\n- 当前局限在于LiDAR帧率较低（10fps），导致极快运动时结果不平滑，未来计划引入Transformer插值或更高帧率传感器优化。\n- 该工作可应用于VR/AR、游戏、影视制作等场景，支持大规模表演的虚拟化身驱动，并已开源代码和数据集以促进后续研究。"
}