利用自然人体动作自动校准摄像头外参，精度达亚像素级。
RPGD: RANSAC-P3P Gradient Descent for Extrinsic Calibration in 3D Human Pose Estimation
- 先用RANSAC-P3P粗略估计，再用梯度下降精细优化。
- 在三个公开数据集和自采数据上均实现亚像素级重投影误差。
- 无需人工标记，适合大规模3D人体姿态数据采集场景。
本文提出RPGD（RANSAC-P3P Gradient Descent）框架，一种由人体姿态驱动的外参标定方法，仅通过自然人体运动即可将基于动捕的3D骨骼数据与单目或多视角RGB相机精确对齐。RPGD将外参标定建模为从粗到精的问题，融合RANSAC-P3P的全局鲁棒性与梯度下降的精细优化能力。我们在三个大规模公开3D人体姿态估计（3D HPE）数据集及一个自采集的真实场景数据集上评估该方法。实验表明，RPGD能稳定恢复接近真实值的外参参数，在复杂噪声环境下仍可实现亚像素级的平均关键点定位误差（MPJPE）重投影误差。结果证明RPGD为大规模3D HPE数据集采集提供了实用且全自动的可靠外参标定方案。
原文摘要 · Abstract (English)
In this paper, we propose RPGD (RANSAC-P3P Gradient Descent), a human-pose-driven extrinsic calibration framework that robustly aligns MoCap-based 3D skeletal data with monocular or multi-view RGB cameras using only natural human motion. RPGD formulates extrinsic calibration as a coarse-to-fine problem tailored to human poses, combining the global robustness of RANSAC-P3P with Gradient-Descent-based refinement. We evaluate RPGD on three large-scale public 3D HPE datasets as well as on a self-collected in-the-wild dataset. Experimental results demonstrate that RPGD consistently recovers extrinsic parameters with accuracy comparable to the provided ground truth, achieving sub-pixel MPJPE reprojection error even in challenging, noisy settings. These results indicate that RPGD provides a practical and automatic solution for reliable extrinsic calibration of large-scale 3D HPE dataset collection.
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。