发表机构
KITE Research Institute; University of Toronto; Vector Institute; University of Bristol; Kiel University（KITE研究所; 多伦多大学; 矢量研究所; 布里斯托大学; 基尔大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有步态数据集规模小、视角受限的问题，提出物理基础合成数据集SynthGait-19K及Gait2Vid生成方法，并引入GaitXFormer模型，验证了合成监督可有效迁移至真实视频，且发现空间参数对域偏移更敏感。
AI 中文摘要
从单目视频中准确估计具有临床意义的步态参数对于可扩展的移动能力评估至关重要，然而现有数据集规模小、视角受限且视觉多样性有限，制约了该领域的进展。我们提出了SynthGait-19K，一个具有物理基础的合成视频数据集，包含来自437名受试者的6,427个MoCap序列导出的19,272个行走视频，并配有配对的SMPL运动和六个步态参数的标注。为构建该数据集，我们开发了Gait2Vid，它通过SMPL统一异构的MoCap记录，并在可控视角和场景外观下合成多样化的RGB行走视频。我们评估生成的视频与其条件步态运动学的一致性，并针对力台测量验证提取的步态事件。利用SynthGait-19K，我们对直接RGB、基于姿态、生物力学和人体网格重建方法进行基准测试，并分析视角、训练数据规模以及合成到真实的域偏移。我们还引入了GaitXFormer作为直接估计步态参数的RGB参考模型。合成监督在GaitXFormer和基于姿态的架构上均能有效迁移到真实视频，展示了在不同表示上的实用性。我们进一步发现，空间步态参数对视觉域偏移更敏感，且改进的HMR重建本身并不一定能转化为下游步态估计的改进。
英文摘要
Accurate estimation of clinically meaningful gait parameters from monocular video is important for scalable mobility assessment, yet progress is limited by the small scale, restricted viewpoints, and limited visual diversity of existing datasets. We introduce SynthGait-19k, a physically grounded synthetic video dataset containing 19,272 walking videos derived from 6,427 MoCap sequences across 437 subjects, with paired SMPL motion and annotations for six gait parameters. To construct the dataset, we develop Gait2Vid, which unifies heterogeneous MoCap recordings through SMPL and synthesizes diverse RGB walking videos under controllable viewpoints and scene appearances. We assess the generated videos for consistency with their conditioning gait kinematics and validate extracted gait events against force-platform measurements. Using SynthGait-19K, we benchmark direct RGB, pose-based, biomechanical, and human-mesh-recovery approaches and analyze viewpoint, training-data scale, and synthetic-to-real domain shift. We also introduce GaitXFormer as a direct RGB reference model for estimating gait parameters. Synthetic supervision transfers effectively to real videos across both GaitXFormer and a pose-based architecture, demonstrating utility across different representations. We further find that spatial gait parameters are more sensitive to visual domain shift and that improved HMR reconstruction alone does not necessarily translate to improved downstream gait estimation.
CommentsProject Page: https://soroushmehraban.github.io/SynthGait-19k/
