SynthGait-19K是一个用于步态参数估计的物理合成视频数据集，包含19,272个由6,427个MoCap序列生成的行走视频，覆盖437个受试者。该数据集旨在解决现有步态数据集规模小、视角受限和视觉多样性有限的问题。
要点：
1. SynthGait-19K包含19,272个行走视频，由6,427个MoCap序列生成，覆盖437个受试者。
2. 数据集通过Gait2Vid工具构建，该工具利用SMPL统一不同MoCap记录，并在可控视角和场景外观下合成RGB行走视频。
3. 数据集验证了生成的视频与条件步态运动学的一致性，并验证了提取的步态事件与力平台测量的准确性。
4. 使用SynthGait-19K对直接RGB、姿态基础、生物力学和人类网格恢复方法进行了基准测试，并分析了视角、训练数据规模和合成到真实域的转移。
5. 引入GaitXFormer作为直接RGB参考模型，用于估计步态参数，并发现合成监督在GaitXFormer和基于姿态的架构中有效转移，证明了其在不同表示中的实用性。
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.
原始发布方：HuggingFace Daily Papers（社区热门论文）
原文时间：2026-09-08 08:00:00 +08:00
