Abstract
Gait patterns play a critical role in human identification and healthcare analytics, yet current progress remains constrained by small, narrowly designed models that fail to scale or generalize. Building a unified gait foundation model requires addressing two longstanding barriers: (a) Scalability. Why have gait models historically failed to follow scaling laws? (b) Generalization. Can one model serve the diverse gait tasks that have traditionally been studied in isolation? We introduce FoundationGait, the first scalable, self-supervised pretraining framework for gait understanding. Its largest version has nearly 0.13 billion parameters and is pretrained on 12 public gait datasets comprising over 2 million walking sequences. Extensive experiments demonstrate that FoundationGait, with or without fine-tuning, performs robustly across a wide spectrum of gait datasets, conditions, tasks (e.g., human identification, scoliosis screening, depression prediction, and attribute estimation), and even input modality. Notably, it achieves 48.0% zero-shot rank-1 accuracy on the challenging in-the-wild Gait3D dataset (1,000 test subjects) and 64.5% on the largest in-the-lab OU-MVLP dataset (5,000+ test subjects), setting a new milestone in robust gait recognition. Coming code and model: this https URL.
Abstract (translated)
步态模式在人类识别和医疗数据分析中扮演着关键角色，然而当前的进展受到小型且设计狭窄的模型限制，这些模型无法扩展或泛化。构建一个统一的步态基础模型需要克服两个长期存在的障碍：（a）可扩展性。为什么步态模型历史上未能遵循规模法则？（b）泛化能力。是否有一种单一模型能够服务于传统上孤立研究的各种步态任务？ 我们介绍了FoundationGait，这是首个用于步态理解的大规模自监督预训练框架。其最大版本包含近0.13亿个参数，并在包括超过200万步行序列的12个公开步态数据集上进行过预训练。 广泛的实验表明，在有或没有微调的情况下，FoundationGait在各种步态数据集、条件、任务（例如人类识别、脊柱侧弯筛查、抑郁症预测和属性估计）以及输入模式下均表现出色。尤为值得注意的是，在具有挑战性的野外环境下的Gait3D数据集中（1,000个测试对象），它实现了48.0%的零样本Rank-1准确率，并在实验室内的OU-MVLP数据集（超过5,000名测试对象）中达到了64.5%，为稳健的步态识别树立了新的里程碑。 代码和模型：请访问此链接 [this https URL] 获取更多信息。
URL
https://arxiv.org/abs/2512.00691
