Silhouette-based Gait Foundation Model

TL;DR

FoundationGait introduces a scalable, self-supervised pretraining framework for gait analysis, enabling robust performance across diverse datasets, tasks, and modalities, and achieving new benchmarks in gait recognition accuracy.

Contribution

It presents the first scalable, self-supervised gait foundation model that generalizes across multiple tasks and datasets, addressing previous limitations in scalability and task diversity.

Findings

Achieves 48.0% zero-shot rank-1 accuracy on Gait3D

Achieves 64.5% accuracy on OU-MVLP dataset

Demonstrates robustness across various gait tasks and conditions

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: https://github.com/ShiqiYu/OpenGait.