PGcGAN: Pathological Gait-Conditioned GAN for Human Gait Synthesis

TL;DR

This paper introduces PGcGAN, a novel GAN framework that synthesizes realistic pathological gait sequences conditioned on specific gait impairments, aiding data augmentation and analysis in clinical gait studies.

Contribution

The paper presents a new pathology-conditioned GAN architecture that generates diverse gait sequences from limited clinical data, improving gait analysis and recognition tasks.

Findings

Synthetic gait sequences closely match real data in PCA and t-SNE analyses.

Data augmentation with synthetic sequences improves gait classification accuracy.

The method effectively models six distinct gait impairment categories.

Abstract

Pathological gait analysis is constrained by limited and variable clinical datasets, which restrict the modeling of diverse gait impairments. To address this challenge, we propose a Pathological Gait-conditioned Generative Adversarial Network (PGcGAN) that synthesises pathology-specific gait sequences directly from observed 3D pose keypoint trajectories data. The framework incorporates one-hot encoded pathology labels within both the generator and discriminator, enabling controlled synthesis across six gait categories. The generator adopts a conditional autoencoder architecture trained with adversarial and reconstruction objectives to preserve structural and temporal gait characteristics. Experiments on the Pathological Gait Dataset demonstrate strong alignment between real and synthetic sequences through PCA and t-SNE analyses, visual kinematic inspection, and downstream classification tasks. Augmenting real data with synthetic sequences improved pathological gait recognition across GRU, LSTM, and CNN models, indicating that pathology-conditioned gait synthesis can effectively support data augmentation in pathological gait analysis.