BarbieGait: An Identity-Consistent Synthetic Human Dataset with Versatile Cloth-Changing for Gait Recognition

2026-04-13

AI Summary

This work addresses the performance degradation in gait recognition caused by clothing diversity in real-world scenarios by introducing BarbieGait, the first large-scale, controllable synthetic gait dataset with identity-consistent clothing variations. By mapping real individuals into a virtual engine, the dataset preserves gait identity while simulating a rich array of clothing changes. Building upon this resource, the authors propose GaitCLIF, a model specifically designed to learn clothing-invariant gait features. Extensive experiments demonstrate that the proposed approach significantly improves cross-clothing gait recognition performance on both BarbieGait and several mainstream gait benchmarks, thereby validating the effectiveness and novelty of the synthetic data generation strategy and the clothing-invariant feature learning framework.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Web Mining and Content Analysis: Web data generation and simulation

Abstract

Gait recognition, as a reliable biometric technology, has seen rapid development in recent years while it faces significant challenges caused by diverse clothing styles in the real world. This paper introduces BarbieGait, a synthetic gait dataset where real-world subjects are uniquely mapped into a virtual engine to simulate extensive clothing changes while preserving their gait identity information. As a pioneering work, BarbieGait provides a controllable gait data generation method, enabling the production of large datasets to validate cross-clothing issues that are difficult to verify with real-world data. However, the diversity of clothing increases intra-class variance and makes one of the biggest challenges to learning cloth-invariant features under varying clothing conditions. Therefore, we propose GaitCLIF (Gait-oriented CLoth-Invariant Feature) as a robust baseline model for cross-clothing gait recognition. Through extensive experiments, we validate that our method significantly improves cross-clothing performance on BarbieGait and the existing popular gait benchmarks. We believe that BarbieGait, with its extensive cross-clothing gait data, will further advance the capabilities of gait recognition in cross-clothing scenarios and promote progress in related research.

Problem

• gait recognition
• clothing variation
• cloth-invariant features
• cross-clothing
• biometric technology

Innovation

• synthetic gait dataset
• cloth-changing simulation
• identity-consistent generation
• cloth-invariant features
• gait recognition