Is Visual Realism Enough? Evaluating Gait Biometric Fidelity in Generative AI Human Animation

TL;DR

This paper evaluates whether state-of-the-art generative AI models can accurately preserve and transfer subtle gait biometrics for person identification, revealing limitations in biometric fidelity despite high visual quality.

Contribution

It introduces a comprehensive evaluation of GenAI human animation models' ability to maintain gait-based biometric identity, highlighting their reliance on appearance over motion cues.

Findings

High visual quality but low biometric fidelity in current models

Models struggle to disentangle identity from appearance in gait transfer

Appearance-based gait recognition is fundamentally flawed when texture is separated from motion

Abstract

Generative AI (GenAI) models have revolutionized animation, enabling the synthesis of humans and motion patterns with remarkable visual fidelity. However, generating truly realistic human animation remains a formidable challenge, where even minor inconsistencies can make a subject appear unnatural. This limitation is particularly critical when AI-generated videos are evaluated for behavioral biometrics, where subtle motion cues that define identity are easily lost or distorted. The present study investigates whether state-of-the-art GenAI human animation models can preserve the subtle spatio-temporal details needed for person identification through gait biometrics. Specifically, we evaluate four different GenAI models across two primary evaluation tasks to assess their ability to i) restore gait patterns from reference videos under varying conditions of complexity, and ii) transfer these gait patterns to different visual identities. Our results show that while visual quality is mostly high, biometric fidelity remains low in tasks focusing on identification, suggesting that current GenAI models struggle to disentangle identity from motion. Furthermore, through an identity transfer task, we expose a fundamental flaw in appearance-based gait recognition: when texture is disentangled from motion, identification collapses, proving current GenAI models rely on visual attributes rather than temporal dynamics.