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.
Recent advances in Generative AI (GenAI) models [13,9] have reshaped the landscape of digital content creation. These models can now produce highly realistic images [38] and videos [22], enabling the automatic synthesis of humans, environments, and motion sequences with unprecedented fidelity. Despite these achievements, the realistic animation of human motion remains one of the most challenging problems in GenAI [41]. Human perception is highly sensitive to imperfections in the appearance and movement of other humans, triggering an instinctive rejection known as the uncanny valley.
Video GenAI Reference Image Driving Video Visual Fidelity
Fig. 1. Motivation. We examine whether synthetic videos generated through state-of-the-art GenAI animation models successfully preserve the identity-specific behavioral biometric traits (gait). Both visual and biometric fidelity are analyzed in the study.
Besides static realism, maintaining temporal coherence across frames remains a major challenge. Although individual frames can look realistic, inconsistencies in pose transitions or dynamics often lead to unnatural or incoherent motion. Addressing these issues is important both for human perception and for applications that rely on accurate motion.
Even with these difficulties, the potential use of GenAI models extends far beyond entertainment. They can also serve as tools for synthetic data generation and model training [10,34], reducing bias [1,31], or increasing privacy [23,24]. If GenAI models could reliably replicate visual and behavioral patterns from different individuals and transfer them onto diverse visual identities, they could substantially expand existing datasets without the need for costly data acquisition [30,2]. Furthermore, they could enable the creation of animations that not only look realistic but also preserve the consistency and individuality of human behavior [8]. These qualities allow new opportunities for simulation, behavioral analysis, and the development of AI models that rely on human behavioral traits as a source of information.
From this perspective, gait recognition represents a particularly relevant and rigorous test case. Gait is a distinctive behavioral biometric pattern characterized by temporal and spatial cues, like rhythm, stride, and posture, that uniquely identify individuals [19]. This uniqueness, however, introduces a critical security dimension: the potential emergence of behavioral DeepFakes [17,26,34]. If GenAI models can accurately clone these motion signatures, they could compromise biometric security systems that rely on gait, for example, for surveillance or access control. Therefore, determining whether current GenAI models can synthesize deceptive behavioral biometrics is a matter of significant safety interest. As a behavioral trait, gait represents an interesting modality for synthetic generation: realistic enough to train recognition models, yet sensitive enough to reveal the limits of motion fidelity in current GenAI models. Motivated by this, in the present study we analyze how effectively animation models can maintain identity-preserving motion traits in the context of gait synthesis and recognition. With this analysis, we aim to bridge the gap between visual realism and behavioral fidelity in AI-generated human animation, contributing to a deeper understanding of their strengths, limitations, and potential applications. The main contributions of the study are:
-We examine whether state-of-the-art GenAI models can preserve identity-specific motion traits during human animation synthesis. We specifically analyze their ability to reproduce gait-related behavioral information from reference videos and transfer it to visually different identities, as illustrated in Fig 1 .
-We expose a critical limitation in current gait recognition models: our identity transfer task reveals they work mainly as appearance-based Re-Identification models, failing to capture temporal dynamics when texture is disentangled.
The remainder of the paper is organized as follows. Sec. 2 reviews the most relevant literature on synthetic human animation and gait analysis. Next, Sec. 3 details the technical framework, covering the GenAI and gait recognition models, and evaluation metrics. Building on this, Sec. 4 outlines the experimental protocol and introduces two main evaluation tasks comprising four distinct scenarios designed to assess specific capabilities of the animation models and the used datasets. The corresponding results, including both quantitative measures and qualitative observations, are presented in Sec. 5. Finally, Sec. 6 summarizes the main findings and discusses future directions.
This section first reviews state-of-the-art GenAI models for video synthesis, ranging from general video generation to specific human motion synthesis. After that, we discuss gait recognition models, which serve as the benchmarking mechanism in our study to evaluate the biometric fidelity o
This content is AI-processed based on open access ArXiv data.