Leveraging Avatar Fingerprinting: A Multi-Generator Photorealistic Talking-Head Public Database and Benchmark

• URL: http://arxiv.org/abs/2603.26934v1
• Date: Fri, 27 Mar 2026 19:17:16 GMT
• Title: Leveraging Avatar Fingerprinting: A Multi-Generator Photorealistic Talking-Head Public Database and Benchmark
• Abstract summary: Avatar fingerprinting aims to determine whether two avatar videos are driven by the same human operator or not.<n> AVAPrintDB is a new publicly available multi-generator talking-head avatar database.<n> benchmark protocols, and avatar fingerprinting systems are publicly available to facilitate reproducible research.
• Score: 13.166206131594024
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Recent advances in photorealistic avatar generation have enabled highly realistic talking-head avatars, raising security concerns regarding identity impersonation in AI-mediated communication. To advance in this challenging problem, the task of avatar fingerprinting aims to determine whether two avatar videos are driven by the same human operator or not. However, current public databases in the literature are scarce and based solely on old-fashioned talking-head avatar generators, not representing realistic scenarios for the current task of avatar fingerprinting. To overcome this situation, the present article introduces AVAPrintDB, a new publicly available multi-generator talking-head avatar database for avatar fingerprinting. AVAPrintDB is constructed from two audiovisual corpora and three state-of-the-art avatar generators (GAGAvatar, LivePortrait, HunyuanPortrait), representing different synthesis paradigms, and includes both self- and cross-reenactments to simulate legitimate usage and impersonation scenarios. Building on this database, we also define a standardized and reproducible benchmark for avatar fingerprinting, considering public state-of-the-art avatar fingerprinting systems and exploring novel methods based on Foundation Models (DINOv2 and CLIP). Also, we conduct a comprehensive analysis under generator and dataset shift. Our results show that, while identity-related motion cues persist across synthetic avatars, current avatar fingerprinting systems remain highly sensitive to changes in the synthesis pipeline and source domain. The AVAPrintDB, benchmark protocols, and avatar fingerprinting systems are publicly available to facilitate reproducible research.

Related papers

• HumanNOVA: Photorealistic, Universal and Rapid 3D Human Avatar Modeling from a Single Image [84.81016200801153]
  We present HumanNOVA, a photorealistic, universal, and rapid model for generating 3D human avatars from a single RGB image.<n>In terms of the architecture, HumanNOVA adopts a feed-forward, token-conditioned avatar modeling framework that allows fast inference in less than one second.
  arXiv  Detail & Related papers  (2026-06-01T17:58:11Z)
• Is It Really You? Exploring Biometric Verification Scenarios in Photorealistic Talking-Head Avatar Videos [12.12643642515884]
  An attacker can steal a user's avatar, preserving his appearance and voice, making it nearly impossible to detect its usage by sight or sound alone.<n>Our main question is whether an individual's facial motion patterns can serve as reliable behavioral biometrics to verify their identity when the avatar's visual appearance is a facsimile of its owner.<n> Experimental results demonstrate that facial motion landmarks enable meaningful identity verification with AUC values approaching 80%.
  arXiv  Detail & Related papers  (2025-08-01T16:23:27Z)
• SmartAvatar: Text- and Image-Guided Human Avatar Generation with VLM AI Agents [91.26239311240873]
  SmartAvatar is a vision-language-agent-driven framework for generating fully rigged, animation-ready 3D human avatars.<n>A key innovation is an autonomous verification loop, where the agent renders draft avatars.<n>The generated avatars are fully rigged and support pose manipulation with consistent identity and appearance.
  arXiv  Detail & Related papers  (2025-06-05T03:49:01Z)
• EVA: Expressive Virtual Avatars from Multi-view Videos [51.33851869426057]
  We introduce Expressive Virtual Avatars (EVA), an actor-specific, fully controllable, and expressive human avatar framework.<n>EVA achieves high-fidelity, lifelike renderings in real time while enabling independent control of facial expressions, body movements, and hand gestures.<n>This work represents a significant advancement towards fully drivable digital human models.
  arXiv  Detail & Related papers  (2025-05-21T11:22:52Z)
• Traceable AI-driven Avatars Using Multi-factors of Physical World and Metaverse [7.436039179584676]
  Metaverse allows users to delegate their AI models to an AI engine, which builds corresponding AI-driven avatars. In this paper, we propose an authentication method using multi-factors to guarantee the traceability of AI-driven avatars.
  arXiv  Detail & Related papers  (2024-08-30T09:04:11Z)
• GenCA: A Text-conditioned Generative Model for Realistic and Drivable Codec Avatars [44.8290935585746]
  Photo-realistic and controllable 3D avatars are crucial for various applications such as virtual and mixed reality (VR/MR), telepresence, gaming, and film production. Traditional methods for avatar creation often involve time-consuming scanning and reconstruction processes for each avatar. We propose a text-conditioned generative model that can generate photo-realistic facial avatars of diverse identities.
  arXiv  Detail & Related papers  (2024-08-24T21:25:22Z)
• DivAvatar: Diverse 3D Avatar Generation with a Single Prompt [95.9978722953278]
  DivAvatar is a framework that generates diverse avatars from a single text prompt. It has two key designs that help achieve generation diversity and visual quality. Extensive experiments show that DivAvatar is highly versatile in generating avatars of diverse appearances.
  arXiv  Detail & Related papers  (2024-02-27T08:10:31Z)
• GPAvatar: Generalizable and Precise Head Avatar from Image(s) [71.555405205039]
  GPAvatar is a framework that reconstructs 3D head avatars from one or several images in a single forward pass. The proposed method achieves faithful identity reconstruction, precise expression control, and multi-view consistency.
  arXiv  Detail & Related papers  (2024-01-18T18:56:34Z)
• GAIA: Zero-shot Talking Avatar Generation [64.78978434650416]
  We introduce GAIA (Generative AI for Avatar), which eliminates the domain priors in talking avatar generation. GAIA beats previous baseline models in terms of naturalness, diversity, lip-sync quality, and visual quality. It is general and enables different applications like controllable talking avatar generation and text-instructed avatar generation.
  arXiv  Detail & Related papers  (2023-11-26T08:04:43Z)
• Avatar Fingerprinting for Authorized Use of Synthetic Talking-Head Videos [16.717930760451996]
  We term this task avatar fingerprinting. We first introduce a large-scale dataset of real and synthetic videos of people interacting on a video call. We verify the identity driving the expressions in a synthetic video, by learning motion signatures that are independent of the facial appearance shown.
  arXiv  Detail & Related papers  (2023-05-05T17:54:34Z)
• OTAvatar: One-shot Talking Face Avatar with Controllable Tri-plane Rendering [81.55960827071661]
  Controllability, generalizability and efficiency are the major objectives of constructing face avatars represented by neural implicit field. We propose One-shot Talking face Avatar (OTAvatar), which constructs face avatars by a generalized controllable tri-plane rendering solution.
  arXiv  Detail & Related papers  (2023-03-26T09:12:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.