RAW: Robust Avatar Watermarking -- Benchmarking and Baseline

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Parry, Jack, Saunders, Jack, Namboodiri, Vinay
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911710274650112
author Parry, Jack
Saunders, Jack
Namboodiri, Vinay
author_facet Parry, Jack
Saunders, Jack
Namboodiri, Vinay
contents Digital avatar watermarking presents unique challenges: avatars are routinely post-processed with background replacement, reframing, and format conversion before deployment. We introduce \textbf{RAW} (Robust Avatar Watermarking), a benchmark comprising 50 synthetic avatar videos from 5 commercial providers and 6 attacks simulating real-world avatar workflows. Evaluating 7 existing methods reveals that avatar-specific attacks such as background removal significantly degrade watermark recovery. We propose \textbf{WALT} (Watermarking Avatars with Learned Textures), which embeds watermarks in UV texture space via 3D face reconstruction. WALT achieves the highest robustness to zoom attacks (92.4\%) while maintaining strong performance on background removal (95.6\%). We release our benchmark to facilitate research into avatar-specific watermarking.
format Preprint
id arxiv_https___arxiv_org_abs_2605_23994
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle RAW: Robust Avatar Watermarking -- Benchmarking and Baseline
Parry, Jack
Saunders, Jack
Namboodiri, Vinay
Computer Vision and Pattern Recognition
Artificial Intelligence
Digital avatar watermarking presents unique challenges: avatars are routinely post-processed with background replacement, reframing, and format conversion before deployment. We introduce \textbf{RAW} (Robust Avatar Watermarking), a benchmark comprising 50 synthetic avatar videos from 5 commercial providers and 6 attacks simulating real-world avatar workflows. Evaluating 7 existing methods reveals that avatar-specific attacks such as background removal significantly degrade watermark recovery. We propose \textbf{WALT} (Watermarking Avatars with Learned Textures), which embeds watermarks in UV texture space via 3D face reconstruction. WALT achieves the highest robustness to zoom attacks (92.4\%) while maintaining strong performance on background removal (95.6\%). We release our benchmark to facilitate research into avatar-specific watermarking.
title RAW: Robust Avatar Watermarking -- Benchmarking and Baseline
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2605.23994