RAW: Robust AvatarWatermarking - Benchmarking and Baseline

Simple item page
dc.contributor.authorParry, Jack
dc.contributor.authorSaunders, Jack
dc.contributor.authorNamboodiri, Vinay
dc.contributor.editorMusialski, Przemyslaw
dc.contributor.editorLim, Isaak
dc.date.accessioned2026-04-20T08:01:25Z
dc.date.available2026-04-20T08:01:25Z
dc.date.issued2026
dc.description.abstractDigital avatar watermarking presents unique challenges: avatars are routinely post-processed with background replacement, reframing, and format conversion before deployment. We introduce 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 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.
dc.description.sectionheadersFaces, Characters & Human Modeling
dc.description.seriesinformationEurographics 2026 - Short Papers
dc.identifier.doi10.2312/egs.20261006
dc.identifier.isbn978-3-03868-299-8
dc.identifier.issn2309-5059
dc.identifier.pages4 pages
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/egs20261006
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/egs20261006
dc.publisherThe Eurographics Association
dc.rightsCC-BY-4.0
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectDigital rights management
dc.subjectSupervised learning
dc.subjectTexturing
dc.subjectComputer Graphics
dc.titleRAW: Robust AvatarWatermarking - Benchmarking and Baseline
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
egs20261006.pdf
Size:
10.46 MB
Format:
Adobe Portable Document Format
Download
Collections
EG 2026 - Short Papers