mlsanityData to 14 Oct 2026

RAW: Robust Avatar Watermarking -- Benchmarking and Baseline

arXiv 2605.23994 ↗First posted 17 May 2026cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Digital 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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 11 of its 22 references that are in the map. First posted on arXiv 17 May 2026.

Builds on

11 of 22 references.

References · 11

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2020Learning an Animatable Detailed 3D Face Model from In-The-Wild Imagescited by 477
  4. 2018HiDDeN: Hiding Data With Deep Networkscited by 397
  5. 2022EMOCA: Emotion Driven Monocular Face Capture and Animationcited by 255
  6. 2021MBRS : Enhancing Robustness of DNN-based Watermarking by Mini-Batch of Real and Simulated JPEG Compressioncited by 110
  7. 2024Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advancescited by 110
  8. 2022Towards Blind Watermarking: Combining Invertible and Non-invertible Mechanismscited by 61
  9. 2023RoSteALS: Robust Steganography using Autoencoder Latent Spacecited by 57
  10. 2024Watermark Anything with Localized Messagescited by 53
  11. 2024Video Seal: Open and Efficient Video Watermarkingcited by 48

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025VideoMarkBench: Benchmarking Robustness of Video Watermarking
  2. 2026RecoverMark: Robust Watermarking for Localization and Recovery of Manipulated Faces
  3. 2025RobustSora: De-Watermarked Benchmark for Robust AI-Generated Video Detection
  4. 2026WARP: A Unified Benchmark for Invisible Image Watermarking -- Robustness and Protection Against Attacks
  5. 2026What Breaks Local Watermarks? A Robustness Benchmark for Local Invisible Image Watermarking
  6. 2021Deep 3D-to-2D Watermarking: Embedding Messages in 3D Meshes and Extracting Them from 2D Renderings
  7. 2026High-Fidelity Face Content Recovery via Tamper-Resilient Versatile Watermarking
  8. 2025WaTeRFlow: Watermark Temporal Robustness via Flow Consistency