paper-with-me

Papers

RAW: Robust Avatar Watermarking -- Benchmarking and Baseline

2026-05-17 · Jack Parry, Jack Saunders, Vinay Namboodiri arxiv

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.

📄 PDF Abstract BibTeX arXiv:2605.23994

Code (0)

등록된 구현이 없습니다.

Tasks

3D Face Reconstruction

Similar Papers 제목 키워드 기반

AudioMarkBench: Benchmarking Robustness of Audio Watermarking

2024-06-11 · Hongbin Liu, Moyang Guo, Zhengyuan Jiang, Lun Wang 외

The increasing realism of synthetic speech, driven by advancements in text-to-speech models, raises ethical concerns regarding impersonation and disinformation. Audio watermarking offers a promising solution via embeddin…

Benchmarkingtext-to-speechText to Speech

From Attack to Protection: Leveraging Watermarking Attack Network for Advanced Add-on Watermarking

2020-08-14 · Seung-Hun Nam, Jihyeon Kang, Daesik Kim, Namhyuk Ahn 외

Multi-bit watermarking (MW) has been designed to enhance resistance against watermarking attacks, such as signal processing operations and geometric distortions. Various benchmark tools exist to assess this robustness th…

Benchmarking

VideoMarkBench: Benchmarking Robustness of Video Watermarking

2025-05-27 · Zhengyuan Jiang, Moyang Guo, Kecen Li, Yuepeng Hu 외

The rapid development of video generative models has led to a surge in highly realistic synthetic videos, raising ethical concerns related to disinformation and copyright infringement. Recently, video watermarking has be…

Benchmarking

VedicTHG: Symbolic Vedic Computation for Low-Resource Talking-Head Generation in Educational Avatars

2026-02-09 · Vineet Kumar Rakesh, Ahana Bhattacharjee, Soumya Mazumdar, Tapas Samanta 외 arxiv

Talking-head avatars are increasingly adopted in educational technology to deliver content with social presence and improved engagement. However, many recent talking-head generation (THG) methods rely on GPU-centric neur…

WaterBench: Towards Holistic Evaluation of Watermarks for Large Language Models

2023-11-13 · Shangqing Tu, Yuliang Sun, Yushi Bai, Jifan Yu 외

To mitigate the potential misuse of large language models (LLMs), recent research has developed watermarking algorithms, which restrict the generation process to leave an invisible trace for watermark detection. Due to t…

BenchmarkingInstruction Following