NAWE: Digital Watermarking with Neural-Assisted Watermark Extraction
Not on the map. Why?
Abstract (arXiv)
NAWE (Neural-Assisted Watermark Extraction) combines an explicit signal-processing watermarking construction with a pretrained neural host predictor. A periodic, perceptually masked watermark carrier provides synchronization, Polar coding supplies redundancy, and denoising followed by subtraction extracts the embedded watermark. The denoiser remains frozen, without watermark-specific training. A one-factor-at-a-time study compares Wiener, BM3D, DRUNet, and GS-DRUNet host estimators. Comparisons with TrustMark, SSL Watermarking, PixelSeal, and WAM show NAWE's lowest geometric and photometric class BER and strong message recovery, while filtering and noise remain limitations consistent with the non-adaptive selection of the watermark extractor. The comparison retains the systems' different payloads and coding.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 7 of its 24 references that are in the map. First posted on arXiv 22 Sep 2026.
Builds on
7 of 24 references.
References · 7
- 2014Microsoft COCO: Common Objects in Contextcited by 17,498
- 2020Plug-and-Play Image Restoration with Deep Denoiser Priorcited by 467
- 2021Watermarking Images in Self-Supervised Latent Spacescited by 90
- 2024WAVES: Benchmarking the Robustness of Image Watermarkscited by 89
- 2023TrustMark: Universal Watermarking for Arbitrary Resolution Imagescited by 50
- 2024Watermark Anything with Localized Messagescited by 49
- 2025Pixel Seal: Adversarial-only training for invisible image and video watermarkingcited by 14
Built on by
Not cited yet.