Pixel Seal: Adversarial-only training for invisible image and video watermarking
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912774331826176 |
|---|---|
| author | Souček, Tomáš Fernandez, Pierre Elsahar, Hady Rebuffi, Sylvestre-Alvise Lacatusu, Valeriu Tran, Tuan Sander, Tom Mourachko, Alexandre |
| author_facet | Souček, Tomáš Fernandez, Pierre Elsahar, Hady Rebuffi, Sylvestre-Alvise Lacatusu, Valeriu Tran, Tuan Sander, Tom Mourachko, Alexandre |
| contents | Invisible watermarking is essential for tracing the provenance of digital content. However, training state-of-the-art models remains notoriously difficult, with current approaches often struggling to balance robustness against true imperceptibility. This work introduces Pixel Seal, which sets a new state-of-the-art for image and video watermarking. We first identify three fundamental issues of existing methods: (i) the reliance on proxy perceptual losses such as MSE and LPIPS that fail to mimic human perception and result in visible watermark artifacts; (ii) the optimization instability caused by conflicting objectives, which necessitates exhaustive hyperparameter tuning; and (iii) reduced robustness and imperceptibility of watermarks when scaling models to high-resolution images and videos. To overcome these issues, we first propose an adversarial-only training paradigm that eliminates unreliable pixel-wise imperceptibility losses. Second, we introduce a three-stage training schedule that stabilizes convergence by decoupling robustness and imperceptibility. Third, we address the resolution gap via high-resolution adaptation, employing JND-based attenuation and training-time inference simulation to eliminate upscaling artifacts. We thoroughly evaluate the robustness and imperceptibility of Pixel Seal on different image types and across a wide range of transformations, and show clear improvements over the state-of-the-art. We finally demonstrate that the model efficiently adapts to video via temporal watermark pooling, positioning Pixel Seal as a practical and scalable solution for reliable provenance in real-world image and video settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_16874 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Pixel Seal: Adversarial-only training for invisible image and video watermarking Souček, Tomáš Fernandez, Pierre Elsahar, Hady Rebuffi, Sylvestre-Alvise Lacatusu, Valeriu Tran, Tuan Sander, Tom Mourachko, Alexandre Computer Vision and Pattern Recognition Artificial Intelligence Cryptography and Security Machine Learning Invisible watermarking is essential for tracing the provenance of digital content. However, training state-of-the-art models remains notoriously difficult, with current approaches often struggling to balance robustness against true imperceptibility. This work introduces Pixel Seal, which sets a new state-of-the-art for image and video watermarking. We first identify three fundamental issues of existing methods: (i) the reliance on proxy perceptual losses such as MSE and LPIPS that fail to mimic human perception and result in visible watermark artifacts; (ii) the optimization instability caused by conflicting objectives, which necessitates exhaustive hyperparameter tuning; and (iii) reduced robustness and imperceptibility of watermarks when scaling models to high-resolution images and videos. To overcome these issues, we first propose an adversarial-only training paradigm that eliminates unreliable pixel-wise imperceptibility losses. Second, we introduce a three-stage training schedule that stabilizes convergence by decoupling robustness and imperceptibility. Third, we address the resolution gap via high-resolution adaptation, employing JND-based attenuation and training-time inference simulation to eliminate upscaling artifacts. We thoroughly evaluate the robustness and imperceptibility of Pixel Seal on different image types and across a wide range of transformations, and show clear improvements over the state-of-the-art. We finally demonstrate that the model efficiently adapts to video via temporal watermark pooling, positioning Pixel Seal as a practical and scalable solution for reliable provenance in real-world image and video settings. |
| title | Pixel Seal: Adversarial-only training for invisible image and video watermarking |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2512.16874 |