{"ID":2827694,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.16874","arxiv_id":"2512.16874","title":"Pixel Seal: Adversarial-only training for invisible image and video watermarking","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2512.16874","url_pdf":"https://arxiv.org/pdf/2512.16874v1","authors":"[\"Tomáš Souček\",\"Pierre Fernandez\",\"Hady Elsahar\",\"Sylvestre-Alvise Rebuffi\",\"Valeriu Lacatusu\",\"Tuan Tran\",\"Tom Sander\",\"Alexandre Mourachko\"]","published":"2025-12-18T18:42:19Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\",\"cs.CR\",\"cs.LG\"]","methods":"[]","has_code":false}