{"ID":2826099,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.19048","arxiv_id":"2512.19048","title":"WaTeRFlow: Watermark Temporal Robustness via Flow Consistency","abstract":"Image watermarking supports authenticity and provenance, yet many schemes are still easy to bypass with various distortions and powerful generative edits. Deep learning-based watermarking has improved robustness to diffusion-based image editing, but a gap remains when a watermarked image is converted to video by image-to-video (I2V), in which per-frame watermark detection weakens. I2V has quickly advanced from short, jittery clips to multi-second, temporally coherent scenes, and it now serves not only content creation but also world-modeling and simulation workflows, making cross-modal watermark recovery crucial. We present WaTeRFlow, a framework tailored for robustness under I2V. It consists of (i) FUSE (Flow-guided Unified Synthesis Engine), which exposes the encoder-decoder to realistic distortions via instruction-driven edits and a fast video diffusion proxy during training, (ii) optical-flow warping with a Temporal Consistency Loss (TCL) that stabilizes per-frame predictions, and (iii) a semantic preservation loss that maintains the conditioning signal. Experiments across representative I2V models show accurate watermark recovery from frames, with higher first-frame and per-frame bit accuracy and resilience when various distortions are applied before or after video generation.","short_abstract":"Image watermarking supports authenticity and provenance, yet many schemes are still easy to bypass with various distortions and powerful generative edits. Deep learning-based watermarking has improved robustness to diffusion-based image editing, but a gap remains when a watermarked image is converted to video by image-...","url_abs":"https://arxiv.org/abs/2512.19048","url_pdf":"https://arxiv.org/pdf/2512.19048v1","authors":"[\"Utae Jeong\",\"Sumin In\",\"Hyunju Ryu\",\"Jaewan Choi\",\"Feng Yang\",\"Jongheon Jeong\",\"Seungryong Kim\",\"Sangpil Kim\"]","published":"2025-12-22T05:33:59Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}