WaTeRFlow: Watermark Temporal Robustness via Flow Consistency
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_ | 1866912782002159616 |
|---|---|
| author | Jeong, Utae In, Sumin Ryu, Hyunju Choi, Jaewan Yang, Feng Jeong, Jongheon Kim, Seungryong Kim, Sangpil |
| author_facet | Jeong, Utae In, Sumin Ryu, Hyunju Choi, Jaewan Yang, Feng Jeong, Jongheon Kim, Seungryong Kim, Sangpil |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_19048 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | WaTeRFlow: Watermark Temporal Robustness via Flow Consistency Jeong, Utae In, Sumin Ryu, Hyunju Choi, Jaewan Yang, Feng Jeong, Jongheon Kim, Seungryong Kim, Sangpil Computer Vision and Pattern Recognition 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. |
| title | WaTeRFlow: Watermark Temporal Robustness via Flow Consistency |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.19048 |