Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.12667 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912598014820352 |
|---|---|
| author | Su, Zihan Qiu, Xuerui Xu, Hongbin Jiang, Tangyu Zhuang, Junhao Yuan, Chun Li, Ming He, Shengfeng Yu, Fei Richard |
| author_facet | Su, Zihan Qiu, Xuerui Xu, Hongbin Jiang, Tangyu Zhuang, Junhao Yuan, Chun Li, Ming He, Shengfeng Yu, Fei Richard |
| contents | The explosive growth of generative video models has amplified the demand for reliable copyright preservation of AI-generated content. Despite its popularity in image synthesis, invisible generative watermarking remains largely underexplored in video generation. To address this gap, we propose Safe-Sora, the first framework to embed graphical watermarks directly into the video generation process. Motivated by the observation that watermarking performance is closely tied to the visual similarity between the watermark and cover content, we introduce a hierarchical coarse-to-fine adaptive matching mechanism. Specifically, the watermark image is divided into patches, each assigned to the most visually similar video frame, and further localized to the optimal spatial region for seamless embedding. To enable spatiotemporal fusion of watermark patches across video frames, we develop a 3D wavelet transform-enhanced Mamba architecture with a novel spatiotemporal local scanning strategy, effectively modeling long-range dependencies during watermark embedding and retrieval. To the best of our knowledge, this is the first attempt to apply state space models to watermarking, opening new avenues for efficient and robust watermark protection. Extensive experiments demonstrate that Safe-Sora achieves state-of-the-art performance in terms of video quality, watermark fidelity, and robustness, which is largely attributed to our proposals. Code is publicly available at https://github.com/Sugewud/Safe-Sora |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_12667 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarking Su, Zihan Qiu, Xuerui Xu, Hongbin Jiang, Tangyu Zhuang, Junhao Yuan, Chun Li, Ming He, Shengfeng Yu, Fei Richard Computer Vision and Pattern Recognition The explosive growth of generative video models has amplified the demand for reliable copyright preservation of AI-generated content. Despite its popularity in image synthesis, invisible generative watermarking remains largely underexplored in video generation. To address this gap, we propose Safe-Sora, the first framework to embed graphical watermarks directly into the video generation process. Motivated by the observation that watermarking performance is closely tied to the visual similarity between the watermark and cover content, we introduce a hierarchical coarse-to-fine adaptive matching mechanism. Specifically, the watermark image is divided into patches, each assigned to the most visually similar video frame, and further localized to the optimal spatial region for seamless embedding. To enable spatiotemporal fusion of watermark patches across video frames, we develop a 3D wavelet transform-enhanced Mamba architecture with a novel spatiotemporal local scanning strategy, effectively modeling long-range dependencies during watermark embedding and retrieval. To the best of our knowledge, this is the first attempt to apply state space models to watermarking, opening new avenues for efficient and robust watermark protection. Extensive experiments demonstrate that Safe-Sora achieves state-of-the-art performance in terms of video quality, watermark fidelity, and robustness, which is largely attributed to our proposals. Code is publicly available at https://github.com/Sugewud/Safe-Sora |
| title | Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarking |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.12667 |