Research map / Video / Video generation
SIGMark: Scalable In-Generation Watermark with Blind Extraction for Video Diffusion
Xinjie zhu, Zijing Zhao, Hui Jin, Qingxiao Guo, Yilong Ma, YUNHAO WANG, Xiaobing Guo, Weifeng Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use GF-PRC instead of single PRC (ablation) | SIGMark · HunyuanVideo I2V ablation | bit accuracy: 0.707 -> 0.905 | Improved |
| add SGO module (ablation) | SIGMark · HunyuanVideo I2V ablation | bit accuracy: 0.534 -> 0.869 | Improved |
| add optical flow segmentation (ablation) | SIGMark · HunyuanVideo I2V ablation | bit accuracy: 0.762 -> 0.869 | Improved |
| add sliding-window detection (ablation) | SIGMark · HunyuanVideo I2V ablation | bit accuracy: 0.823 -> 0.869 | Improved |
| SIGMark vs VideoMark under frame drop | in-generation watermark · HunyuanVideo I2V temporal disturbance | bit accuracy: 0.52 -> 0.81 | Improved |
| SIGMark vs VideoShield under clip | in-generation watermark · HunyuanVideo I2V temporal disturbance | bit accuracy: 0.83 -> 0.85 | No clear effect |
| SIGMark vs VideoShield under Gaussian noise | in-generation watermark · HunyuanVideo I2V spatial disturbance | bit accuracy: 1.00 -> 0.89 | Hurt |
| in-generation instead of post-processing watermark (V-score) | video watermarking · HunyuanVideo I2V VBench-2.0 | V-score: 0.456 -> 0.488 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- VideoShield — VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking (ICLR 2025) · better on 2 of 9 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking (ICLR 2025 · similarity 0.90)
- T2SMark: Balancing Robustness and Diversity in Noise-as-Watermark for Diffusion Models (NeurIPS 2025 · similarity 0.89)
- Shallow Diffuse: Robust and Invisible Watermarking through Low-Dim Subspaces in Diffusion Models (NeurIPS 2025 · similarity 0.88)
- Hidden in the Noise: Two-Stage Robust Watermarking for Images (ICLR 2025 · similarity 0.87)
- Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarking (NeurIPS 2025 · similarity 0.87)
- BitMark: Watermarking Bitwise Autoregressive Image Generative Models (NeurIPS 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
