让图像水印在生成视频后仍能被识别，防伪更可靠。
LoT-Pass: Long-term-robust Image Watermarking for Image to Video Generation
- 用扩散距离衡量水印在视频中随时间的稳定性
- 在开源与商用模型上均显著提升水印鲁棒性
- 适合内容创作者与平台方防范深度伪造
图像引导视频生成（I2V）技术的快速发展引发了虚假信息和欺诈滥用的担忧，亟需有效的数字水印方案。现有水印方法虽在单一模态内表现稳健，但在I2V场景中无法追溯源图像。为此，我们提出“鲁棒扩散距离”概念，用于度量水印信号在生成视频中的时序持久性。基于此，我们设计I2VWM跨模态水印框架，通过训练阶段的视频仿真噪声层和推理阶段的光流对齐模块，增强水印在时间维度上的鲁棒性。在开源与商业I2V模型上的实验表明，I2VWM显著提升了水印的抗破坏能力，同时保持不可感知性，为生成式视频时代的跨模态水印树立了新范式。
原文摘要 · Abstract (English)
The rapid progress of image-guided video generation (I2V) has raised concerns about its potential misuse in misinformation and fraud, underscoring the urgent need for effective digital watermarking. While existing watermarking methods demonstrate robustness within a single modality, they fail to trace source images in I2V settings. To address this gap, we introduce the concept of Robust Diffusion Distance, which measures the temporal persistence of watermark signals in generated videos. Building on this, we propose I2VWM, a cross-modal watermarking framework designed to enhance watermark robustness across time. I2VWM leverages a video-simulation noise layer during training and employs an optical-flow-based alignment module during inference. Experiments on both open-source and commercial I2V models demonstrate that I2VWM significantly improves robustness while maintaining imperceptibility, establishing a new paradigm for cross-modal watermarking in the era of generative video. \href{https://github.com/MrCrims/I2VWM-Robust-Watermarking-for-Image-to-Video-Generation}{Code Released.}
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。