WaTeRFlow：通过流一致性实现水印时间鲁棒性
WaTeRFlow: Watermark Temporal Robustness via Flow Consistency
AI总结：
WaTeRFlow通过流一致性提升I2V场景下的水印鲁棒性，结合FUSE引擎、时间一致性损失和语义保持损失，实现跨模态水印恢复。
摘要：
图像水印支持真实性与来源，但许多方案仍然容易被各种失真和强大的生成编辑所绕过。基于深度学习的水印技术提高了对基于扩散的图像编辑的鲁棒性，但在将水印图像转换为视频时，图像到视频（I2V）转换中每帧水印检测会减弱。I2V已从短而抖动的片段迅速发展到多秒、时间一致的场景，并且现在不仅用于内容创作，还用于世界建模和模拟流程，使跨模态水印恢复变得至关重要。我们提出了WaTeRFlow，一个专为I2V鲁棒性设计的框架。它包括（i）FUSE（流引导统一合成引擎），通过指令驱动编辑和快速视频扩散代理在训练过程中使编码器-解码器暴露于现实失真；（ii）带有时间一致性损失（TCL）的光流扭曲，稳定每帧预测；（iii）语义保持损失，保持条件信号。在代表性I2V模型上的实验显示，从帧中准确恢复水印，具有更高的第一帧和每帧比特准确性和在各种失真应用前后视频生成时的鲁棒性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
