WaTeRFlow：通过流一致性实现水印的时序鲁棒性
WaTeRFlow: Watermark Temporal Robustness via Flow Consistency
针对图像到视频（I2V）生成后水印检测失效的问题，提出用光流对齐加时序一致性损失来稳定逐帧水印预测，并借助视频扩散代理模型在训练中模拟真实失真；做生成内容溯源或水印鲁棒性评测的视觉研究者可直接复用这套训练与评测设定。
原文依据 optical-flow warping with a Temporal Consistency Loss (TCL) that stabilizes per-frame predictions
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论图像水印支撑真实性与来源追溯，但许多方案仍容易被各种失真和强大的生成式编辑绕过。基于深度学习的水印方法提升了对扩散式图像编辑的鲁棒性，然而当带水印图像经图像到视频（I2V）转换为视频时仍存在缺口，此时逐帧水印检测会变弱。I2V 已迅速从短暂、抖动的片段发展到数秒长、时序连贯的场景，如今不仅服务于内容创作，也服务于世界建模与仿真工作流，这使得跨模态水印恢复变得至关重要。我们提出 WaTeRFlow，一个专为 I2V 场景下的鲁棒性而设计的框架。它由三部分组成：(i) FUSE（流引导统一合成引擎），在训练中通过指令驱动的编辑和快速视频扩散代理，使编码器-解码器暴露于真实失真之下；(ii) 光流对齐配合时序一致性损失（TCL），用于稳定逐帧预测；(iii) 语义保持损失，用于维持条件信号。在多个代表性 I2V 模型上的实验表明，该框架能从视频帧中准确恢复水印，在首帧与逐帧比特准确率上更高，并且在视频生成之前或之后施加各种失真时都更具韧性。
英文原文摘要 1302 字符
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.