WaTeRFlow: Watermark Temporal Robustness via Flow Consistency

TL;DR

WaTeRFlow is a novel framework designed to improve the robustness of watermarks in videos generated via image-to-video conversion, ensuring accurate recovery despite distortions and edits.

Contribution

It introduces a flow-guided synthesis engine, optical-flow warping with a temporal consistency loss, and a semantic preservation loss to enhance watermark robustness in I2V scenarios.

Findings

Higher watermark bit accuracy in experiments

Resilience to various distortions in video generation

Effective stabilization of per-frame predictions

Abstract

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.