# FlowMark: Mask-Guided Video Watermarking

arXiv: https://arxiv.org/abs/2607.05261 · HTML: https://mlsanity.com/paper/2607.05261/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 51 references that are in the map.
- First posted on arXiv 6 Jul 2026.

## Builds on (most cited first, 5 of 5)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1711.10275/) (2017)
- [TreeLearn: A deep learning method for segmenting individual trees from ground-based LiDAR forest point clouds](https://mlsanity.com/paper/2309.08471/) (2023)
- [Remember to correct the bias when using deep learning for regression!](https://mlsanity.com/paper/2203.16470/) (2022)
- [Direct Estimation of Tree Volume and Aboveground Biomass Using Deep Regression with Synthetic Lidar Data](https://mlsanity.com/paper/2603.04683/) (2026)

## Built on by (most cited first, 2 of 2)

- [Asymmetric Phase Coding Video Watermarking](https://mlsanity.com/paper/2608.29212/) (2026)
- [Rethinking Visual Provenance: Detection and Watermarking Across Direct Visual Generation and LLM-Driven Code Rendering](https://mlsanity.com/paper/2610.08137/) (2026)

## Abstract (arXiv)

We present FlowMark, a video watermarking framework guided by automatically predicted object masks. In contrast to prior region-based approaches that require user-supplied mask guidance, FlowMark learns to identify optimal regions for watermark embedding through a dedicated Mask Predictor network. Our end-to-end trainable architecture combines region-aware encoding with noise-augmented training to ensure robustness against compression, geometric transformations, and content variation, while preserving high perceptual quality. Our content-adaptive masking keeps watermark signals coherent with natural video dynamics, effectively eliminating perceptual flicker. Beyond compression robustness, FlowMark maintains reliable watermark recovery under video-native temporal edits (e.g., frame swap, insertion, deletion, resampling, and interpolation) and real-world social media distribution pipelines (e.g., YouTube and Facebook re-encoding). Experimental results on both image and video datasets show that FlowMark reliably embeds 128-bit messages with up to 50.08 dB PSNR, offering strong performance for content provenance, temporal authenticity verification, and video integrity protection.