Picking watermarks from noise (PWFN): an improved robust watermarking model against intensive distortions

no code implementations • 8 May 2024 • Sijing Xie, Chengxin Zhao, Nan Sun, Wei Li, Hefei Ling

To improve the robustness of the decoder against stronger noise, this paper proposes to introduce a denoise module between the noise layer and the decoder.

Decoder

SSyncOA: Self-synchronizing Object-aligned Watermarking to Resist Cropping-paste Attacks

no code implementations • 6 May 2024 • Chengxin Zhao, Hefei Ling, Sijing Xie, Han Fang, Yaokun Fang, Nan Sun

Modern image processing tools have made it easy for attackers to crop the region or object of interest in images and paste it into other images.

Decoder Object +1

DBDH: A Dual-Branch Dual-Head Neural Network for Invisible Embedded Regions Localization

no code implementations • 6 May 2024 • Chengxin Zhao, Hefei Ling, Sijing Xie, Nan Sun, Zongyi Li, Yuxuan Shi, Jiazhong Chen

In addition, we introduce an extra segmentation head to segment the mask of the embedding region during training.