Adaptor: Improving the Robustness and Imperceptibility of Watermarking by the Adaptive Strength Factor

Wang, Baowei; Wu, Yufeng; Wang, Guiling

doi:10.1109/tcsvt.2023.3265970

Cited by 9 publications

(1 citation statement)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Firstly, multi-scale downsampling combined with SE-Block [18] is used in the encoder to extract feature information. SE-Block [18] has been proved to be able to better extract the frequency domain information of images [19,20]; secondly, the watermark information is fully fused with the latent space generated by the encoder in a multi-scale manner; finally, the structure of the downsampling part in the decoder and the encoder is the same, and the two share parameters to improve the decoding rate. As evidenced by the results, our approach surpasses other methods in producing images of better quality under JPEG compression, with a negligible decoding bit error rate (BER) that approaches 0.004%.…”

Section: Outmentioning

confidence: 99%

A robust watermarking algorithm against JPEG compression based on multiscale autoencoder

Zhang,

Chen,

Wang

2023

IET Image Processing

View full text Add to dashboard Cite

The network structure of digital watermarking algorithm based on deep learning is usually encoder‐noise layer‐decoder. Most of the existing encoders suffer from the problem of insufficient feature extraction, and the introduction of simulated differentiable joint photographic experts group (JPEG) compression in the noise layer cannot ensure the robustness under real JPEG. In this paper, a watermarking algorithm based on multi‐scale auto‐encoder is proposed, which can effectively extract the image feature information by combining with the channel attention mechanism. At the same time, some parameters of decoder and encoder are shared to reduce redundant feature embedding and improve extraction accuracy. This paper also proposes a robust training scheme against JPEG compression, which can guide the model to store the watermark in the low‐frequency region needed for decoding. Experimental results show that the peak signal‐to‐noise ratio (PSNR) of the proposed algorithm is above 48 and the decoding rate is above 99% under JPEG compression with quality factor Q = 50. Moreover, this scheme can effectively promote the combination of noise layer in training. In addition, the proposed algorithm is also robust to other common network noises.

show abstract