EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Image Watermarking Algorithm Leveraging Dual-Attention Synergy and Adaptive Multi-Scale Fusion

Zhenghan Yang, Huadong Sun, Nuohan Lv

Electronics · 11.06.2026 · 15 (12) · 2580

DOI: 10.3390/electronics15122580 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 11.06.2026. Verfasst von Zhenghan Yang und 2 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fundamental Research Funds in Universities of Heilongjiang Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Blind image watermarking models such as HiDDeN have laid an important foundation for end-to-end watermarking. Nevertheless, they still suffer from three major limitations: single-scale feature extraction, fixed fusion weights, and slow training convergence. To address these issues, this paper proposes an adaptive multi-scale watermarking algorithm based on collaborative dual-attention mechanisms. The algorithm designs an adaptive multi-scale feature fusion module (MA-FFM) with a dynamic gating network in the encoder, which flexibly combines local multi-scale textures with global contextual information, overcoming the limitation of fixed fusion weights. In the decoder, a multi-level channel attention module is embedded to strengthen the extraction of watermark signals. The two attention modules work synergistically: the encoder focuses on adaptive feature fusion while the decoder leverages channel attention to selectively enhance watermark-related features, forming a dual-attention synergy that balances robustness and imperceptibility. Moreover, the dynamic gating network adaptively adjusts the contribution of local versus global features via learnable weights, whose evolution from approximately 0.51 to about 0.89 improves model interpretability. Experiments are conducted on the COCO 2017 dataset. Compared with HiDDeN, the proposed algorithm reduces the bit error rate (BER) from 0.1696 to 0.1538 under no attack with a relative reduction of 9.3%, increases PSNR by 0.61 dB, and improves SSIM from 0.9058 to 0.9077. Under various attacks—including JPEG compression, Gaussian noise, salt-and-pepper noise, and brightness/contrast adjustments—the BER remains consistently lower than that of HiDDeN. Ablation studies confirm the effectiveness of each module. Overall, the proposed algorithm preserves visual quality, improves the accuracy of watermark embedding and extraction, and exhibits strong generalization robustness against common image distortions.

Förderung

  • Fundamental Research Funds in Universities of Heilongjiang Province

Zitieren

APA

Yang, Z., Sun, H., & Lv, N. (2026). Image Watermarking Algorithm Leveraging Dual-Attention Synergy and Adaptive Multi-Scale Fusion. Electronics, 15(12), 2580. https://doi.org/10.3390/electronics15122580

Vancouver

Yang Z, Sun H, Lv N. Image Watermarking Algorithm Leveraging Dual-Attention Synergy and Adaptive Multi-Scale Fusion. Electronics. 2026;15(12):2580. doi:10.3390/electronics15122580

BibTeX
@article{Yang2026,
  author = {Yang, Zhenghan and Sun, Huadong and Lv, Nuohan},
  title = {Image Watermarking Algorithm Leveraging Dual-Attention Synergy and Adaptive Multi-Scale Fusion},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {12},
  pages = {2580},
  doi = {10.3390/electronics15122580}
}
Kostenlos starten →