Multi-level cross-modal attention guided DIBR 3D image watermarking

• Published in: Journal of visual communication and image representation Vol. 109; p. 104455
• Main Authors: Chen, Qingmo, Wang, Zhang, He, Zhouyan, Luo, Ting, Huang, Jiangtao
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.06.2025
• Subjects: Cross-modal Attention; Depth-image-based rendering (DIBR) 3D image; Transformer; Watermarking; Cross-modal Attention; Transformer; Watermarking; Depth-image-based rendering (DIBR) 3D image
• ISSN: 1047-3203
• DOI: 10.1016/j.jvcir.2025.104455

For depth-image-based rendering (DIBR) 3D images, both center and synthesized virtual views are subject to illegal distribution during transmission. To address the issue of copyright protection of DIBR 3D images, we propose a multi-level cross-modal attention guided network (MCANet) for 3D image watermarking. To optimize the watermark embedding process, the watermark adjustment module (WAM) is designed to extract cross-modal information at different scales, thereby calculating 3D image attention to adjust the watermark distribution. Furthermore, the nested dual output U-net (NDOU) is devised to enhance the compensatory capability of the skip connections, thus providing an effective global feature to the up-sampling process for high image quality. Compared to state-of-the-art (SOTA) 3D image watermarking methods, the proposed watermarking model shows superior performance in terms of robustness and imperceptibility.