In the field of copyright protection, mesh watermarking is a key technology for protecting 3D models from malicious attacks during transmission. However, existing watermarking algorithms for 3D meshes often fail to effectively connect the spatial and frequency domains and the setting rule of watermark embedding strength is not clear enough. To solve this problem, we propose a robust mesh watermarking algorithm guided by invisibility (RWGI). Taking the Laplacian transform of a mesh as an example, we establish, for the first time during the watermark embedding process, a model that characterizes the relationship between the spatial-domain invisibility evaluation index and the spectraldomain embedding strength. In this way, the watermark embedding can be adaptively guided by the invisibility index, ensuring the quantification of the watermark embedding strength on demand. Additionally, we design a spectral coefficient optimization strategy based on absolute value, along with a simple yet efficient watermarking segmentation algorithm. Experimental results show that the proposed algorithm achieves strong invisibility, robustness against common attacks, and adaptive control of watermark embedding intensity with respect to model scale.
[1] 张国有, 崔健. 基于顶点范数三维网格模型抗简化盲水印算法[J]. 计算机工程与设计, 2023, 44(3): 692-698. Zhang G Y, Cui J. Anti-simplified blind watermarking algorithm for three dimensional mesh model based on vertex norm [J]. Computer Engineering and Design, 2023, 44(3): 692-698. (in Chinese)
[2] Hou G Y, Ou B, Long M, et al. Separable reversible data hiding for encrypted 3D mesh models based on octree subdivision and multi-MSB prediction [J]. IEEE Transactions on Multimedia, 2024, 26: 2395-2407.
[3] Tsai Y Y. Separable reversible data hiding for encrypted three-dimensional models based on spatial subdivision and space encoding [J]. IEEE Transactions on Multimedia, 2021, 23: 2286- 2296.
[4] Peng F, Long B, Long M. A general region nesting-based semi-fragile reversible watermarking for authenticating 3D mesh models [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2021, 31(11): 4538-4553.
[5] Peng F, Liao T, Long M. A semi-fragile reversible watermarking for authenticating 3D models in dual domains based on variable direction double modulation [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2022, 32(12): 8394-8408.
[6] Cheung Y, Wu H. A sequential quantization strategy for data embedding and integrity verification [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2007, 17(8): 1007-1016.
[7] Liu J, Wang Y, Li Y, et al. A robust and blind 3D watermarking algorithm using multiresolution adaptive parameterization of surface [J]. Neurocomputing, 2017, 237: 304-315.
[8] Wang K, Lavoué G, Denis F, et al. Hierarchical watermarking of semiregular meshes based on wavelet transform [J]. IEEE Transactions on Information Forensics and Security, 2008, 3(4): 620-634.
[9] Ohbuchi R, Takahashi S, Miyazawa T, et al. Watermarking 3D polygonal meshes in the mesh spectral domain [C]//Graphics Interface, 2001: 9-17.
[10] Ohbuchi R, Mukaiyama A, Takahashi S. A frequency-domain approach to watermarking 3D shapes [J]. Computer Graphics Forum, 2002, 21(3): 373-382.
[11] Wu J, Kobbelt L. Efficient spectral watermarking of large meshes with orthogonal basis functions [J]. Visual Computer, 2005, 21: 848-857.
[12] Yang Y, Ivrissimtzis I. Polygonal mesh watermarking using Laplacian coordinates [J]. Computer Graphics Forum, 2010, 29(5): 1585-1593.
[13] Yoo I, Chang H, Luo X, et al. Deep 3D-to-2D watermarking: embedding messages in 3D meshes and extracting them from 2D renderings [C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022: 10031-10040.
[14] Wang F, Zhou H, Fang H, et al. Deep 3D mesh watermarking with self-adaptive robustness [J]. Cybersecurity, 2022, 5(1): 24.
[15] Zhu X, Ye G, Luo X, et al. Rethinking mesh watermark: towards highly robust and adaptable deep 3D mesh watermarking [C]//38th AAAI Conference on Artificial Intelligence, 2024, 38(7): 7784-7792.
[16] Luo Z, Guo Q, Cheung K C, et al. CopyRNeRF: protecting the copyright of neural radiance fields [C]//IEEE/CVF International Conference on Computer Vision, 2023: 22401-22411.
[17] Jang Y, Lee D I, Jang M H, et al. WateRF: robust watermarks in radiance fields for protection of copyrights [C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024: 12087-12097.
[18] Qi S, Luo Z, Cheung K C, et al. Protecting NeRFs’ copyright via plug-and-play watermarking base model [DB/OL]. (2024-07-10) [2024-11-12]. https://arxiv.org/abs/2407.07735.
[19] 孙文权, 刘佳, 董炜娜, 等. 基于可逆神经网络的神经辐射场水印[J]. 计算机应用研究, 2024, 41(6): 1840-1844. Sun W Q, Liu J, Dong W N, et al. Watermarking for neural radiation fields by invertible neural network [J]. Application Research of Computers, 2024, 41(6): 1840-1844. (in Chinese)
[20] 陈立峰, 刘佳, 董炜娜, 等. 面向神经辐射场的水印算法[J]. 计算机应用研究, 2024, 41(7): 2184- 2188. Chen L F, Liu J, Dong W N, et al. Watermarking for neural radiance field [J]. Application Research of Computers, 2024, 41(7): 2184-2188. (in Chinese)
[21] Zhang X, Meng J, Li R, et al. GS-hider: hiding messages into 3D Gaussian splatting [DB/OL]. (2024-05-24) [2024-11-12]. https://arxiv.org/abs/2405.15118.
[22] Jang Y, Park H, Yang F, et al. 3D-GSW: 3D gaussian splatting watermark for protecting copyrights in radiance fields [DB/OL]. (2024-09-20) [2024-11-12]. https://arxiv.org/abs/2409.13222.
[23] Al-Khafaji H, Abhayaratne C. Graph spectral domain blind watermarking [C]//IEEE International Conference on Acoustics, Speech and Signal Processing, 2019: 2492-2496
[24] Huang Y, Niu B, Guan H, et al. Enhancing image watermarking with adaptive embedding parameter and PSNR guarantee [J]. IEEE Transactions on Multimedia, 2019, 21(10): 2447-2460.
[25] Reuter M, Wolter F E, Peinecke N. Laplace-Beltrami spectra as ‘Shape-DNA’ of surfaces and solids [J]. Computer-Aided Design, 2006, 38(4): 342-366.
[26] Zeng G R, Qiu Z D. Image watermarking based on DC component in DCT [C]//2nd International Symposium on Intelligent Information Technology Application, 2008: 573-576.
[27] Zhang H, Van Kaick O, Dyer R. Spectral mesh processing [J]. Computer Graphics Forum, 2010, 29(6): 1865-1894.
[28] Taubin G. A signal processing approach to fair surface design [C]//22nd Annual Conference on Computer Graphics and Interactive Techniques, 1995: 351-358.
[29] Lai Y K, Hu S M, Martin R R, et al. Fast mesh segmentation using random walks [C]//ACM Symposium on Solid and Physical Modeling, 2008: 183-191.
[30] Qi C R, Su H, Mo K, et al. PointNet: deep learning on point sets for 3D classification and segmentation [C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2017: 77-85.
