EUVIMEDEUVIMED entdecken
Crossref

Can Protective Watermarking Safeguard the Copyright of 3D Gaussian Splatting?

Wenkai Huang, Yijia Guo, Gaolei Li, Lei Ma, Hang Zhang, Liwen Hu, Jiazheng Wang, Jianhua Li, Tiejun Huang

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (7) · 5149-5157

DOI: 10.1609/aaai.v40i7.37429 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Wenkai Huang und 8 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

3D Gaussian Splatting (3DGS) has emerged as a powerful representation for 3D scenes, widely adopted due to its exceptional efficiency and high-fidelity visual quality. Given the significant value of 3DGS assets, recent works have introduced specialized watermarking schemes to ensure copyright protection and ownership verification. However, can existing 3D Gaussian watermarking approaches genuinely guarantee robust protection of the 3D assets? In this paper, for the first time, we systematically explore and validate possible vulnerabilities of 3DGS watermarking frameworks. We demonstrate that conventional watermark removal techniques designed for 2D images do not effectively generalize to the 3DGS scenario due to the specialized rendering pipeline and unique attributes of each gaussian primitives. Motivated by this insight, we propose GSPure, the first watermark purification framework specifically for 3DGS watermarking representations. By analyzing view-dependent rendering contributions and exploiting geometrically accurate feature clustering, GSPure precisely isolates and effectively removes watermark-related Gaussian primitives while preserving scene integrity. Extensive experiments demonstrate that our GSPure achieves the best watermark purification performance, reducing watermark PSNR by up to 16.34dB while minimizing degradation to original scene fidelity with less than 1dB PSNR loss. Moreover, it consistently outperforms existing methods in both effectiveness and generalization.

Zitieren

APA

Huang, W., Guo, Y., Li, G., Ma, L., Zhang, H., Hu, L., Wang, J., Li, J., & Huang, T. (2026). Can Protective Watermarking Safeguard the Copyright of 3D Gaussian Splatting?. Proceedings of the AAAI Conference on Artificial Intelligence, 40(7), 5149-5157. https://doi.org/10.1609/aaai.v40i7.37429

Vancouver

Huang W, Guo Y, Li G, Ma L, Zhang H, Hu L, et al. Can Protective Watermarking Safeguard the Copyright of 3D Gaussian Splatting?. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(7):5149-5157. doi:10.1609/aaai.v40i7.37429

BibTeX
@article{Huang2026,
  author = {Huang, Wenkai and Guo, Yijia and Li, Gaolei and Ma, Lei and Zhang, Hang and Hu, Liwen and Wang, Jiazheng and Li, Jianhua and Huang, Tiejun},
  title = {Can Protective Watermarking Safeguard the Copyright of 3D Gaussian Splatting?},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {7},
  pages = {5149--5157},
  doi = {10.1609/aaai.v40i7.37429}
}
Kostenlos starten →