嘘~ 正在从服务器偷取页面 . . .

NeRF


⚠️ 以下所有内容总结都来自于 大语言模型的能力,如有错误,仅供参考,谨慎使用
🔴 请注意:千万不要用于严肃的学术场景,只能用于论文阅读前的初筛!
💗 如果您觉得我们的项目对您有帮助 ChatPaperFree ,还请您给我们一些鼓励!⭐️ HuggingFace免费体验

2025-02-28 更新

The NeRF Signature: Codebook-Aided Watermarking for Neural Radiance Fields

Authors:Ziyuan Luo, Anderson Rocha, Boxin Shi, Qing Guo, Haoliang Li, Renjie Wan

Neural Radiance Fields (NeRF) have been gaining attention as a significant form of 3D content representation. With the proliferation of NeRF-based creations, the need for copyright protection has emerged as a critical issue. Although some approaches have been proposed to embed digital watermarks into NeRF, they often neglect essential model-level considerations and incur substantial time overheads, resulting in reduced imperceptibility and robustness, along with user inconvenience. In this paper, we extend the previous criteria for image watermarking to the model level and propose NeRF Signature, a novel watermarking method for NeRF. We employ a Codebook-aided Signature Embedding (CSE) that does not alter the model structure, thereby maintaining imperceptibility and enhancing robustness at the model level. Furthermore, after optimization, any desired signatures can be embedded through the CSE, and no fine-tuning is required when NeRF owners want to use new binary signatures. Then, we introduce a joint pose-patch encryption watermarking strategy to hide signatures into patches rendered from a specific viewpoint for higher robustness. In addition, we explore a Complexity-Aware Key Selection (CAKS) scheme to embed signatures in high visual complexity patches to enhance imperceptibility. The experimental results demonstrate that our method outperforms other baseline methods in terms of imperceptibility and robustness. The source code is available at: https://github.com/luo-ziyuan/NeRF_Signature.

神经辐射场(NeRF)作为一种重要的三维内容表示形式,正受到越来越多的关注。随着基于NeRF的创作作品的增多,版权保护的需求已成为一个关键问题。尽管已经提出一些将数字水印嵌入NeRF的方法,但它们往往忽略了模型级别的关键考量,并产生了大量的时间开销,导致感知透明度和稳健性降低,同时也给用户带来了不便。在本文中,我们将图像水印的先前标准扩展到模型级别,并提出了NeRF Signature,这是一种新型的NeRF水印方法。我们采用助码本签名嵌入(CSE)技术,不会改变模型结构,从而保持感知透明度并增强模型级别的稳健性。此外,经过优化后,任何所需的签名都可以通过CSE嵌入,并且当NeRF所有者想要使用新的二进制签名时,无需进行微调。然后,我们引入了一种联合姿态补丁加密水印策略,将签名隐藏在从特定视角呈现的补丁中,以实现更高的稳健性。此外,我们还探索了一种基于复杂度的密钥选择(CAKS)方案,以在高视觉复杂度的补丁中嵌入签名,以提高感知透明度。实验结果表明,我们的方法在感知透明度和稳健性方面优于其他基准方法。源代码可在以下网址找到:https://github.com/luo-ziyuan/NeRF_Signature

论文及项目相关链接

PDF 16 pages, accepted by TPAMI

Summary

本文提出一种针对NeRF模型的新型数字水印方法——NeRF Signature。此方法利用Codebook辅助签名嵌入技术,不改变模型结构,实现模型级别的水印嵌入。结合姿势补丁加密水印策略及复杂性感知密钥选择方案,提升水印的隐蔽性和鲁棒性。实验结果显示,该方法在隐蔽性和鲁棒性方面优于其他基线方法。

Key Takeaways

  1. NeRF作为一种重要的三维内容表示形式,其版权保护需求迫切。
  2. 当前NeRF水印方法存在模型级别考虑不足、时间开销大等问题。
  3. 本文提出NeRF Signature,首次将图像水印标准扩展到模型级别。
  4. 采用Codebook辅助签名嵌入技术,不影响模型结构,保持隐蔽性并增强鲁棒性。
  5. 结合姿势补丁加密策略,将签名隐藏在特定视角的补丁中,提高鲁棒性。
  6. 引入复杂性感知密钥选择方案,在高视觉复杂性补丁中嵌入签名,进一步增强隐蔽性。

Cool Papers

点此查看论文截图


文章作者: Kedreamix
版权声明: 本博客所有文章除特別声明外,均采用 CC BY 4.0 许可协议。转载请注明来源 Kedreamix !
 上一篇
Diffusion Models Diffusion Models
Diffusion Models 方向最新论文已更新,请持续关注 Update in 2025-02-28 HDM Hybrid Diffusion Model for Unified Image Anomaly Detection
下一篇 
3DGS 3DGS
3DGS 方向最新论文已更新,请持续关注 Update in 2025-02-28 Scaffold-SLAM Structured 3D Gaussians for Simultaneous Localization and Photorealistic Mapping
2025-02-28