CopyRNeRF: Protecting the CopyRight of Neural Radiance Fields
ICCV 2023

Ziyuan Luo1, 2, Qing Guo3, Ka Chun Cheung2, 4, Simon See2, Renjie Wan1, *
1 Department of Computer Science, Hong Kong Baptist University
2 NVIDIA AI Technology Center, NVIDIA
3 IHPC and CFAR, Agency for Science, Technology and Research, Singapore
4 Department of Mathematics, Hong Kong Baptist University
* Corresponding author
Paper Code
Figure 1

Abstract

Neural Radiance Fields (NeRF) have the potential to be a major representation of media. Since training a NeRF has never been an easy task, the protection of its model copyright should be a priority. In this paper, by analyzing the pros and cons of possible copyright protection solutions, we propose to protect the copyright of NeRF models by replacing the original color representation in NeRF with a watermarked color representation. Then, a distortion-resistant rendering scheme is designed to guarantee robust message extraction in 2D renderings of NeRF. Our proposed method can directly protect the copyright of NeRF models while maintaining high rendering quality and bit accuracy when compared among optional solutions.

Framework

Figure 1

Illustration of our proposed method. (a) A watermarked color representation is obtained with the given secret message, which is able to produce watermarked color for rendering. (b) During training, a distortion-resistant rendering is deployed to map the geometry (σ) and watermarked color representations to image patches with several distortions. (c) Finally, the secret message can be revealed by a CNN-based message extractor.

BibTeX

@inproceedings{luo2023copyrnerf,
  author    = {Ziyuan Luo and Qing Guo and Ka Chun Cheung and Simon See and Renjie Wan},
  title     = {Copy{RN}e{RF}: Protecting the CopyRight of Neural Radiance Fields},
  booktitle   = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  year      = {2023},
}