MarkNeRF: Watermarking for Neural Radiance Field
Source abstract
Abstract
This paper presents a novel watermarking scheme designed to address the copyright protection challenges encountered with Neural radiation field (NeRF) models. We employ an embedding network to integrate the watermark into the images within the training set. Then, the NeRF model is utilized for 3D modeling. For copyright verification, a secret image is generated by inputting a confidential viewpoint into NeRF. On this basis, design an extraction network to extract embedded watermark images from confidential viewpoints. In the event of suspicion regarding the unauthorized usage of NeRF in a black-box scenario, the verifier can extract the watermark from the confidential viewpoint to authenticate the model’s copyright. The experimental results demonstrate not only the production of visually appealing watermarks but also robust resistance against various types of noise attacks, thereby substantiating the effectiveness of our approach in safeguarding NeRF.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Computer Graphics and Visualization Techniques · Cell Image Analysis Techniques · Advanced Steganography and Watermarking Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (27)
Show source-provided references
1. NeRF: Representing scenes as neural radiance fields for view synthesis10.1145/3503250 ↗
2. K. Liu et al., “StyleRF: Zero-shot 3D style transfer of neural radiance fields,” Mar. 24, 2023. Accessed: Jan. 15, 2024. [Online]. Available: http://arxiv.org/abs/2303.10598
3. NeRF-editing: Geometry editing of neural radiance fields
4. D-NeRF: Neural radiance fields for dynamic scenes
5. Space-time neural irradiance fields for free-viewpoint video
6. Analytical study of hybrid techniques for image encryption and decryption10.3390/s20185162 ↗
7. A novel compound-coupled hyperchaotic map for image encryption10.3390/sym14030493 ↗
8. Illegal 3D content distribution tracking system based on DNN forensic watermarking
9. Multiview neural surface reconstruction by disentangling geometry and appearance
10. Deep 3D-to-2D watermarking: Embedding messages in 3D meshes and extracting them from 2D renderings
11. B. D. Rouhani, H. Chen, and F. Koushanfar, “DeepSigns: A generic watermarking framework for IP protection of deep learning models,” May 31, 2018. Accessed: Apr. 14, 2024. [Online]. Available: http://arxiv.org/abs/1804.00750
12. Screen-cam robust and blind watermarking for tile satellite images10.1109/ACCESS.2020.3007689 ↗
13. Towards robust deep hiding under non-differentiable distortions for practical blind watermarking
14. Research on watermarking algorithms for 3D color point cloud models
15. Blind robust 3D mesh watermarking based on mesh saliency and wavelet transform for copyright protection10.3390/info10020067 ↗
16. Anti simplified blind watermarking algorithm based on vertex norm 3D mesh model
17. A 3D printing model watermarking algorithm based on 3D slicing and feature points10.3390/electronics7020023 ↗
18. A robust color image watermarking algorithm based on 3D-DCT and SVD
19. Deep 3D mesh watermarking with self-adaptive robustness10.1186/s42400-022-00125-w ↗
20. C. Li, B. Y. Feng, Z. Fan, P. Pan, and Z. Wang, “StegaNeRF: Embedding invisible information within neural radiance fields,” Dec. 03, 2022. Accessed: Jan. 15, 2024. [Online]. Available: http://arxiv.org/abs/2212.01602
21. Z. Luo, Q. Guo, K. C. Cheung, S. See, and R. Wan, “CopyRNeRF: Protecting the copyright of neural radiance fields,” Jul. 29, 2023. Accessed: Jan. 15, 2024. [Online]. Available: http://arxiv.org/abs/2307.11526
22. Turning your weakness into a strength: Watermarking deep neural networks by backdooring
23. K. A. Zhang, A. Cuesta-Infante, L. Xu, and K. Veeramachaneni, “SteganoGAN: High capacity image steganography with GANs,” Jan. 29, 2019. Accessed: Jan. 15, 2024. [Online]. Available: http://arxiv.org/abs/1901.03892
24. Least significant bit hash algorithm for digital image watermarking authentication
25. Baluja · Advances in Neural Information Processing Systems · 2017 · 30
26. J. Zhu, R. Kaplan, J. Johnson, and L. Fei-Fei, “HiDDeN: Hiding data with deep networks,” Jul. 25, 2018. Accessed: Jan. 15, 2024. [Online]. Available: http://arxiv.org/abs/1807.09937
27. The unreasonable effectiveness of deep features as a perceptual metric