CopyRNeRF: Protecting the CopyRight of Neural Radiance Fields

Ziyuan Luo; Qing Guo; Ka Chun Cheung; Simon See; Renjie Wan

doi:10.1109/ICCV51070.2023.02047

CopyRNeRF: Protecting the CopyRight of Neural Radiance Fields

Ziyuan Luo, Qing Guo, Ka Chun Cheung, Simon See, Renjie Wan^*

^*Corresponding author for this work

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

2 Citations (Scopus)

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. Project page: https://luo-ziyuan.github.io/copyrnerf.

Original language	English
Title of host publication	2023 IEEE/CVF International Conference on Computer Vision (ICCV)
Place of Publication	Paris, France
Publisher	IEEE
Pages	22401-22411
Number of pages	11
ISBN (Electronic)	9798350307184
ISBN (Print)	9798350307191
DOIs	https://doi.org/10.1109/ICCV51070.2023.02047
Publication status	Published - Oct 2023
Event	18th IEEE International Conference on Computer Vision, ICCV 2023 - Paris Convention Center, Paris, France Duration: 2 Oct 2023 → 6 Oct 2023 https://iccv2023.thecvf.com/ (Conference website) https://iccv2023.thecvf.com/iccv2023.main.conference.program-38--MTE.php (Conference programme ) https://openaccess.thecvf.com/ICCV2023 (Conference proceedings)

Publication series

Name	International Conference on Computer Vision (ICCV)
ISSN (Print)	1550-5499
ISSN (Electronic)	2380-7504

Conference

Conference	18th IEEE International Conference on Computer Vision, ICCV 2023
Country/Territory	France
City	Paris
Period	2/10/23 → 6/10/23
Internet address	https://iccv2023.thecvf.com/ (Conference website) https://iccv2023.thecvf.com/iccv2023.main.conference.program-38--MTE.php (Conference programme ) https://openaccess.thecvf.com/ICCV2023 (Conference proceedings)

Access to Document

10.1109/ICCV51070.2023.02047

https://openaccess.thecvf.com/content/ICCV2023/papers/Luo_CopyRNeRF_Protecting_the_CopyRight_of_Neural_Radiance_Fields_ICCV_2023_paper.pdf

Cite this

@inproceedings{945f99d2626941889e36c9a67fed078c,

title = "CopyRNeRF: Protecting the CopyRight of Neural Radiance Fields",

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. Project page: https://luo-ziyuan.github.io/copyrnerf.",

author = "Ziyuan Luo and Qing Guo and Cheung, {Ka Chun} and Simon See and Renjie Wan",

year = "2023",

month = oct,

doi = "10.1109/ICCV51070.2023.02047",

language = "English",

isbn = "9798350307191",

series = "International Conference on Computer Vision (ICCV)",

publisher = "IEEE",

pages = "22401--22411",

booktitle = "2023 IEEE/CVF International Conference on Computer Vision (ICCV)",

address = "United States",

note = "18th IEEE International Conference on Computer Vision, ICCV 2023 ; Conference date: 02-10-2023 Through 06-10-2023",

url = "https://iccv2023.thecvf.com/, https://iccv2023.thecvf.com/iccv2023.main.conference.program-38--MTE.php, https://openaccess.thecvf.com/ICCV2023",

}

Luo, Z, Guo, Q, Cheung, KC, See, S & Wan, R 2023, CopyRNeRF: Protecting the CopyRight of Neural Radiance Fields. in 2023 IEEE/CVF International Conference on Computer Vision (ICCV). International Conference on Computer Vision (ICCV), IEEE, Paris, France, pp. 22401-22411, 18th IEEE International Conference on Computer Vision, ICCV 2023, Paris, France, 2/10/23. https://doi.org/10.1109/ICCV51070.2023.02047

CopyRNeRF: Protecting the CopyRight of Neural Radiance Fields. / Luo, Ziyuan; Guo, Qing; Cheung, Ka Chun et al.
2023 IEEE/CVF International Conference on Computer Vision (ICCV). Paris, France: IEEE, 2023. p. 22401-22411 (International Conference on Computer Vision (ICCV)).

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - CopyRNeRF: Protecting the CopyRight of Neural Radiance Fields

AU - Luo, Ziyuan

AU - Guo, Qing

AU - Cheung, Ka Chun

AU - See, Simon

AU - Wan, Renjie

PY - 2023/10

Y1 - 2023/10

N2 - 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. Project page: https://luo-ziyuan.github.io/copyrnerf.

AB - 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. Project page: https://luo-ziyuan.github.io/copyrnerf.

U2 - 10.1109/ICCV51070.2023.02047

DO - 10.1109/ICCV51070.2023.02047

M3 - Conference proceeding

SN - 9798350307191

T3 - International Conference on Computer Vision (ICCV)

SP - 22401

EP - 22411

BT - 2023 IEEE/CVF International Conference on Computer Vision (ICCV)

PB - IEEE

CY - Paris, France

T2 - 18th IEEE International Conference on Computer Vision, ICCV 2023

Y2 - 2 October 2023 through 6 October 2023

ER -

CopyRNeRF: Protecting the CopyRight of Neural Radiance Fields

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this