Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

CopyRNeRF: Protecting the CopyRight of Neural Radiance Fields

About

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.

Ziyuan Luo, Qing Guo, Ka Chun Cheung, Simon See, Renjie Wan• 2023

Related benchmarks

TaskDatasetResultRank
Digital WatermarkingBlender and LLFF (test)
Bit Accuracy (No Attack)91.16
15
3D Scene WatermarkingBlender and LLFF 16 bits
Bit Accuracy91.16
14
3D Scene WatermarkingBlender and LLFF 32 bits
Bit Accuracy78.08
14
3D Scene WatermarkingBlender and LLFF 48 bits
Bit Acc60.06
14
3D Watermarking Robustness against Diffusion AttacksBlender and LLFF (test)
Bit Accuracy (Deterministic)0.512
6
Image Quality AssessmentBlender and LLFF views (test)
SSIM0.747
6
3D WatermarkingLLFF and Blender (train)
Training Time (min)85
6
3D Scene Watermarking and ReconstructionBlender
PSNR30.29
5
3D Scene Watermarking and ReconstructionLLFF
PSNR24.03
5
3D Scene Watermarking and ReconstructionMipNeRF360
PSNR22.47
5
Showing 10 of 10 rows

Other info

Follow for update