GeometrySticker: Enabling Ownership Claim of Recolorized Neural Radiance Fields

ECCV 2024
Xiufeng Huang1,2, Ka Chun Cheung2, Simon See2, Renjie Wan1
1Department of Computer Science, Hong Kong Baptist University,
2NVIDIA AI Technology Center, NVAITC
Figure 1

Abstract

Remarkable advancements in the recolorization of Neural Radiance Fields (NeRF) have simplified the process of modifying NeRF's color attributes. Yet, with the potential of NeRF to serve as shareable digital assets, there's a concern that malicious users might alter the color of NeRF models and falsely claim the recolorized version as their own. To safeguard against such breaches of ownership, enabling original NeRF creators to establish rights over recolorized NeRF is crucial. While ap- proaches like CopyRNeRF have been introduced to embed binary mes- sages into NeRF models as digital signatures for copyright protection, the process of recolorization can remove these binary messages. In our paper, we present GeometrySticker, a method for seamlessly integrating binary messages into the geometry components of radiance fields, akin to applying a sticker. GeometrySticker can embed binary messages into NeRF models while preserving the effectiveness of these messages against recolorization. Our comprehensive studies demonstrate that Geometry- Sticker is adaptable to prevalent NeRF architectures and maintains a commendable level of robustness against various distortions.

Framework

Figure 1

Our proposed scenario for ownership claim over the recolorized NeRF. Users can construct their NeRF models using readily available platforms, such as NeRFStudio. Ownership message attachment: They can then swiftly stick binary messages onto those created NeRF models via our proposed GeometrySticker. These watermarked NeRF models remain suitable for standard recolorization processes (herein termed Authorized recolorization). Ownership verification: Should unauthorized recolorization occur, the creators of the NeRF models can retrieve the watermarks from the altered models to verify ownership.

Qualitative Results

Qualitative Results

BibTeX

@article{huang2024geometrysticker,
  title     = {GeometrySticker: Enabling Ownership Claim of Recolorized Neural Radiance Fields},
  author    = {Xiufeng Huang, Ka Chun Cheung, Simon See, Renjie Wan},
  journal   = {ECCV},
  year      = {2024},
}