IPR-NeRF: Ownership Verification meets Neural Radiance Field
This addresses the risk of plagiarism and misuse for businesses using NeRF models, offering a domain-specific solution for computer vision.
The paper tackles the problem of intellectual property protection for Neural Radiance Field (NeRF) models by proposing IPR-NeRF, a framework that embeds watermarks in black-box settings and digital signatures in white-box settings, with experiments showing it maintains rendering quality and is robust against attacks.
Neural Radiance Field (NeRF) models have gained significant attention in the computer vision community in the recent past with state-of-the-art visual quality and produced impressive demonstrations. Since then, technopreneurs have sought to leverage NeRF models into a profitable business. Therefore, NeRF models make it worth the risk of plagiarizers illegally copying, re-distributing, or misusing those models. This paper proposes a comprehensive intellectual property (IP) protection framework for the NeRF model in both black-box and white-box settings, namely IPR-NeRF. In the black-box setting, a diffusion-based solution is introduced to embed and extract the watermark via a two-stage optimization process. In the white-box setting, a designated digital signature is embedded into the weights of the NeRF model by adopting the sign loss objective. Our extensive experiments demonstrate that not only does our approach maintain the fidelity (\ie, the rendering quality) of IPR-NeRF models, but it is also robust against both ambiguity and removal attacks compared to prior arts.