Protecting NeRFs' Copyright via Plug-And-Play Watermarking Base Model

TL;DR

This paper introduces NeRFProtector, a plug-and-play watermarking method that embeds copyright information into Neural Radiance Fields during creation, ensuring protection without sacrificing rendering quality.

Contribution

We propose a novel plug-and-play watermarking approach using a pre-trained base model and progressive distillation for NeRFs, enabling flexible copyright protection.

Findings

NeRFProtector achieves performance comparable to state-of-the-art neural rendering methods.

The method allows flexible embedding of watermarks during NeRF creation.

Watermarked NeRFs maintain high visual quality and fidelity.

Abstract

Neural Radiance Fields (NeRFs) have become a key method for 3D scene representation. With the rising prominence and influence of NeRF, safeguarding its intellectual property has become increasingly important. In this paper, we propose \textbf{NeRFProtector}, which adopts a plug-and-play strategy to protect NeRF's copyright during its creation. NeRFProtector utilizes a pre-trained watermarking base model, enabling NeRF creators to embed binary messages directly while creating their NeRF. Our plug-and-play property ensures NeRF creators can flexibly choose NeRF variants without excessive modifications. Leveraging our newly designed progressive distillation, we demonstrate performance on par with several leading-edge neural rendering methods. Our project is available at: \url{https://qsong2001.github.io/NeRFProtector}.