Watermarking for Neural Radiation Fields by Invertible Neural Network

TL;DR

This paper introduces a watermarking scheme for neural radiation fields using invertible neural networks, enabling copyright protection of 3D scenes by embedding and extracting watermarks through inverse image transformations.

Contribution

It proposes a novel invertible neural network-based watermarking method that embeds watermarks during training and extracts them from rendered images, protecting 3D scene copyrights.

Findings

Effective watermark embedding and extraction demonstrated

Watermark robustness across multiple viewpoints

Image quality enhancement improves watermark recovery

Abstract

To protect the copyright of the 3D scene represented by the neural radiation field, the embedding and extraction of the neural radiation field watermark are considered as a pair of inverse problems of image transformations. A scheme for protecting the copyright of the neural radiation field is proposed using invertible neural network watermarking, which utilizes watermarking techniques for 2D images to achieve the protection of the 3D scene. The scheme embeds the watermark in the training image of the neural radiation field through the forward process in the invertible network and extracts the watermark from the image rendered by the neural radiation field using the inverse process to realize the copyright protection of both the neural radiation field and the 3D scene. Since the rendering process of the neural radiation field can cause the loss of watermark information, the scheme incorporates an image quality enhancement module, which utilizes a neural network to recover the rendered image and then extracts the watermark. The scheme embeds a watermark in each training image to train the neural radiation field and enables the extraction of watermark information from multiple viewpoints. Simulation experimental results demonstrate the effectiveness of the method.