Deep Neural Watermarking for Robust Copyright Protection in 3D Point Clouds

TL;DR

This paper introduces a deep neural watermarking framework for 3D point clouds that embeds and extracts watermarks robustly against various geometric and non-geometric attacks, enhancing copyright protection.

Contribution

It proposes a novel SVD-based watermark embedding combined with deep learning for reliable watermark extraction in 3D point clouds, outperforming traditional methods.

Findings

Deep learning-based extraction achieves up to 0.83 bitwise accuracy.

Method maintains high fidelity under severe distortions like cropping and noise.

Outperforms traditional SVD-based techniques significantly.

Abstract

The protection of intellectual property has become critical due to the rapid growth of three-dimensional content in digital media. Unlike traditional images or videos, 3D point clouds present unique challenges for copyright enforcement, as they are especially vulnerable to a range of geometric and non-geometric attacks that can easily degrade or remove conventional watermark signals. In this paper, we address these challenges by proposing a robust deep neural watermarking framework for 3D point cloud copyright protection and ownership verification. Our approach embeds binary watermarks into the singular values of 3D point cloud blocks using spectral decomposition, i.e. Singular Value Decomposition (SVD), and leverages the extraction capabilities of Deep Learning using PointNet++ neural network architecture. The network is trained to reliably extract watermarks even after the data undergoes various attacks such as rotation, scaling, noise, cropping and signal distortions. We validated our method using the publicly available ModelNet40 dataset, demonstrating that deep learning-based extraction significantly outperforms traditional SVD-based techniques under challenging conditions. Our experimental evaluation demonstrates that the deep learning-based extraction approach significantly outperforms existing SVD-based methods with deep learning achieving bitwise accuracy up to 0.83 and Intersection over Union (IoU) of 0.80, compared to SVD achieving a bitwise accuracy of 0.58 and IoU of 0.26 for the Crop (70%) attack, which is the most severe geometric distortion in our experiment. This demonstrates our method's ability to achieve superior watermark recovery and maintain high fidelity even under severe distortions.