Deep 3D Mesh Watermarking with Self-Adaptive Robustness

TL;DR

This paper introduces the first deep learning framework for 3D mesh watermarking that achieves adaptive robustness, high universality, and fast embedding while maintaining visual quality, addressing limitations of traditional manual designs.

Contribution

It presents an end-to-end deep learning model using GCNs for 3D mesh watermarking with adaptive robustness and no dependency on mesh topology.

Findings

Achieves superior robustness against attacks compared to baseline methods.

Provides faster watermark embedding process.

Maintains high visual quality of watermarked meshes.

Abstract

Robust 3D mesh watermarking is a traditional research topic in computer graphics, which provides an efficient solution to the copyright protection for 3D meshes. Traditionally, researchers need manually design watermarking algorithms to achieve sufficient robustness for the actual application scenarios. In this paper, we propose the first deep learning-based 3D mesh watermarking framework, which can solve this problem once for all. In detail, we propose an end-to-end network, consisting of a watermark embedding sub-network, a watermark extracting sub-network and attack layers. We adopt the topology-agnostic graph convolutional network (GCN) as the basic convolution operation for 3D meshes, so our network is not limited by registered meshes (which share a fixed topology). For the specific application scenario, we can integrate the corresponding attack layers to guarantee adaptive robustness against possible attacks. To ensure the visual quality of watermarked 3D meshes, we design a curvature-based loss function to constrain the local geometry smoothness of watermarked meshes. Experimental results show that the proposed method can achieve more universal robustness and faster watermark embedding than baseline methods while guaranteeing comparable visual quality.