Rethinking Mesh Watermark: Towards Highly Robust and Adaptable Deep 3D Mesh Watermarking

TL;DR

This paper introduces Deep3DMark, a deep learning-based 3D mesh watermarking method that is highly robust, adaptable to different mesh sizes and categories, and outperforms existing techniques under attack.

Contribution

The paper presents a novel attention-based deep learning approach for 3D mesh watermarking that is both robust and adaptable to various mesh sizes and types.

Findings

Achieves 10%-50% higher accuracy under mesh attacks.

Remains effective on meshes 190 times larger.

Outperforms traditional and previous DNN-based methods in robustness and quality.

Abstract

The goal of 3D mesh watermarking is to embed the message in 3D meshes that can withstand various attacks imperceptibly and reconstruct the message accurately from watermarked meshes. The watermarking algorithm is supposed to withstand multiple attacks, and the complexity should not grow significantly with the mesh size. Unfortunately, previous methods are less robust against attacks and lack of adaptability. In this paper, we propose a robust and adaptable deep 3D mesh watermarking Deep3DMark that leverages attention-based convolutions in watermarking tasks to embed binary messages in vertex distributions without texture assistance. Furthermore, our Deep3DMark exploits the property that simplified meshes inherit similar relations from the original ones, where the relation is the offset vector directed from one vertex to its neighbor. By doing so, our method can be trained on simplified meshes but remains effective on large size meshes (size adaptable) and unseen categories of meshes (geometry adaptable). Extensive experiments demonstrate our method remains efficient and effective even if the mesh size is 190x increased. Under mesh attacks, Deep3DMark achieves 10%~50% higher accuracy than traditional methods, and 2x higher SNR and 8% higher accuracy than previous DNN-based methods.