Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Towards Secure and Usable 3D Assets: A Novel Framework for Automatic Visible Watermarking

Gursimran Singh, Tianxi Hu, Mohammad Akbari, Qiang Tang, Yong Zhang

TL;DR

This work rigorously defines the novel task of automated 3D visible watermarking in terms of two competing aspects: watermark quality and asset utility and proposes a method of embedding visible watermarks that automatically deter-mines the right location, orientation, and number of wa-termarks to be placed on arbitrary 3D assets for high watermark quality and asset utility.

Abstract

3D models, particularly AI-generated ones, have witnessed a recent surge across various industries such as entertainment. Hence, there is an alarming need to protect the intellectual property and avoid the misuse of these valuable assets. As a viable solution to address these concerns, we rigorously define the novel task of automated 3D visible watermarking in terms of two competing aspects: watermark quality and asset utility. Moreover, we propose a method of embedding visible watermarks that automatically determines the right location, orientation, and number of watermarks to be placed on arbitrary 3D assets for high watermark quality and asset utility. Our method is based on a novel rigid-body optimization that uses back-propagation to automatically learn transforms for ideal watermark placement. In addition, we propose a novel curvature-matching method for fusing the watermark into the 3D model that further improves readability and security. Finally, we provide a detailed experimental analysis on two benchmark 3D datasets validating the superior performance of our approach in comparison to baselines. Code and demo are available.

Towards Secure and Usable 3D Assets: A Novel Framework for Automatic Visible Watermarking

TL;DR

This work rigorously defines the novel task of automated 3D visible watermarking in terms of two competing aspects: watermark quality and asset utility and proposes a method of embedding visible watermarks that automatically deter-mines the right location, orientation, and number of wa-termarks to be placed on arbitrary 3D assets for high watermark quality and asset utility.

Abstract

3D models, particularly AI-generated ones, have witnessed a recent surge across various industries such as entertainment. Hence, there is an alarming need to protect the intellectual property and avoid the misuse of these valuable assets. As a viable solution to address these concerns, we rigorously define the novel task of automated 3D visible watermarking in terms of two competing aspects: watermark quality and asset utility. Moreover, we propose a method of embedding visible watermarks that automatically determines the right location, orientation, and number of watermarks to be placed on arbitrary 3D assets for high watermark quality and asset utility. Our method is based on a novel rigid-body optimization that uses back-propagation to automatically learn transforms for ideal watermark placement. In addition, we propose a novel curvature-matching method for fusing the watermark into the 3D model that further improves readability and security. Finally, we provide a detailed experimental analysis on two benchmark 3D datasets validating the superior performance of our approach in comparison to baselines. Code and demo are available.
Paper Structure (35 sections, 9 equations, 15 figures, 6 tables)

This paper contains 35 sections, 9 equations, 15 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Related Works
  3. Problem Definition
  4. Watermark Quality
  5. Asset Utility
  6. Watermark Quality vs. Asset Utility
  7. Method
  8. Initialization
  9. Finetuning
  10. Filtering
  11. Embossing
  12. Experiments
  13. Quantitative Results
  14. Qualitative Results
  15. Ablation Study
  16. ...and 20 more sections

Figures (15)

  • Figure 1: The overall framework of our proposed automatic 3D visible watermarking.
  • Figure 2: Qualitative analysis of our method with (left) and without (right) curve-matching fusion on an example from Objaverse.
  • Figure 3: Trade-off results between the watermark quality and asset quality metrics on Manifold40. $H_f$: number of watermarks.
  • Figure 4: Visual example of 3D models from Manifold40 (top) and Meshy (bottom) watermarked with our method (left) and Li et al. baseline (right). Ours provides better placement quality, readability, and viewability.
  • Figure 5: Left shows the original model; middle and right show the results of the remeshing attack with low and high strength.
  • ...and 10 more figures