自动为3D模型嵌入可见水印，兼顾清晰度与使用价值。
Towards Secure and Usable 3D Assets: A Novel Framework for Automatic Visible Watermarking
- 基于刚体优化和反向传播自动确定水印位置、方向与数量。
- 水印融合采用曲率匹配，提升可读性与安全性。
- 适用于需版权保护的AI生成3D模型，如游戏与影视资产。
3D模型，尤其是人工智能生成的模型，在娱乐等行业中迅速普及，对其知识产权保护和防止滥用的需求日益迫切。为此，本文严谨定义了自动化3D可见水印这一新任务，需平衡水印质量与资产可用性两大矛盾目标。提出一种方法，可自动确定任意3D资产上水印的位置、方向与数量，以实现高水印质量和高资产可用性。该方法基于一种新型刚体优化，利用反向传播自动学习最优水印放置变换。此外，提出一种新颖的曲率匹配融合方法，进一步增强水印的可读性与安全性。在两个基准3D数据集上进行详尽实验，验证了所提方法优于基线的性能。代码与演示已公开。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。