Dual-Process Watermarked Diffusion: Integrating Watermarking With Denoising in Point Clouds
Jinfu Wei, Heng Chang, Xiaohang Liu, Li Liu, Likun Li, Shiji Zhou, Chengyuan Li, Di Xu
Abstract
The integration of depth sensing and laser scanning technologies has propelled point cloud data to the forefront of 3D graphical modeling. This paper addresses a critical gap in the literature: the protection of intellectual property in generating point clouds using Diffusion Models (DMs). We introduce Dual-Process Watermarked Diffusion (DPWD), a pioneering watermarking framework for Diffusion Models (DMs) used in point cloud generation. DPWD embeds watermarks directly into DMs, ensuring strong protection against intellectual property theft. To do so, we introduce a two-stage watermark strategy: 1) watermark embedding using a permutation invariant module, and 2) watermark integration into the DM’s noise predictor. The framework is robust against common attacks and preserves the quality of generated point clouds. Empirical results on various point cloud tasks demonstrate DPWD’s effectiveness in safeguarding intellectual property rights without compromising model performance. DPWD sets a new standard for model protection in the GenAI era.
BibTeX
@inproceedings{icassp2025_dualprocesswater,
title = {Dual-Process Watermarked Diffusion: Integrating Watermarking With Denoising in Point Clouds},
author = {Jinfu Wei and Heng Chang and Xiaohang Liu and Li Liu and Likun Li and Shiji Zhou and Chengyuan Li and Di Xu and Wei Gao and Ran Liao},
booktitle = {ICASSP 2025},
year = {2025}
}