# Geometry-Preserving Blind Watermarking for Raw 3D Point Clouds

arXiv: https://arxiv.org/abs/2609.32222 · HTML: https://mlsanity.com/paper/2609.32222/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 40 references that are in the map.
- First posted on arXiv 26 Sep 2026.

## Builds on (most cited first, 19 of 19)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes](https://mlsanity.com/paper/2308.11417/) (2023)
- [Open3D: A Modern Library for 3D Data Processing](https://mlsanity.com/paper/1801.09847/) (2018)
- [Deep Learning for 3D Point Clouds: A Survey](https://mlsanity.com/paper/1912.12033/) (2019)
- [HiDDeN: Hiding Data With Deep Networks](https://mlsanity.com/paper/1807.09937/) (2018)
- [StegaStamp: Invisible Hyperlinks in Physical Photographs](https://mlsanity.com/paper/1904.05343/) (2019)
- [Stratified Transformer for 3D Point Cloud Segmentation](https://mlsanity.com/paper/2203.14508/) (2022)
- [StegaNeRF: Embedding Invisible Information within Neural Radiance Fields](https://mlsanity.com/paper/2212.01602/) (2022)
- [GaussianMarker: Uncertainty-Aware Copyright Protection of 3D Gaussian Splatting](https://mlsanity.com/paper/2410.23718/) (2024)
- [Exploring the Devil in Graph Spectral Domain for 3D Point Cloud Attacks](https://mlsanity.com/paper/2202.07261/) (2022)
- [MarkSplatter: Generalizable Watermarking for 3D Gaussian Splatting Model via Splatter Image Structure](https://mlsanity.com/paper/2509.00757/) (2025)
- [Deep 3D Mesh Watermarking with Self-Adaptive Robustness](https://mlsanity.com/paper/2109.07202/) (2021)
- [Mesh Watermark Removal Attack and Mitigation: A Novel Perspective of Function Space](https://mlsanity.com/paper/2311.12059/) (2023)
- [Blind Deep-Learning-Based Image Watermarking Robust Against Geometric Transformations](https://mlsanity.com/paper/2402.09062/) (2024)
- [Deep Neural Watermarking for Robust Copyright Protection in 3D Point Clouds](https://mlsanity.com/paper/2510.27533/) (2025)

## Abstract (arXiv)

Raw 3D point clouds are a core geometric representation. Establishing their ownership is challenging because point sets are irregular, unstructured, and frequently altered by resampling and geometric preprocessing. We present a blind watermarking framework that operates directly on xyz coordinates and supports both object-level shapes and scene-scale scans. At verification time, the embedded message is recovered from the observed point cloud alone, without access to the original point cloud, color, normals, or mesh connectivity. The method jointly learns watermark embedding and extraction through a feed-forward octree-based architecture, enabling efficient multi-scale geometric reasoning on large point sets. During training, a stochastic transformation layer exposes the decoder to common geometric perturbations, while progressive pose alignment improves robustness to pose changes. Experiments on object-level and scene-level benchmarks demonstrate reliable message recovery under common geometric processing while maintaining low geometric distortion. Qualitative comparisons further show that the learned perturbations are less visually conspicuous and less spatially structured than those of handcrafted alternatives.