# GS-Marker: Generalizable and Robust Watermarking for 3D Gaussian Splatting

arXiv: https://arxiv.org/abs/2503.18718 · HTML: https://mlsanity.com/paper/2503.18718/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 36 references that are in the map.
- First posted on arXiv 24 Mar 2025.

## Builds on (most cited first, 29 of 29)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation](https://mlsanity.com/paper/2402.05054/) (2024)
- [HiDDeN: Hiding Data With Deep Networks](https://mlsanity.com/paper/1807.09937/) (2018)
- [DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes](https://mlsanity.com/paper/2312.07920/) (2023)
- [OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation](https://mlsanity.com/paper/2301.07525/) (2023)
- [The Stable Signature: Rooting Watermarks in Latent Diffusion Models](https://mlsanity.com/paper/2303.15435/) (2023)
- [GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation](https://mlsanity.com/paper/2403.14621/) (2024)
- [StegaStamp: Invisible Hyperlinks in Physical Photographs](https://mlsanity.com/paper/1904.05343/) (2019)
- [Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformers](https://mlsanity.com/paper/2312.09147/) (2023)
- [VastGaussian: Vast 3D Gaussians for Large Scene Reconstruction](https://mlsanity.com/paper/2402.17427/) (2024)
- [COLMAP-Free 3D Gaussian Splatting](https://mlsanity.com/paper/2312.07504/) (2023)
- [SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting](https://mlsanity.com/paper/2403.05087/) (2024)
- [HUGS: Human Gaussian Splats](https://mlsanity.com/paper/2311.17910/) (2023)
- [EditGuard: Versatile Image Watermarking for Tamper Localization and Copyright Protection](https://mlsanity.com/paper/2312.08883/) (2023)
- [Human Gaussian Splatting: Real-time Rendering of Animatable Avatars](https://mlsanity.com/paper/2311.17113/) (2023)
- [Generalizable and Animatable Gaussian Head Avatar](https://mlsanity.com/paper/2410.07971/) (2024)
- [DVMark: A Deep Multiscale Framework for Video Watermarking](https://mlsanity.com/paper/2104.12734/) (2021)
- [CopyRNeRF: Protecting the CopyRight of Neural Radiance Fields](https://mlsanity.com/paper/2307.11526/) (2023)
- [StegaNeRF: Embedding Invisible Information within Neural Radiance Fields](https://mlsanity.com/paper/2212.01602/) (2022)
- [WateRF: Robust Watermarks in Radiance Fields for Protection of Copyrights](https://mlsanity.com/paper/2405.02066/) (2024)
- [GS-Hider: Hiding Messages into 3D Gaussian Splatting](https://mlsanity.com/paper/2405.15118/) (2024)
- [Deep 3D-to-2D Watermarking: Embedding Messages in 3D Meshes and Extracting Them from 2D Renderings](https://mlsanity.com/paper/2104.13450/) (2021)
- [Large-capacity and Flexible Video Steganography via Invertible Neural Network](https://mlsanity.com/paper/2304.12300/) (2023)
- [GaussianMarker: Uncertainty-Aware Copyright Protection of 3D Gaussian Splatting](https://mlsanity.com/paper/2410.23718/) (2024)
- [Deep 3D Mesh Watermarking with Self-Adaptive Robustness](https://mlsanity.com/paper/2109.07202/) (2021)
- [Rethinking Mesh Watermark: Towards Highly Robust and Adaptable Deep 3D Mesh Watermarking](https://mlsanity.com/paper/2307.11628/) (2023)

## Built on by (most cited first, 6 of 6)

- [Deep Neural Watermarking for Robust Copyright Protection in 3D Point Clouds](https://mlsanity.com/paper/2510.27533/) (2025)
- [Intellectual Property Protection for 3D Gaussian Splatting Assets: A Survey](https://mlsanity.com/paper/2602.03878/) (2026)
- [StegoNGP: 3D Cryptographic Steganography using Instant-NGP](https://mlsanity.com/paper/2603.00949/) (2026)
- [Splats in Splats++: Robust and Generalizable 3D Gaussian Splatting Steganography](https://mlsanity.com/paper/2604.15862/) (2026)
- [NGS-Marker: Robust Native Watermarking for 3D Gaussian Splatting](https://mlsanity.com/paper/2608.17447/) (2026)
- [FlyMark: Training-Free Invisible Watermarking of 3D Gaussian Splatting via a Fruit Fly Connectome](https://mlsanity.com/paper/2610.11364/) (2026)

## Abstract (arXiv)

In the Generative AI era, safeguarding 3D models has become increasingly urgent. While invisible watermarking is well-established for 2D images with encoder-decoder frameworks, generalizable and robust solutions for 3D remain elusive. The main difficulty arises from the renderer between the 3D encoder and 2D decoder, which disrupts direct gradient flow and complicates training. Existing 3D methods typically rely on per-scene iterative optimization, resulting in time inefficiency and limited generalization. In this work, we propose a single-pass watermarking approach for 3D Gaussian Splatting (3DGS), a well-known yet underexplored representation for watermarking. We identify two major challenges: (1) ensuring effective training generalized across diverse 3D models, and (2) reliably extracting watermarks from free-view renderings, even under distortions. Our framework, named GS-Marker, incorporates a 3D encoder to embed messages, distortion layers to enhance resilience against various distortions, and a 2D decoder to extract watermarks from renderings. A key innovation is the Adaptive Marker Control mechanism that adaptively perturbs the initially optimized 3DGS, escaping local minima and improving both training stability and convergence. Extensive experiments show that GS-Marker outperforms per-scene training approaches in terms of decoding accuracy and model fidelity, while also significantly reducing computation time.