analiza aiqbench
This research introduces X-SG$^2$S, a feed-forward watermarking framework designed to protect 3D Gaussian Splatting assets from unauthorized use and information leakage. By enabling robust multi-modal embedding across 1D to 3D dimensions without requiring pipeline modifications or parameter fine-tuning, the method addresses critical fragility issues in existing geometric perturbation scenarios. The approach successfully balances high-fidelity scene reconstruction with secure copyright protection, marking a significant step toward practical security integration in generative 3D workflows.
X-SG$^2$S: Safe and Generalizable Gaussian Splatting with X-dimensional Watermarks
arXiv:2502.10475v3 Announce Type: replace-cross Abstract: 3D Gaussian Splatting (3DGS) has been widely used in 3D reconstruction and 3D generation. However, the rapid adoption of 3D Gaussian Splatting raises growing concerns about information leakage and unauthorized use, urging the exploration of effective watermarking techniques. However, existing methods are limited by low capacity, fragility under geometric perturbations, and the infeasible requirement for costly fine-tuning or pipeline modifications, motivating the need for a generalizable, feed-forward framework capable of robust multi-modal embedding with minimal intrusion. In this paper, we propose a new framework X-SG$^2$S which can simultaneously inject 1D to 3D watermarks for copyright protection, while keeping the high fidelity of original 3DGS scenes. Specifically, we first split the watermarks into message patches. A self-adaptive gate is developed to select the injection positions of the watermark messages. Then, we use an XD (multi-dimensional) injection head to inject multi-modal messages into sorted 3DGS points. To restore watermarking messages, a learnable gate is developed to recognize the watermarked locations, from which our XD-extraction heads are used to restore hidden messages. X-SG$^2$S is the first framework to unify 1D-to-3D watermarking and enable simultaneous multi-modal watermark embedding in 3DGS, achieving this with minimal rendering interference and zero modifications to parameters or pipelines. Extensive experiments demonstrate that X-SG$^2$S effectively preserves consistency between the watermark and the original 3DGS, exhibits robustness against model degradation, and maintains accurate judgment capabilities.
Abstract:3D Gaussian Splatting (3DGS) has been widely used in 3D reconstruction and 3D generation. However, the rapid adoption of 3D Gaussian Splatting raises growing concerns about information leakage and unauthorized use, urging the exploration of effective watermarking techniques. However, existing methods are limited by low capacity, fragility under geometric perturbations, and the infeasible requirement for costly fine-tuning or pipeline modifications, motivating the need for a generalizable, feed-forward framework capable of robust multi-modal embedding with minimal intrusion. In this paper, we propose a new framework X-SG$^2$S which can simultaneously inject 1D to 3D watermarks for copyright protection, while keeping the high fidelity of original 3DGS scenes. Specifically, we first split the watermarks into message patches. A self-adaptive gate is developed to select the injection positions of the watermark messages. Then, we use an XD (multi-dimensional) injection head to inject multi-modal messages into sorted 3DGS points. To restore watermarking messages, a learnable gate is developed to recognize the watermarked locations, from which our XD-extraction heads are used to restore hidden messages. X-SG$^2$S is the first framework to unify 1D-to-3D watermarking and enable simultaneous multi-modal watermark embedding in 3DGS, achieving this with minimal rendering interference and zero modifications to parameters or pipelines. Extensive experiments demonstrate that X-SG$^2$S effectively preserves consistency between the watermark and the original 3DGS, exhibits robustness against model degradation, and maintains accurate judgment capabilities.
Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
arXiv:2502.10475 [cs.CR]
(or arXiv:2502.10475v3 [cs.CR] for this version)
https://doi.org/10.48550/arXiv.2502.10475 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 326 cuvinte
Subiecte conexe
From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learning
arXiv · 12 iun. 2026
TruncGradGS: Improved 3D Gaussian Splatting via Truncated Gradient Updates
arXiv · 5 sept. 2026
PolyMerge: Compressing 3D Gaussian Splats with Polytope Coverings for Provably Safe Resource-Constrained Navigation
arXiv · 16 iun. 2026
Resonant Brane Splatting for Arbitrary-Scale Super-Resolution
arXiv · 9 sept. 2026