Intellectual Property Protection for 3D Gaussian Splatting Assets: A Survey
Not on the map. Why?
Abstract (arXiv)
3D Gaussian Splatting (3DGS) has become a mainstream representation for real-time 3D scene synthesis, enabling applications in virtual and augmented reality, robotics, and 3D content creation. Its rising commercial value and explicit parametric structure raise emerging intellectual property (IP) protection concerns, prompting a surge of research on 3DGS IP protection. However, current progress remains fragmented, lacking a unified view of the underlying mechanisms, protection paradigms, and robustness challenges. To address this gap, we present the first systematic survey on 3DGS IP protection and introduce a bottom-up framework that examines (i) underlying Gaussian-based perturbation mechanisms, (ii) passive and active protection paradigms, and (iii) robustness threats under emerging generative AI era, revealing gaps in technical foundations and robustness characterization and indicating opportunities for deeper investigation. Finally, we outline six research directions across robustness, efficiency, and protection paradigms, offering a roadmap toward reliable and trustworthy IP protection for 3DGS assets.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 78 of its 97 references that are in the map. First posted on arXiv 2 Feb 2026.
Builds on
78 of 97 references.
References · 78
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
- 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
- 2022Flow Matching for Generative Modelingcited by 5,426
- 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,591
- 2019Machine Unlearningcited by 1,020
- 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 742
- 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 730
- 2023Instruct-NeRF2NeRF: Editing 3D Scenes with Instructionscited by 482
- 2022Diffusion Models for Adversarial Purificationcited by 469
- 2018HiDDeN: Hiding Data With Deep Networkscited by 384
- 2023GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splattingcited by 331
38 more
- 2023Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformerscited by 257
- 2025AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Viewscited by 234
- 2023Glaze: Protecting Artists from Style Mimicry by Text-to-Image Modelscited by 200
- 2021Unlearnable Examples: Making Personal Data Unexploitablecited by 188
- 2023GaussianEditor: Editing 3D Gaussians Delicately with Text Instructionscited by 166
- 2023Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examplescited by 163
- 2024GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editingcited by 114
- 2024Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advancescited by 105
- 20243D Gaussian as a New Era: A Surveycited by 102
- 2024DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editingcited by 92
- 2023Mist: Towards Improved Adversarial Examples for Diffusion Modelscited by 91
- 20243D Gaussian Splatting: Survey, Technologies, Challenges, and Opportunitiescited by 77
- 2024How NeRFs and 3D Gaussian Splatting are Reshaping SLAM: a Surveycited by 72
- 2024View-Consistent 3D Editing with Gaussian Splattingcited by 67
- 2023Toward effective protection against diffusion based mimicry through score distillationcited by 64
- 2023Domain Watermark: Effective and Harmless Dataset Copyright Protection is Closed at Handcited by 52
- 2024On Large Language Model Continual Unlearningcited by 51
- 2021Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorizationcited by 50
- 2022Harnessing Out-Of-Distribution Examples via Augmenting Content and Stylecited by 43
- 2024EditSplat: Multi-View Fusion and Attention-Guided Optimization for View-Consistent 3D Scene Editing with 3D Gaussian Splattingcited by 40
- 2025Exploring Criteria of Loss Reweighting to Enhance LLM Unlearningcited by 39
- 2023Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?cited by 37
- 2023CopyRNeRF: Protecting the CopyRight of Neural Radiance Fieldscited by 33
- 2023IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AIcited by 32
- 2023Robust Generalization against Photon-Limited Corruptions via Worst-Case Sharpness Minimizationcited by 29
- 2024GS-Hider: Hiding Messages into 3D Gaussian Splattingcited by 26
- 2024Beyond Gaussians: Fast and High-Fidelity 3D Splatting with Linear Kernelscited by 22
- 2024GaussianMarker: Uncertainty-Aware Copyright Protection of 3D Gaussian Splattingcited by 20
- 2023On the Over-Memorization During Natural, Robust and Catastrophic Overfittingcited by 19
- 2024Protecting NeRFs' Copyright via Plug-And-Play Watermarking Base Modelcited by 18
- 2024GuardSplat: Efficient and Robust Watermarking for 3D Gaussian Splattingcited by 18
- 20243D-GSW: 3D Gaussian Splatting for Robust Watermarkingcited by 17
- 2025Rethinking Data Protection in the (Generative) Artificial Intelligence Eracited by 17
- 2025MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning Segmentationcited by 16
- 2024Geometry Cloak: Preventing TGS-based 3D Reconstruction from Copyrighted Imagescited by 15
- 2025SecureGS: Boosting the Security and Fidelity of 3D Gaussian Splatting Steganographycited by 14
- 2025Beyond Optimal Transport: Model-Aligned Coupling for Flow Matchingcited by 13
- 2024Eliminating Catastrophic Overfitting Via Abnormal Adversarial Examples Regularizationcited by 11
50 most cited of 78 All 78 (JSON)
Built on by
Citing papers per year: 2026: 2.
2 papers.