mlsanityData to 7 Oct 2026

4D-GSW: Kinematic-Aware Spatio-Temporal Consistent Watermarking for 4D Gaussian Splatting

arXiv 2605.22342 ↗First posted 21 May 2026cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

While 4D Gaussian Splatting (4DGS) has revolutionized high-fidelity dynamic reconstruction, safeguarding the intellectual property of these assets remains an open challenge. Conventional steganographic techniques often neglect the underlying kinematic manifolds, triggering non-physical artifacts such as severe temporal flickering and "FVD collapse". To address this, we propose 4D-GSW, a kinematic-aware watermarking framework designed to embed robust copyright information while preserving high spatio-temporal consistency. Unlike prior 4D steganography that primarily focuses on opacity-guided invisibility, our approach explicitly addresses the physical coherence of motion trajectories. We introduce a Spatio-Temporal Curvature (STC) metric to identify "Dynamic Instants," adaptively gating watermark gradient injection to shield critical motion manifolds from non-physical perturbations. To ensure global coherence across complex deformations, we formulate a joint HMM-MRF energy minimization model that synchronizes watermark phases within both temporal trajectories and spatial neighborhoods. Furthermore, an anisotropic gradient routing mechanism ensures that watermark embedding remains strictly decoupled from photometric reconstruction fidelity. Extensive experiments have demonstrated the superior performance of our method in robustly hiding watermarks while resisting various attacks and maintaining high rendering quality and spatiotemporal consistency.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 40 of its 48 references that are in the map. First posted on arXiv 21 May 2026.

Builds on

40 of 48 references.

References · 40

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  4. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  5. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
  6. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  7. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
  8. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,194
  9. 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,144
  10. 2023Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstructioncited by 753
  11. 2023K-Planes: Explicit Radiance Fields in Space, Time, and Appearancecited by 742
  12. 2023Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesiscited by 731
28 more
  1. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 667
  2. 2023Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splattingcited by 470
  3. 2018HiDDeN: Hiding Data With Deep Networkscited by 384
  4. 2023GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splattingcited by 331
  5. 2024Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splattingcited by 218
  6. 2024L4GM: Large 4D Gaussian Reconstruction Modelcited by 143
  7. 2023Consistent4D: Consistent 360deg Dynamic Object Generation from Monocular Videocited by 124
  8. 20234DGen: Grounded 4D Content Generation with Spatial-temporal Consistencycited by 117
  9. 2024Per-Gaussian Embedding-Based Deformation for Deformable 3D Gaussian Splattingcited by 104
  10. 20244Diffusion: Multi-view Video Diffusion Model for 4D Generationcited by 104
  11. 2023HiFi4G: High-Fidelity Human Performance Rendering via Compact Gaussian Splattingcited by 68
  12. 2023Recent Advances in Optimal Transport for Machine Learningcited by 66
  13. 2024SC4D: Sparse-Controlled Video-to-4D Generation and Motion Transfercited by 61
  14. 2024MeGA: Hybrid Mesh-Gaussian Head Avatar for High-Fidelity Rendering and Head Editingcited by 37
  15. 2023CopyRNeRF: Protecting the CopyRight of Neural Radiance Fieldscited by 33
  16. 2022StegaNeRF: Embedding Invisible Information within Neural Radiance Fieldscited by 32
  17. 2024GS-Hider: Hiding Messages into 3D Gaussian Splattingcited by 26
  18. 2024WateRF: Robust Watermarks in Radiance Fields for Protection of Copyrightscited by 25
  19. 2021Deep 3D-to-2D Watermarking: Embedding Messages in 3D Meshes and Extracting Them from 2D Renderingscited by 23
  20. 2024GaussianMarker: Uncertainty-Aware Copyright Protection of 3D Gaussian Splattingcited by 20
  21. 2024GuardSplat: Efficient and Robust Watermarking for 3D Gaussian Splattingcited by 18
  22. 20243D-GSW: 3D Gaussian Splatting for Robust Watermarkingcited by 17
  23. 2025SecureGS: Boosting the Security and Fidelity of 3D Gaussian Splatting Steganographycited by 14
  24. 2025HAIF-GS: Hierarchical and Induced Flow-Guided Gaussian Splatting for Dynamic Scenecited by 11
  25. 2024WATER-GS: Toward Copyright Protection for 3D Gaussian Splatting via Universal Watermarkingcited by 8
  26. 2025VTGaussian-SLAM: RGBD SLAM for Large Scale Scenes with Splatting View-Tied 3D Gaussianscited by 8
  27. 2025SQS: Enhancing Sparse Perception Models via Query-based Splatting in Autonomous Drivingcited by 4
  28. 2024Splats in Splats: Robust and Effective 3D Steganography towards Gaussian Splattingcited by 2

Built on by

Not cited yet.