Research map / 3D vision / Gaussian splatting
Where, What, Why: Toward Explainable 3D-GS Watermarking
Mingshu Cai, Jiajun Li, Osamu Yoshie, Yuya Ieiri, Yixuan Li
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add SBAG carrier selection (ablation) | 3D-GS watermarking · Ablation 32-bit | Bit accuracy: 97.10 -> 97.80 (w/o SBAG vs full) | Improved |
| add SBAG carrier selection (ablation) | 3D-GS watermarking · Ablation 32-bit | PSNR: 33.70 -> 35.20 | Improved |
| add channel-wise Group Mask (ablation) | 3D-GS watermarking · Ablation 32-bit | PSNR: 34.10 -> 35.20 | Improved |
| add decoupled finetuning (ablation) | 3D-GS watermarking · Ablation 32-bit | Bit accuracy: 95.10 -> 97.80 | Improved |
| add decoupled finetuning (ablation) | 3D-GS watermarking · Ablation 32-bit | PSNR: 33.10 -> 35.20 | Improved |
| use adaptive carrier budget instead of 1% fixed (ablation) | 3D-GS watermarking · Carrier budget | Bit accuracy: 97.19 -> 98.46 | Improved |
| use adaptive carrier budget instead of 10% fixed (ablation) | 3D-GS watermarking · Carrier budget | PSNR: 34.24 -> 35.98 | Improved |
| increase message length from 32 to 64 bits | Ours · Blender/LLFF/Mip-NeRF360 avg | Bit accuracy: 98.46 -> 91.65 | Hurt |
| proposed method vs 3D-GSW under Gaussian noise on 3D-GS parameters | Ours · Model-level distortion 32-bit | Bit accuracy: 89.93 -> 90.52 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- 3D-GSW — 3D-GSW: 3D Gaussian Splatting for Robust Watermarking (CVPR 2025) · better on 7 of 7 shared results
- GuardSplat — GuardSplat: Efficient and Robust Watermarking for 3D Gaussian Splatting (CVPR 2025) · better on 7 of 7 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- GaussianMarker: Uncertainty-Aware Copyright Protection of 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.91)
- 3D-GSW: 3D Gaussian Splatting for Robust Watermarking (CVPR 2025 · similarity 0.91)
- GuardSplat: Efficient and Robust Watermarking for 3D Gaussian Splatting (CVPR 2025 · similarity 0.90)
- SecureGS: Boosting the Security and Fidelity of 3D Gaussian Splatting Steganography (ICLR 2025 · similarity 0.87)
- GS-Hider: Hiding Messages into 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.87)
- Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models (CVPR 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
