Research map / 3D vision / Gaussian splatting
CompMarkGS: Robust Watermarking for Compressed 3D Gaussian Splatting
Sumin In, Youngdong Jang, Utae Jeong, MinHyuk Jang, Hyeongcheol Park, Eunbyung Park, Sangpil Kim
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 quantization distortion layer (QDL) (ablation) | CompMarkGS · HAC after compression | bit accuracy (%): 90.75 -> 95.92 | Improved |
| Add quantization distortion layer (QDL) (ablation) | CompMarkGS · ContextGS after compression | bit accuracy (%): 88.09 -> 94.03 | Improved |
| Add frequency-aware anchor growing (FAG) (ablation) | CompMarkGS · HAC after compression | bit accuracy (%): 93.95 -> 95.92 | Improved |
| Add frequency-aware anchor growing (FAG) (ablation) | CompMarkGS · ContextGS after compression | PSNR: 27.15 -> 27.55 | Improved |
| Add HSV loss (ablation) | CompMarkGS · HAC after compression | bit accuracy (%): 92.57 -> 95.92 | Improved |
| Add HSV loss (ablation) | CompMarkGS · HAC after compression | LPIPS: 0.179 -> 0.177 | Improved |
| Embed watermark in anchor feature instead of position (ablation) | CompMarkGS · HAC after compression | PSNR: 12.05 -> 27.65 | Improved |
| Embed watermark in anchor feature instead of offsets (ablation) | CompMarkGS · HAC after compression | PSNR: 24.61 -> 27.65 | Improved |
| Add dedicated watermark embedding feature f' (ablation) | CompMarkGS · ContextGS after compression | PSNR: 26.79 -> 27.55 | Improved |
| Increase message length from 32 to 64 bits | CompMarkGS · before compression | bit accuracy (%): 96.52 -> 91.29 | Hurt |
| Use CompMarkGS instead of 3D-GSW | anchor-based 3DGS watermark · ContextGS | PSNR: 19.83 -> 27.55 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.
- WateRF — WateRF: Robust Watermarks in Radiance Fields for Protection of Copyrights (CVPR 2024) · better on 6 of 6 shared results
- GaussianMarker — GaussianMarker: Uncertainty-Aware Copyright Protection of 3D Gaussian Splatting (NeurIPS 2024) · better on 4 of 4 shared results
- 3D-GSW — 3D-GSW: 3D Gaussian Splatting for Robust Watermarking (CVPR 2025) · better on 3 of 3 shared results
- GuardSplat — GuardSplat: Efficient and Robust Watermarking for 3D Gaussian Splatting (CVPR 2025) · better on 3 of 3 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
- 3D-GSW: 3D Gaussian Splatting for Robust Watermarking (CVPR 2025 · similarity 0.92)
- GaussianMarker: Uncertainty-Aware Copyright Protection of 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.92)
- GuardSplat: Efficient and Robust Watermarking for 3D Gaussian Splatting (CVPR 2025 · similarity 0.91)
- SecureGS: Boosting the Security and Fidelity of 3D Gaussian Splatting Steganography (ICLR 2025 · similarity 0.89)
- Optimized Minimal 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.88)
- GS-Hider: Hiding Messages into 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.88)
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.
