Research map / 3D vision / Gaussian splatting
Splats in Splats: Robust and Effective 3D Steganography Towards Gaussian Splatting
Yijia Guo, Wenkai Huang, Yang Li, Gaolei Li, Hang Zhang, Liwen Hu, Jianhua Li, Tiejun Huang, Lei Ma
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 autoencoder-assisted opacity mapping (ablation) | Splats in Splats · Mip-NeRF360 (9 scenes) ablation (original scene) | PSNR: 24.209 -> 26.749 | Improved |
| add autoencoder-assisted opacity mapping (ablation) | Splats in Splats · Mip-NeRF360 (9 scenes) ablation (hidden scene) | PSNR: 23.346 -> 26.517 | Improved |
| add SH coefficient encryption (ablation) | Splats in Splats · Mip-NeRF360 (9 scenes) ablation (hidden scene) | PSNR: 11.092 -> 26.517 | Improved |
| add SH coefficient encryption (ablation) | Splats in Splats · Mip-NeRF360 (9 scenes) ablation (original scene) | PSNR: 26.795 -> 26.749 | No clear effect |
| importance-graded vs average SH encryption (ablation) | Splats in Splats · hidden scene under Gaussian noise | PSNR: 16.267 -> 22.979 | Improved |
| vary bit shifting length k from 10 to 22 (ablation) | Splats in Splats · Mip-NeRF360 (9 scenes) | PSNR/SSIM | No clear effect |
| vary opacity mask threshold tau from 0.0 to 0.3 (ablation) | Splats in Splats · Mip-NeRF360 (9 scenes) | PSNR/SSIM | Mixed |
| use vanilla-3DGS-preserving embedding vs GS-Hider | Splats in Splats · Mip-NeRF360 (9 scenes) hidden scene | PSNR: 25.179 -> 26.517 | Improved |
| use Splats in Splats under 25% sequential pruning | Splats in Splats · Mip-NeRF360 (9 scenes) hidden scene | PSNR: SecureGS 16.960 vs Ours 26.517 | Improved |
| use Splats in Splats vs GS-Hider rendering speed | Splats in Splats · Mip-NeRF360 (9 scenes) | FPS: 44 -> 118 | Improved |
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.
- SecureGS — SecureGS: Boosting the Security and Fidelity of 3D Gaussian Splatting Steganography (ICLR 2025) · better on 6 of 6 shared results
- GS-Hider — GS-Hider: Hiding Messages into 3D Gaussian Splatting (NeurIPS 2024) · better on 6 of 6 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
- SecureGS: Boosting the Security and Fidelity of 3D Gaussian Splatting Steganography (ICLR 2025 · similarity 0.94)
- GS-Hider: Hiding Messages into 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.94)
- GuardSplat: Efficient and Robust Watermarking for 3D Gaussian Splatting (CVPR 2025 · similarity 0.92)
- GaussianMarker: Uncertainty-Aware Copyright Protection of 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.90)
- Geometry Cloak: Preventing TGS-based 3D Reconstruction from Copyrighted Images (NeurIPS 2024 · similarity 0.90)
- 3D-GSW: 3D Gaussian Splatting for Robust Watermarking (CVPR 2025 · similarity 0.90)
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.
