Research map / 3D vision / NeRF and radiance fields
StegaNeRF: Embedding Invisible Information within Neural Radiance Fields
Chenxin Li, Brandon Y. Feng, Zhiwen Fan, Panwang Pan, Zhangyang Wang
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 |
|---|---|---|---|
| train NeRF from scratch on images watermarked with 2D steganography (LSB, DeepStega) | NeRF with 2D steganography · LLFF and NeRF-Synthetic | hidden recovery SSIM: LSB 0.0132, DeepStega 0.2098 vs StegaNeRF 0.9730 | Hurt |
| add classifier-conditioned detector (ablation) | StegaNeRF · LLFF ablation | hidden recovery SSIM: 0.4417 -> 0.9224 | Improved |
| add classifier-guided detector conditioning (ablation) | StegaNeRF · LLFF ablation | hidden recovery SSIM: 0.5461 -> 0.9224 | Improved |
| add gradient masking (ablation) | StegaNeRF · LLFF ablation | rendering PSNR: 27.86 -> 28.21 | Improved |
| use soft masking instead of binary mask (ablation) | StegaNeRF · LLFF ablation | hidden recovery accuracy: 94.44 -> 100.0 | Improved |
| embed one hidden image per scene vs one common image across scenes | StegaNeRF multi-scene · LLFF multi-scene | hidden recovery SSIM: One-for-All 0.9860 vs One-for-One 0.9122 on first scene; NeRF PSNR equal 24.99 | Mixed |
| apply StegaNeRF stage on trained NeRF | Plenoxels NeRF · NeRF-Synthetic | rendering PSNR: 31.13 -> 30.96 | Mixed |
| JPEG compression and Gaussian blur on renderings | StegaNeRF · LLFF | hidden recovery SSIM | No clear effect |
Later papers that compared with this method
1 later accepted paper reports StegaNeRF as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- GeometrySticker: Enabling Ownership Claim of Recolorized Neural Radiance Fields (ECCV 2024 · better on 8 of 8 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
- Aleth-NeRF: Illumination Adaptive NeRF with Concealing Field Assumption (AAAI 2024 · similarity 0.88)
- WateRF: Robust Watermarks in Radiance Fields for Protection of Copyrights (CVPR 2024 · similarity 0.87)
- Rad-NeRF: Ray-decoupled Training of Neural Radiance Field (NeurIPS 2024 · similarity 0.87)
- CodecNeRF: Toward Fast Encoding and Decoding, Compact, and High-quality Novel-view Synthesis (AAAI 2025 · similarity 0.87)
- NeRF-VPT: Learning Novel View Representations with Neural Radiance Fields via View Prompt Tuning (AAAI 2024 · similarity 0.87)
- Optimize the Unseen - Fast NeRF Cleanup with Free Space Prior (NeurIPS 2025 · similarity 0.87)
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.
