Research map / 3D vision / NeRF and radiance fields
GeometrySticker: Enabling Ownership Claim of Recolorized Neural Radiance Fields
Xiufeng HUANG, Ka Chun Cheung, Simon See, Renjie Wan
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 |
|---|---|---|---|
| embed messages in geometry instead of color representation | NeRF watermarking · Blender recolorization (CLIP) | bit accuracy (%): 52.48 -> 99.50 | Improved |
| use GeometrySticker instead of CopyRNeRF under image distortions | NeRF watermarking · Blender (rotation) | bit accuracy (%): 64.52 -> 98.87 | Improved |
| use GeometrySticker instead of StegaNeRF under cropout | NeRF watermarking · Blender (cropout) | bit accuracy (%): 60.30 -> 98.75 | Improved |
| restrict message attachment to selected high-density surface points with learnable Laplace CDF (ablation) | GeometrySticker · ablation of cover media selection (visual) | visual distortion | Improved |
| make the Laplace CDF threshold learnable rather than fixed (ablation) | GeometrySticker · ablation of cover media selection (visual) | visual distortion | Improved |
| apply GeometrySticker to different NeRF architectures | GeometrySticker · NeRF, InstantNGP, TensoRF | bit accuracy: 100% on all three | No clear effect |
| adversarial attack with leaked message extractor | GeometrySticker · threat analysis | bit accuracy | Hurt |
| model purification by fine-tuning on clean images | GeometrySticker · threat analysis | bit accuracy | 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.
- StegaNeRF — StegaNeRF: Embedding Invisible Information within Neural Radiance Fields (ICCV 2023) · better on 8 of 8 shared results
- CopyRNeRF — CopyRNeRF: Protecting the CopyRight of Neural Radiance Fields (ICCV 2023) · better on 2 of 2 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
- CopyRNeRF: Protecting the CopyRight of Neural Radiance Fields (ICCV 2023 · similarity 0.91)
- Protecting NeRFs' Copyright via Plug-And-Play Watermarking Base Model (ECCV 2024 · similarity 0.90)
- NeRF Analogies: Example-Based Visual Attribute Transfer for NeRFs (CVPR 2024 · similarity 0.86)
- WateRF: Robust Watermarks in Radiance Fields for Protection of Copyrights (CVPR 2024 · similarity 0.86)
- NeRFail: Neural Radiance Fields-Based Multiview Adversarial Attack (AAAI 2024 · similarity 0.86)
- InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules (ICLR 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.
