Research map / Point clouds / Point cloud classification
NeuralEditor: Editing Neural Radiance Fields via Manipulating Point Clouds
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 IST to correct view-dependent colors after deformation (ablation) | NeuralEditor · NeRF Synthetic Hotdog, zero-shot | PSNR: 27.02 -> 27.49 | Helped |
| Add IST to correct view-dependent colors after deformation (ablation) | NeuralEditor · NeRF Synthetic Hotdog, fine-tune 1 epoch | PSNR: 36.69 -> 37.22 | Helped |
| Use spline integration instead of traditional point sampling (ablation) | NeuralEditor · NeRF Synthetic Hotdog, zero-shot | PSNR: 27.48 -> 27.49 | No clear effect |
| Use spline integration instead of traditional point sampling (ablation) | NeuralEditor · NeRF Synthetic Hotdog, fine-tune 1 epoch | PSNR: 36.69 -> 37.22 | Helped |
| Use deterministic rather than stochastic integration (ablation) | NeuralEditor · NeRF Synthetic Hotdog, zero-shot | PSNR: 27.46 -> 27.49 | Helped |
| Use deterministic rather than stochastic integration (ablation) | NeuralEditor · NeRF Synthetic Hotdog, fine-tune 1 epoch | PSNR: 36.87 -> 37.22 | Helped |
| Use NeRF modeling rather than direct point-cloud plotting (ablation) | NeuralEditor · NeRF Synthetic Hotdog, zero-shot | PSNR: 27.01 -> 27.49 | Helped |
| Use NeRF modeling rather than direct point-cloud plotting (ablation) | NeuralEditor · NeRF Synthetic Hotdog, fine-tune 1 epoch | PSNR: 36.38 -> 37.22 | Helped |
| Add point-cloud normal vectors (ablation) | NeuralEditor · NeRF Synthetic Hotdog, zero-shot | PSNR: 27.26 -> 27.49 | Helped |
| Add point-cloud normal vectors (ablation) | NeuralEditor · NeRF Synthetic Hotdog, fine-tune 1 epoch | PSNR: 37.00 -> 37.22 | Helped |
| Use Phong reflection rather than traditional color modeling (ablation) | NeuralEditor · NeRF Synthetic Hotdog, zero-shot | PSNR: 27.21 -> 27.49 | Helped |
| Use Phong reflection rather than traditional color modeling (ablation) | NeuralEditor · NeRF Synthetic Hotdog, fine-tune 1 epoch | PSNR: 36.51 -> 37.22 | Helped |
Closest papers by meaning
- NeRF-Editing: Geometry Editing of Neural Radiance Fields (CVPR 2022 · similarity 0.93)
- EditableNeRF: Editing Topologically Varying Neural Radiance Fields by Key Points (CVPR 2023 · similarity 0.90)
- Removing Objects From Neural Radiance Fields (CVPR 2023 · similarity 0.89)
- Rad-NeRF: Ray-decoupled Training of Neural Radiance Field (NeurIPS 2024 · similarity 0.88)
- SIGNeRF: Scene Integrated Generation for Neural Radiance Fields (CVPR 2024 · similarity 0.88)
- LAENeRF: Local Appearance Editing for Neural Radiance Fields (CVPR 2024 · 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.