Research map / 3D vision / 3D generation
SINE: Semantic-Driven Image-Based NeRF Editing With Prior-Guided Editing Field
Chong Bao, Yinda Zhang, Bangbang Yang, Tianxing Fan, Zesong Yang, Hujun Bao, Guofeng Zhang, Zhaopeng Cui
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 |
|---|---|---|---|
| remove geometric prior constraints (ablation) | SINE geometric editing · Single-image geometric NeRF editing | novel-view geometric plausibility | Hurt |
| disable the texture modification field (ablation) | SINE texture editing · Single-image texture NeRF editing | local texture detail | Hurt |
| remove the color compositing layer (ablation) | SINE texture editing · Single-image texture NeRF editing | texture-edit coverage | Hurt |
| remove editing regularization (ablation) | SINE geometric editing · Single-image geometric NeRF editing | preservation of irrelevant regions | Hurt |
| remove editing regularization (ablation) | SINE texture editing · Single-image texture NeRF editing | preservation of irrelevant regions | Hurt |
| remove photometric supervision (ablation) | SINE geometric editing · Single-image geometric NeRF editing | editing fidelity | Hurt |
| remove silhouette supervision (ablation) | SINE geometric editing · Single-image geometric NeRF editing | editing fidelity | Hurt |
| remove deformation regularization (ablation) | SINE geometric editing · Single-image geometric NeRF editing | geometric integrity | Hurt |
| remove cycle loss (ablation) | SINE geometric editing · Single-image geometric NeRF editing | semantic geometric guidance | Hurt |
| replace texture-transfer supervision with photometric painting loss (ablation) | SINE texture editing · Single-image texture NeRF editing | texture completeness across views | Hurt |
| replace the 3D editing field with direct template-NeRF fine-tuning | SINE geometric editing · Single-image geometric NeRF editing | multi-view consistency | Hurt |
| replace the 3D editing field with direct template-NeRF fine-tuning | SINE texture editing · Single-image texture NeRF editing | fine-grained texture editing | Hurt |
Closest papers by meaning
- Decomposing NeRF for Editing via Feature Field Distillation (NeurIPS 2022 · similarity 0.92)
- Seal-3D: Interactive Pixel-Level Editing for Neural Radiance Fields (ICCV 2023 · similarity 0.91)
- LAENeRF: Local Appearance Editing for Neural Radiance Fields (CVPR 2024 · similarity 0.90)
- ED-NeRF: Efficient Text-Guided Editing of 3D Scene With Latent Space NeRF (ICLR 2024 · similarity 0.89)
- Language-driven Object Fusion into Neural Radiance Fields with Pose-Conditioned Dataset Updates (CVPR 2024 · similarity 0.89)
- Customize your NeRF: Adaptive Source Driven 3D Scene Editing via Local-Global Iterative Training (CVPR 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.
