Research map / 3D vision / NeRF and radiance fields
FENeRF: Face Editing in Neural Radiance Fields
Check 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 |
|---|---|---|---|
| Use FENeRF's joint semantic-image rendering and learnable feature grid instead of Giraffe | 3D-aware face generation · CelebA-HQ | FID: 16.2 -> 12.1 | Helped |
| Use FENeRF's joint semantic-image rendering and learnable feature grid instead of Giraffe | 3D-aware face generation · FFHQ | FID: 31.9 -> 28.2 | Helped |
| Use FENeRF's joint semantic-image rendering and learnable feature grid instead of Giraffe | 3D-aware face generation · CelebA-HQ | KID: 9.1 -> 1.6 | Helped |
| Use FENeRF's joint semantic-image rendering and learnable feature grid instead of Giraffe | 3D-aware face generation · FFHQ | KID: 32.7 -> 17.3 | Helped |
| Add image rendering alongside semantic rendering (ablation) | FENeRF · Face geometry and semantic rendering | geometry and semantic quality | Helped |
| Add semantic rendering alongside image rendering (ablation) | FENeRF · Face geometry | geometry quality | Helped |
| Add coordinate embeddings to the color branch (ablation) | FENeRF · Synthesized portraits | image detail | Helped |
| Inject coordinate embeddings at the beginning of the MLP with coordinates (ablation) | FENeRF · Synthesized portraits and semantic maps | artifact level | Hurt |
| Remove coordinate embeddings (ablation) | FENeRF · Synthesized portraits | image detail | Hurt |
| Train with semantic-map supervision only, without image rendering (ablation) | FENeRF · Face geometry and semantics | geometry and semantic quality | Hurt |
| Invert real portraits into the geometry latent space | FENeRF · CelebAMask-HQ portraits | mIoU: 0.5 by 100 iterations; over 0.7 within 200 iterations | Helped |
Closest papers by meaning
- In-N-Out: Faithful 3D GAN Inversion with Volumetric Decomposition for Face Editing (CVPR 2024 · similarity 0.89)
- InstructPix2NeRF: Instructed 3D Portrait Editing from a Single Image (ICLR 2024 · similarity 0.89)
- FFaceNeRF: Few-shot Face Editing in Neural Radiance Fields (CVPR 2025 · similarity 0.88)
- SIGNeRF: Scene Integrated Generation for Neural Radiance Fields (CVPR 2024 · similarity 0.87)
- Reference-Based 3D-Aware Image Editing with Triplanes (CVPR 2025 · similarity 0.87)
- StrokeFaceNeRF: Stroke-based Facial Appearance Editing in Neural Radiance Field (CVPR 2024 · similarity 0.86)
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.