Research map / 3D vision / NeRF and radiance fields
GIRAFFE: Representing Scenes As Compositional Generative Neural Feature 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 compositional 3D feature fields with neural rendering instead of the strongest reported baseline | GIRAFFE · Cats, 64² | FID: 18 -> 8 | Helped |
| Use compositional 3D feature fields with neural rendering instead of the strongest reported baseline | GIRAFFE · CelebA, 64² | FID: 15 -> 6 | Helped |
| Use compositional 3D feature fields with neural rendering instead of the strongest reported baseline | GIRAFFE · Cars, 64² | FID: 16 -> 16 | No clear effect |
| Use compositional 3D feature fields with neural rendering instead of the strongest reported baseline | GIRAFFE · Chairs, 64² | FID: 34 -> 20 | Helped |
| Use compositional 3D feature fields with neural rendering instead of the strongest reported baseline | GIRAFFE · Churches, 64² | FID: 19 -> 17 | Helped |
| Use compositional 3D feature fields with neural rendering instead of the strongest reported baseline | GIRAFFE · CelebA-HQ, 256² | FID: 33 -> 21 | Helped |
| Use compositional 3D feature fields with neural rendering instead of the strongest reported baseline | GIRAFFE · FFHQ, 256² | FID: 59 -> 32 | Helped |
| Use compositional 3D feature fields with neural rendering instead of the strongest reported baseline | GIRAFFE · Cars, 256² | FID: 34 -> 26 | Helped |
| Use compositional 3D feature fields with neural rendering instead of the strongest reported baseline | GIRAFFE · Churches, 256² | FID: 58 -> 30 | Helped |
| Use compositional 3D feature fields with neural rendering instead of the strongest reported baseline | GIRAFFE · Clevr-2, 256² | FID: 106 -> 31 | Helped |
| Add RGB skip connections (ablation) | GIRAFFE neural renderer · CompCars | FID: 16.66 -> 16.16 | Helped |
| Add the final activation (ablation) | GIRAFFE neural renderer · CompCars | FID: 21.61 -> 16.16 | Helped |
Closest papers by meaning
- Compositional Scene Understanding through Inverse Generative Modeling (ICML 2025 · similarity 0.89)
- Denoising Diffusion via Image-Based Rendering (ICLR 2024 · similarity 0.86)
- SCION: Scene Composition via Instanced Neural Primitives (NeurIPS 2026 · similarity 0.86)
- Generative Photography: Scene-Consistent Camera Control for Realistic Text-to-Image Synthesis (CVPR 2025 · similarity 0.86)
- CityDreamer: Compositional Generative Model of Unbounded 3D Cities (CVPR 2024 · similarity 0.85)
- Generating compositional scenes via Text-to-image RGBA Instance Generation (NeurIPS 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.