Research map / 3D vision / 3D generation
3D Neural Field Generation Using Triplane Diffusion
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 |
|---|---|---|---|
| Use NFD instead of SDF-StyleGAN | 3D shape generation · ShapeNet Cars | FID: 98.0 -> 83.6 | Helped |
| Use NFD instead of SDF-StyleGAN | 3D shape generation · ShapeNet Cars | Precision: 35.9 -> 49.5 | Helped |
| Use NFD instead of SDF-StyleGAN | 3D shape generation · ShapeNet Cars | Recall: 36.2 -> 50.5 | Helped |
| Use NFD instead of SDF-StyleGAN | 3D shape generation · ShapeNet Chairs | FID: 36.5 -> 26.4 | Helped |
| Use NFD instead of SDF-StyleGAN | 3D shape generation · ShapeNet Chairs | Precision: 90.9 -> 92.4 | Helped |
| Use NFD instead of SDF-StyleGAN | 3D shape generation · ShapeNet Chairs | Recall: 87.4 -> 94.8 | Helped |
| Use NFD instead of SDF-StyleGAN | 3D shape generation · ShapeNet Planes | FID: 65.8 -> 32.4 | Helped |
| Use NFD instead of SDF-StyleGAN | 3D shape generation · ShapeNet Planes | Precision: 64.5 -> 70.5 | Helped |
| Use NFD instead of SDF-StyleGAN | 3D shape generation · ShapeNet Planes | Recall: 72.8 -> 81.1 | Helped |
Closest papers by meaning
- Generating Images with 3D Annotations Using Diffusion Models (ICLR 2024 · similarity 0.89)
- Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shape (ICLR 2024 · similarity 0.89)
- A 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale (NeurIPS 2026 · similarity 0.88)
- Mosaic-SDF for 3D Generative Models (CVPR 2024 · similarity 0.88)
- Neural Point Cloud Diffusion for Disentangled 3D Shape and Appearance Generation (CVPR 2024 · similarity 0.88)
- Large-Vocabulary 3D Diffusion Model with Transformer (ICLR 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.