Research map / 3D vision / 3D generation
Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation
Rui Chen, Yongwei Chen, Ningxin Jiao, Kui Jia
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 |
|---|---|---|---|
| disentangle geometry and appearance learning instead of a single entangled network (ablation) | Fantasia3D · stone bust prompt (qualitative) | visual quality | Improved |
| use rendered normal map as shape encoding instead of shaded image with fixed material (ablation) | Fantasia3D geometry stage · stone bust prompt (qualitative) | geometry quality | Improved |
| use full BRDF material instead of simple diffuse color rendering (ablation) | Fantasia3D appearance stage · stone bust prompt (qualitative) | realism | Improved |
| add UV edge padding when exporting textures | Fantasia3D texturing · texture export (qualitative) | seam artifacts | Improved |
| add random rotation augmentation to normal map input | Fantasia3D geometry stage · geometry alignment with text | text-geometry alignment | Improved |
| Fantasia3D vs Latent-NeRF with same input meshes | user-guided generation · user-guided generation (qualitative) | geometry and texture quality | Improved |
Closest papers by meaning
- DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Data (CVPR 2024 · similarity 0.89)
- ViewDiff: 3D-Consistent Image Generation with Text-to-Image Models (CVPR 2024 · similarity 0.89)
- VP3D: Unleashing 2D Visual Prompt for Text-to-3D Generation (CVPR 2024 · similarity 0.89)
- ArtiScene: Language-Driven Artistic 3D Scene Generation Through Image Intermediary (CVPR 2025 · similarity 0.88)
- DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior (ICLR 2024 · similarity 0.88)
- Disentangled 3D Scene Generation with Layout Learning (ICML 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.
