Research map / 3D vision / Face and shape
ShapeCrafter: A Recursive Text-Conditioned 3D Shape Generation Model
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 |
|---|---|---|---|
| recursive generation with phrase sequences instead of single-step AutoSDF | ShapeCrafter · Text2Shape chairs | CLIP-S: 48.92 -> 52.43 | Helped |
| recursive generation instead of AutoSDF | ShapeCrafter · Text2Shape chairs | FID: 18.45 -> 16.36 | Helped |
| recursive generation vs AutoSDF as phrase count grows | ShapeCrafter · Text2Shape++ >4 phrases | FID: 22.47 -> 16.89 | Helped |
| recursive generation vs AutoSDF on short inputs | ShapeCrafter · Text2Shape++ 1-2 phrases | SGLOT-C: 0.53 -> 0.47 | Hurt |
| add conditional training with residual blocks (ablation) | ShapeCrafter · Text2Shape chairs | CLIP-S: 49.53 -> 52.43 | Helped |
| add conditional training with residual blocks (ablation) | ShapeCrafter · Text2Shape chairs | FID: 20.22 -> 16.36 | Helped |
| add random transformer after residual blocks (ablation) | ShapeCrafter · Text2Shape chairs | FID: 19.83 -> 16.36 | Helped |
| add random transformer after residual blocks (ablation) | ShapeCrafter · Text2Shape chairs | CLIP-S: 49.29 -> 52.43 | Helped |
| reorder transformer generation by distribution change (ablation) | ShapeCrafter · Text2Shape chairs | CLIP-S: 42.47 -> 52.43 | Helped |
| reorder transformer generation by distribution change (ablation) | ShapeCrafter · Text2Shape chairs | FID: 16.67 -> 16.36 | Helped |
| add more phrases to the description | ShapeCrafter · latent distribution | mean entropy H: 0.423 -> 0.267 | Helped |
Closest papers by meaning
- ShapeWalk: Compositional Shape Editing Through Language-Guided Chains (CVPR 2024 · similarity 0.89)
- ShapeWords: Guiding Text-to-Image Synthesis with 3D Shape-Aware Prompts (CVPR 2025 · similarity 0.88)
- Controllable Dynamic 3D Shape Generation via 3D Trajectories and Text (NeurIPS 2026 · similarity 0.87)
- HyperSDFusion: Bridging Hierarchical Structures in Language and Geometry for Enhanced 3D Text2Shape Generation (CVPR 2024 · similarity 0.87)
- ShapeCraft: LLM Agents for Structured, Textured and Interactive 3D Modeling (NeurIPS 2025 · similarity 0.87)
- ShapeShifter: 3D Variations Using Multiscale and Sparse Point-Voxel Diffusion (CVPR 2025 · similarity 0.87)
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.