Prompting Image Generators for Training-free Primitive Shape Abstraction
Quick summary
arXiv:2607.05568v2 Announce Type: replace-cross Abstract: Compact primitive abstractions represent 3D shapes with a few geometric primitives while preserving recognizable components. Learned methods depend on their training classes, and optimization-based methods split shapes geometrically rather than into parts. We instead reuse the visual part knowledge of pretrained models without task-specific training or fine-tuning. A vision-language model names parts in multi-view renders, and an unmodified image generator paints color-coded part masks. Reprojection and spatial clustering recover 3D ins
Key takeaways
- arXiv:2607.05568v2 Announce Type: replace-cross Abstract: Compact primitive abstractions represent 3D shapes with a few geometric primitives while preserving recognizable components.
- Learned methods depend on their training classes, and optimization-based methods split shapes geometrically rather than into parts.
- We instead reuse the visual part knowledge of pretrained models without task-specific training or fine-tuning.
Why it matters
This model development creates a new option for users and a new testing obligation for developers. A fixed evaluation set comparing quality, cost and failure behavior is more useful than launch claims.
Member comments