# StackGen3D: Generating Stable 3D Block Stack Structures from Multiview Silhouettes

- Source: arXiv cs.RO
- Published: 2026-10-26T04:00:00.000Z
- RoboHot: https://robohot.news/en/items/u0kvfi5o5f3d8k8058laqxwqs
- Original: https://arxiv.org/abs/2610.31803

## Summary

The StackGen3D framework generates stable block assembly structures from a given block inventory and three orthographic silhouette images. It first uses a physics-informed graph neural network (PI-GNN) to model support relationships between blocks and to curate a dataset of stable structures, then trains a conditional flow-matching model to learn the multimodal distribution of block configurations that match the target silhouettes. In preliminary experiments, Best-of-10 selection raised physical stability from 45.3% to 72.4%, with a silhouette IoU of 0.970.