Hierarchical Multi-Level 3D Geometry Generation with Stress-Aware Learning

TMLR Paper6341 Authors

Abstract: Current approaches for Lego 3d structural assembly are usually learned to maximize intersection over union between generated output and target construction. We propose a new approach which is able to build stable structures based on physics-aware reward. Our method employs a two-level agent architecture in which a high-level proximal policy optimization based planner proposes a scheme, while a low-level wave function collapse agent handles precise brick placement with constraint satisfaction. Experimental results demonstrate that our hierarchical method consistently constructs buildings that satisfy stress constraints while reducing material usage. We also show that replacing the computationally expensive finite element method solver with a fast Fourier neural operator achieves comparable performance, confirming the approach's scalability for large-scale problems.

Submission Type: Regular submission (no more than 12 pages of main content)

Changes Since Last Submission:

Changes in the scope of review
https://openreview.net/forum?id=kyoXKiyoA3&noteId=Tz6DTwdvZF

Assigned Action Editor: ~Weijian_Deng1

Submission Number: 6341