USDCraft: Geometrically Grounded Programmatic Modeling of Articulated 3D Assets for Simulation

Key points

• Geometrically faithful and functional articulated 3D assets are essential for real-to-sim robot manipulation, where policies trained in simulation must transfer to physical objects.1
• Recent mesh-based methods learn to infer articulation from annotated 3D assets, but deployment remains challenging when real-world objects fall outside the training distribution or their meshes are incomplete or corrupted.1
• We propose source geometry analysis, which converts the source mesh into a metric textual description that distinguishes observed surface from unknown space, and iterative geometric rechecking, which re-encodes each candidate in the same representation so that discrepancies point to program edits while unobserved regions remain open to completion.1
• Experiments demonstrate leading articulation recovery on two benchmarks and validate USDCraft's effectiveness for real-to-sim-to-real robot manipulation.1

Sources (2)

• [1]USDCraft: Geometrically Grounded Programmatic Modeling of Articulated 3D Assets for Simulation
  Hugging Face Daily Papers · Oct 8, 12:00 AM

  To address these limitations, we formulate articulated asset reconstruction as programmatic modeling grounded in partial geometric evidence and introduce USDCraft, a framework in which a pretrained LLM writes and revises executable programs for simulation-ready articulated assets without task-specific training.

  Geometrically faithful and functional articulated 3D assets are essential for real-to-sim robot manipulation, where policies trained in simulation must transfer to physical objects.

• [2]USDCraft: Geometrically Grounded Programmatic Modeling of Articulated 3D Assets for Simulation
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 06:23 AM · same content

Extractive summary: sentences quoted from the sources.