FACT: Fidelity-Aware Construction of Articulated Twins

2026-09-29

AI Summary

This study addresses the susceptibility of existing visually plausible articulated assets to failure during contact interactions and their inaccurate motion. To overcome these limitations, this work proposes FACT, an agent framework that constructs high-fidelity articulated digital twins through an iterative evidence-diagnosis-revision closed loop. Methodologically, it introduces a shared editable representation that integrates quantitative feedback to drive geometric reconstruction, collision proxy repair, and simulation residual-guided physical parameter fitting. Furthermore, the framework incorporates feature planning alongside task-aware local repartitioning strategies. Experimental results demonstrate that this approach substantially improves both geometric reconstruction accuracy and interaction reliability, reproducing physical responses with greater fidelity than direct inference methods.

Abstract

Visually plausible articulated assets may still fail during contact interactions or exhibit inaccurate motion. We present FACT (Fidelity-Aware Construction of Articulated Twins), an agentic framework that progressively constructs articulated twins to improve geometry, contact, and dynamic fidelity. The agent drives an evidence--diagnosis--revision loop on a shared editable representation, selecting measurements and model edits using quantitative feedback, while numerical tools execute and validate the updates. It reconstructs editable articulated geometry from images through feature planning, targeted measurements, and diagnostic refinement. On this reference, it repairs collision proxies through task-aware local repartitioning before fidelity-constrained compression. Finally, it constructs response models from passive-response videos, using simulation residuals to guide model revision and constrained physical parameter fitting. Experiments show that FACT improves geometric reconstruction over baselines, enables more reliable interaction with simpler collision proxies, and better reproduces held-out physical responses than direct parameter inference.

Problem

• Articulated Twins
• Contact Interaction
• Dynamic Fidelity
• Geometry Reconstruction
• Digital Assets

Innovation

• Articulated Twins
• Agentic Framework
• Evidence-Diagnosis-Revision Loop
• Collision Proxy Repair
• Simulation Residuals