Skip to content

FACT: Fidelity-Aware Construction of Articulated Twins

Sep 2026 · 0 citations · 60 references
Computer Science

TL;DR

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.

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.

View source

Similar papers

Preprint Oct 2026

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

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. Recent mesh-based methods learn to infer articulation from annotated 3D assets, but deployment remains challenging when real-world objects...

Chuan-Rui Zhang, Zai-Jia Yang, Duo-Min Wang et al. · 0 citations
Preprint Aug 2026

ArtLang: Structured Language-to-Kinematics Grounding for Articulated 3D Actuation

This work presents ArtLang, a framework for open-vocabulary language control of persistent reconstructed articulated assets, which represents an asset as a semantic-kinematic articulation graph and augments its surface with language features and graph-constrained motion.

Sylvia Yuan, Dan Wang, Ravi Ramamoorthi et al. · 0 citations
Preprint Aug 2026

ArtiMo: Agent-Driven Articulated Mesh Animation

ArtiMo, a novel agent-driven framework for text-guided articulated mesh animation, develops an agentic pipeline powered by Large Language and Vision-Language Models (LLMs/VLMs) to orchestrate motion generation without requiring model fine-tuning.

Chun-Yu Zou, Peng Dai, Yi-Hua Huang et al. · 0 citations
Preprint Sep 2026

DeformSmith: Physics Harness-Guided Hierarchical Generation of Deformable Assets for Robot Manipulation

Creating deformable assets for robot manipulation requires jointly specifying their geometry, appearance, and physical properties. This is especially challenging for deformable objects, since text and images provide limited evidence about how they deform and respond to contact, yet these responses directly affect their...

Can Li, Jie Gu, Zi-Shun Deng et al. · 0 citations
#machine learning Preprint Sep 2026

GaussianBench: Physics-Fidelity Evaluation for Gaussian Scene Representations

3D Gaussian Splatting has evolved from static reconstruction toward physics-integrated representations meant to predict how scenes change under interaction. This creates an evaluation problem: a rollout can look plausible while relying on incorrect internal mechanics, and visual agreement with observed motion does not...

Chukwudalu Dumebi-Kachikwu · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.