ArtiMo: Agent-Driven Articulated Mesh Animation

2026-08-20

AI Summary

为解决文本驱动3D网格动画中的运动协调问题，提出ArtiMo框架，利用大语言模型和视觉-语言模型生成因果连贯的动画，无需微调模型。

Abstract

Animating articulated 3D meshes via text requires satisfying strict kinematic constraints, modeling causal interactions between parts, and achieving instruction fidelity. Due to the absence of task-specific training data and explicit articulation supervision, existing data-driven mesh animation methods are largely inapplicable to this setting. To address this, we propose ArtiMo, a novel agent-driven framework for text-guided articulated mesh animation. Operating in a zero-shot manner, ArtiMo develops an agentic pipeline powered by Large Language and Vision-Language Models (LLMs/VLMs) to orchestrate motion generation. By synergizing the explicit kinematic constraints of URDF with the agent's reasoning and planning capabilities, it effectively produces causally coherent part motions and interactions without requiring model fine-tuning. To ensure motion correctness, the agent additionally utilizes a visual self-improvement mechanism: generated animations are rendered into compact keyframes and motion cues, enabling the VLM to iteratively diagnose and correct errors. Furthermore, we contribute a new benchmark dataset spanning 21 articulated object categories, featuring high-quality motion annotations enriched with causal relationships. Extensive experiments demonstrate that ArtiMo significantly outperforms baselines, particularly on complex, causally driven motions. The project page is available at https://zou-2004.github.io/ArtiMo/.

Problem

• text-guided
• articulated mesh animation
• kinematic constraints
• causal interactions
• instruction fidelity

Innovation

• Agent-Driven Framework
• Text-Guided Animation
• Zero-Shot Operation
• Visual Self-Improvement Mechanism
• Causal Coherence