A unified framework that decomposes monolithic 3D meshes into 'sim-ready' interactive articulated assets using a sparse 3D VQ-VAE.
March 25, 2026
Original Paper
SIMART: Decomposing Monolithic Meshes into Sim-ready Articulated Assets via MLLM
arXiv · 2603.23386
The Takeaway
Generative 3D usually produces static objects; this method bridges the gap to Embodied AI by automatically predicting kinematics and part-level decomposition. It reduces token counts by 70% while enabling immediate physics-based simulation in robotics environments.
From the abstract
High-quality articulated 3D assets are indispensable for embodied AI and physical simulation, yet 3D generation still focuses on static meshes, leaving a gap in "sim-ready" interactive objects. Most recent articulated object creation methods rely on multi-stage pipelines that accumulate errors across decoupled modules. Alternatively, unified MLLMs offer a single-stage path to joint static asset understanding and sim-ready asset generation. However dense voxel-based 3D tokenization yields long 3D