ArtLLM: Generating Articulated Assets via 3D LLM

TL;DR

ArtLLM is a new framework that generates detailed articulated 3D objects from complete meshes, improving layout accuracy and joint prediction over existing methods, with applications in digital twins and robot learning.

Contribution

Introduces ArtLLM, a 3D multimodal large language model that predicts parts and joints from point clouds, enabling high-quality articulated asset generation from complete meshes.

Findings

Outperforms state-of-the-art in part layout accuracy

Achieves superior joint prediction results

Generalizes well to real-world objects

Abstract

Creating interactive digital environments for gaming, robotics, and simulation relies on articulated 3D objects whose functionality emerges from their part geometry and kinematic structure. However, existing approaches remain fundamentally limited: optimization-based reconstruction methods require slow, per-object joint fitting and typically handle only simple, single-joint objects, while retrieval-based methods assemble parts from a fixed library, leading to repetitive geometry and poor generalization. To address these challenges, we introduce ArtLLM, a novel framework for generating high-quality articulated assets directly from complete 3D meshes. At its core is a 3D multimodal large language model trained on a large-scale articulation dataset curated from both existing articulation datasets and procedurally generated objects. Unlike prior work, ArtLLM autoregressively predicts a variable number of parts and joints, inferring their kinematic structure in a unified manner from the object's point cloud. This articulation-aware layout then conditions a 3D generative model to synthesize high-fidelity part geometries. Experiments on the PartNet-Mobility dataset show that ArtLLM significantly outperforms state-of-the-art methods in both part layout accuracy and joint prediction, while generalizing robustly to real-world objects. Finally, we demonstrate its utility in constructing digital twins, highlighting its potential for scalable robot learning.