Particulate: Feed-Forward 3D Object Articulation

TL;DR

Particulate is a fast, transformer-based model that infers 3D object articulations from meshes, enabling quick, accurate, and versatile articulation estimation for both real and AI-generated assets.

Contribution

The paper introduces Particulate, a novel feed-forward transformer model for 3D articulation inference, and a new benchmark for evaluation.

Findings

Particulate outperforms existing methods in accuracy.

Inference is significantly faster than prior optimization-based approaches.

Works effectively on both real and AI-generated 3D assets.

Abstract

We introduce Particulate, a feed-forward model that, given a 3D mesh of an object, infers its articulations, including its 3D parts, their kinematic structure, and the motion constraints. The model is based on a transformer network, the Part Articulation Transformer, which predicts all these parameters for all joints. We train the network end-to-end on a diverse collection of articulated 3D assets from public datasets. During inference, Particulate maps the output of the network back to the input mesh, yielding a fully articulated 3D model in seconds, much faster than prior approaches that require per-object optimization. Particulate also works on AI-generated 3D assets, enabling the generation of articulated 3D objects from a single (real or synthetic) image when combined with an off-the-shelf image-to-3D model. We further introduce a new challenging benchmark for 3D articulation estimation curated from high-quality public 3D assets, and redesign the evaluation protocol to be more consistent with human preferences. Empirically, Particulate significantly outperforms state-of-the-art approaches.