UniArt: Unified 3D Representation for Generating 3D Articulated Objects with Open-Set Articulation

TL;DR

UniArt is a diffusion-based framework that synthesizes fully articulated 3D objects from a single image, enabling open-set articulation prediction and achieving state-of-the-art quality and accuracy.

Contribution

UniArt introduces a unified latent representation and reversible joint-to-voxel embedding for end-to-end 3D articulated object synthesis from images.

Findings

Achieves state-of-the-art mesh quality on PartNet-Mobility

Demonstrates accurate articulation prediction including unseen categories

Enables open-set generalization to novel joint types

Abstract

Articulated 3D objects play a vital role in realistic simulation and embodied robotics, yet manually constructing such assets remains costly and difficult to scale. In this paper, we present UniArt, a diffusion-based framework that directly synthesizes fully articulated 3D objects from a single image in an end-to-end manner. Unlike prior multi-stage techniques, UniArt establishes a unified latent representation that jointly encodes geometry, texture, part segmentation, and kinematic parameters. We introduce a reversible joint-to-voxel embedding, which spatially aligns articulation features with volumetric geometry, enabling the model to learn coherent motion behaviors alongside structural formation. Furthermore, we formulate articulation type prediction as an open-set problem, removing the need for fixed joint semantics and allowing generalization to novel joint categories and unseen object types. Experiments on the PartNet-Mobility benchmark demonstrate that UniArt achieves state-of-the-art mesh quality and articulation accuracy.