{"ID":2836602,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.21887","arxiv_id":"2511.21887","title":"UniArt: Unified 3D Representation for Generating 3D Articulated Objects with Open-Set Articulation","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.","short_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 m...","url_abs":"https://arxiv.org/abs/2511.21887","url_pdf":"https://arxiv.org/pdf/2511.21887v1","authors":"[\"Bu Jin\",\"Weize Li\",\"Songen Gu\",\"Yupeng Zheng\",\"Yuhang Zheng\",\"Zhengyi Zhou\",\"Yao Yao\"]","published":"2025-11-26T20:09:11Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}