用一张图生成可动3D模型，支持新关节类型
UniArt: Unified 3D Representation for Generating 3D Articulated Objects with Open-Set Articulation
- 统一编码几何、纹理、部件和运动参数的潜在表示
- 在PartNet-Mobility上达到最优网格质量和关节精度
- 无需预设关节类型，可生成未见过的新关节和物体
可动3D物体在真实模拟和具身机器人中至关重要，但手动构建成本高且难以扩展。本文提出UniArt，一种基于扩散模型的端到端框架，仅需单张图像即可生成完整可动3D对象。与以往多阶段方法不同，UniArt建立统一的潜在表示，联合编码几何、纹理、部件分割和运动学参数。引入可逆的关节-体素嵌入，将关节特征空间对齐到体素几何，使模型同时学习连贯的运动行为与结构形成。此外，将关节类型预测建模为开集问题，无需固定关节语义，实现对新关节类别和未见物体类型的泛化。在PartNet-Mobility基准上的实验表明，UniArt在网格质量和关节准确性方面达到当前最优。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。