Particulate：前馈式三维物体关节化
Particulate: Feed-Forward 3D Object Articulation
把关节物体的部件分割、运动学树与运动约束统一到一个前馈 Transformer 中一次预测，替代逐物体优化，可直接接到 image-to-3D 模型后面做单图生成可动 3D 资产。
原文依据 a feed-forward model that, given a 3D mesh of an object, infers its articulations
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出 Particulate，一个前馈模型：给定物体的三维网格，推断其关节结构，包括三维部件、部件的运动学结构以及运动约束。该模型基于一个 Transformer 网络——部件关节 Transformer，为所有关节预测上述全部参数。我们在来自公开数据集的多样化关节三维资产集合上端到端训练该网络。推理时，Particulate 将网络输出映射回输入网格，在数秒内得到完整可动的三维模型，远快于此前需要逐物体优化的方法。Particulate 同样适用于 AI 生成的三维资产，与现成的图像到三维模型结合后，可由单张（真实或合成）图像生成关节化三维物体。我们进一步提出一个具有挑战性的三维关节估计新基准，其数据精选自高质量公开三维资产，并重新设计评测协议，使其更符合人类偏好。实验表明，Particulate 显著优于最优方法。
英文原文摘要 1111 字符
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.