Instruct-Particulate: 基于运动学控制的可扩展前馈式3D物体关节化
Instruct-Particulate: Scaling Feed-Forward 3D Object Articulation with Kinematic Control
AI总结：
提出Instruct-Particulate模型，通过运动学规范（部件描述、连接性、关节类型等）指导3D网格的关节分割和运动参数预测，利用异构数据集（15万+物体）训练，实现跨类别和AI生成网格的泛化。
摘要：
重建关节式3D物体对于动画、游戏和机器人模拟至关重要。最近的神经网络可以估计3D物体的关节结构，但其泛化能力仍然受到该任务标注数据稀缺的限制。为了解决这一差距，我们引入了Instruct-Particulate，一个模型，它接受一个3D网格以及一个目标运动学规范，包括部件描述、连接性、关节类型和可选的点提示，并预测相应的运动学部件分割和关节运动参数。运动学规范消除了任务的歧义，并允许模型针对不同粒度的标注，从而使得使用更丰富的异构训练数据成为可能。在测试时，运动学规范可以从大规模视觉-语言模型中自动获得，因此该模型可以应用于任何输入网格。为了大规模训练我们的模型，我们构建了一个包含超过15万个关节式3D物体的异构数据集，通过使用视觉-语言模型对部分其他3D模型（整体或已分解为部件）进行运动学标注，扩展了现有的公开数据集。实验表明，我们的模型在跨类别和AI生成网格上泛化更好，通过图像到3D模型实现了从真实世界图像重建关节式资产。
英文摘要：
Reconstructing articulated 3D objects is important for animation, gaming, and robotic simulations. Recent neural networks can estimate the articulated structure of 3D objects, but their generalization remains limited by the scarcity of annotated data for this task. To address this gap, we introduce Instruct-Particulate, a model that takes a 3D mesh together with a target kinematic specification, including part descriptions, connectivity, joint types, and optional point prompts, and predicts the corresponding kinematic part segmentation and joint motion parameters. The kinematic specification disambiguates the task and allows the model to target annotations of different granularity, thereby making it possible to use more abundant heterogeneous training data. At test time, the kinematic specification can be obtained automatically from large-scale vision-language models, so the model can be applied to any input mesh. To train our model at scale, we construct a heterogeneous dataset of more than 150,000 articulated 3D objects, extending existing publicly available collections with data obtained by partially labelling other 3D models (monolithic or already decomposed into parts) with kinematic labels by means of vision-language models. Experiments show that our model generalizes better across categories and to AI-generated meshes, enabling articulated asset reconstruction from real-world images via image-to-3D models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
