We address the problem of building digital twins of unknown articulated objects from two RGBD scans of the object at different articulation states. We decompose the problem into two stages, each addressing distinct aspects. Our method first reconstructs object-level shape at each state, then recovers the underlying articulation model including part segmentation and joint articulations that associate the two states. By explicitly modeling point-level correspondences and exploiting cues from images, 3D reconstructions, and kinematics, our method yields more accurate and stable results compared to prior work. It also handles more than one movable part and does not rely on any object shape or structure priors. Project page: https://github.com/NVlabs/DigitalTwinArt

中文翻译：

---

用于构建未知铰接物体数字孪生的神经隐式表示

我们解决了根据不同关节状态下物体的两次 RGBD 扫描构建未知关节物体的数字孪生的问题。我们将问题分解为两个阶段，每个阶段解决不同的方面。我们的方法首先重建每个状态的对象级形状，然后恢复底层的关节模型，包括关联两个状态的部分分割和关节关节。通过显式地建模点级对应关系并利用图像、3D 重建和运动学的线索，与之前的工作相比，我们的方法产生了更准确、更稳定的结果。它还可以处理多个可移动部件，并且不依赖于任何物体形状或结构先验。项目页面：https://github.com/NVlabs/DigitalTwinArt