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:
this https URL

我们通过两个不同关节状态的物体的两个 RGBD 扫描构建未知关节物体的数字孪生问题，通过分解成两个阶段并采用显式建模，我们的方法能够重建物体形状并恢复关节模型，通过利用图像、3D 重建和运动学信息，我们的方法相比之前的工作具有更高的准确性和稳定性，并且能够处理多个活动部件并不依赖于任何物体形状或结构的先验知识。