Neural Implicit Representation for Building Digital Twins of Unknown Articulated Objects
This addresses the challenge of creating digital twins for articulated objects in robotics or simulation, representing an incremental improvement over prior methods.
The paper tackles the problem of building digital twins of unknown articulated objects from two RGBD scans, achieving more accurate and stable results by decomposing the task into shape reconstruction and articulation recovery without relying on object priors.
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