Skip to yearly menu bar Skip to main content


Poster

Neural Implicit Representation for Building Digital Twins of Unknown Articulated Objects

Yijia Weng · Bowen Wen · Jonathan Tremblay · Valts Blukis · Dieter Fox · Leonidas Guibas · Stan Birchfield

Arch 4A-E Poster #290
[ ] [ Project Page ]
[ Poster
Wed 19 Jun 10:30 a.m. PDT — noon PDT

Abstract:

We tackle 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://digitaltwinart.github.io/digitaltwinart2023/

Chat is not available.