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; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp. 3141-3150

Abstract

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

Related Material

[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Weng_2024_CVPR, author = {Weng, Yijia and Wen, Bowen and Tremblay, Jonathan and Blukis, Valts and Fox, Dieter and Guibas, Leonidas and Birchfield, Stan}, title = {Neural Implicit Representation for Building Digital Twins of Unknown Articulated Objects}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3141-3150} }