arXiv Analytics

Sign in

arXiv:2306.00979 [cs.CV]AbstractReferencesReviewsResources

Building Rearticulable Models for Arbitrary 3D Objects from 4D Point Clouds

Shaowei Liu, Saurabh Gupta, Shenlong Wang

Published 2023-06-01Version 1

We build rearticulable models for arbitrary everyday man-made objects containing an arbitrary number of parts that are connected together in arbitrary ways via 1 degree-of-freedom joints. Given point cloud videos of such everyday objects, our method identifies the distinct object parts, what parts are connected to what other parts, and the properties of the joints connecting each part pair. We do this by jointly optimizing the part segmentation, transformation, and kinematics using a novel energy minimization framework. Our inferred animatable models, enables retargeting to novel poses with sparse point correspondences guidance. We test our method on a new articulating robot dataset, and the Sapiens dataset with common daily objects, as well as real-world scans. Experiments show that our method outperforms two leading prior works on various metrics.

Comments: Accepted to CVPR 2023. Project page: https://stevenlsw.github.io/reart
Categories: cs.CV
Related articles:
arXiv:2203.16482 [cs.CV] (Published 2022-03-30)
RFNet-4D: Joint Object Reconstruction and Flow Estimation from 4D Point Clouds
arXiv:1906.05105 [cs.CV] (Published 2019-06-12)
Pose from Shape: Deep Pose Estimation for Arbitrary 3D Objects
arXiv:1903.01695 [cs.CV] (Published 2019-03-05)
Real-time Multiple People Hand Localization in 4D Point Clouds