Show simple item record

dc.contributor.authorGao, Wei
dc.contributor.authorTedrake, Russ
dc.date.accessioned2021-11-05T20:53:18Z
dc.date.available2021-11-05T20:53:18Z
dc.date.issued2019-06
dc.identifier.urihttps://hdl.handle.net/1721.1/137623
dc.description.abstractProbabilistic point-set registration methods have been gaining more attention for their robustness to noise, outliers and occlusions. However, these methods tend to be much slower than the popular iterative closest point (ICP) algorithms, which severely limits their usability. In this paper, we contribute a novel probabilistic registration method that achieves state-of-the-art robustness as well as substantially faster computational performance than modern ICP implementations. This is achieved using a rigorous yet computationally-efficient probabilistic formulation. Point-set registration is cast as a maximum likelihood estimation and solved using the EM algorithm. We show that with a simple augmentation, the E step can be formulated as a filtering problem, allowing us to leverage advances in efficient Gaussian filtering methods. We also propose a customized permutohedral filter [1] for improved efficiency while retaining sufficient accuracy for our task. Additionally, wepresent a simple and efficient twist parameterization that generalizes our method to the registration of articulated and deformable objects. For articulated objects, the complexity of our method is almost independent of the Degrees Of Freedom (DOFs). The results demonstrate the proposed method consistently outperforms many competitive baselines on a variety of registration tasks. The video demo and source code are available on our project pageen_US
dc.language.isoen
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en_US
dc.relation.isversionof10.1109/cvpr.2019.01135en_US
dc.rightsCreative Commons Attribution-Noncommercial-Share Alikeen_US
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0/en_US
dc.sourcearXiven_US
dc.titleFilterReg: Robust and Efficient Probabilistic Point-Set Registration Using Gaussian Filter and Twist Parameterizationen_US
dc.typeArticleen_US
dc.identifier.citationGao, Wei and Tedrake, Russ. 2019. "FilterReg: Robust and Efficient Probabilistic Point-Set Registration Using Gaussian Filter and Twist Parameterization." 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
dc.contributor.departmentMassachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
dc.contributor.departmentMassachusetts Institute of Technology. Department of Aeronautics and Astronautics
dc.contributor.departmentMassachusetts Institute of Technology. Department of Mechanical Engineering
dc.relation.journal2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)en_US
dc.eprint.versionAuthor's final manuscripten_US
dc.type.urihttp://purl.org/eprint/type/ConferencePaperen_US
eprint.statushttp://purl.org/eprint/status/NonPeerRevieweden_US
dc.date.updated2021-01-27T17:55:13Z
dspace.orderedauthorsGao, W; Tedrake, Ren_US
dspace.date.submission2021-01-27T17:55:15Z
mit.licenseOPEN_ACCESS_POLICY
mit.metadata.statusAuthority Work and Publication Information Neededen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record