In Search of Inliers: 3D Correspondence by Local and Global Voting

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

We present a method for finding correspondence between 3D models. From an initial set of feature correspondences, our method uses a fast voting scheme to separate the inliers from the outliers. The novelty of our method lies in the use of a combination of local and global constraints to determine if a vote should be cast. On a local scale, we use simple, low-level geometric invariants. On a global scale, we apply covariant constraints for finding compatible correspondences. We guide the sampling for collecting voters by downward dependencies on previous voting stages. All of this together results in an accurate matching procedure. We evaluate our algorithm by controlled and comparative testing on different datasets, giving superior performance compared to state of the art methods. In a final experiment, we apply our method for 3D object detection, showing potential use of our method within higher-level vision.
Original languageEnglish
Title of host publicationIEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Number of pages8
PublisherIEEE
Publication date2014
Pages2075-2082
DOIs
Publication statusPublished - 2014
EventIEEE Conference on Computer Vision and Pattern Recognition - Columbus, OH, United States
Duration: 23. Jun 201428. Jun 2014

Conference

ConferenceIEEE Conference on Computer Vision and Pattern Recognition
CountryUnited States
CityColumbus, OH
Period23/06/201428/06/2014
SeriesI E E E Conference on Computer Vision and Pattern Recognition. Proceedings
ISSN1063-6919

Cite this

Buch, A. G., Yang, Y., Krüger, N., & Petersen, H. G. (2014). In Search of Inliers: 3D Correspondence by Local and Global Voting. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 2075-2082). IEEE. I E E E Conference on Computer Vision and Pattern Recognition. Proceedings https://doi.org/10.1109/CVPR.2014.266
Buch, Anders Glent ; Yang, Yang ; Krüger, Norbert ; Petersen, Henrik Gordon. / In Search of Inliers : 3D Correspondence by Local and Global Voting. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2014. pp. 2075-2082 (I E E E Conference on Computer Vision and Pattern Recognition. Proceedings).
@inproceedings{85db98b28cfb49f19266fb740edacd93,
title = "In Search of Inliers: 3D Correspondence by Local and Global Voting",
abstract = "We present a method for finding correspondence between 3D models. From an initial set of feature correspondences, our method uses a fast voting scheme to separate the inliers from the outliers. The novelty of our method lies in the use of a combination of local and global constraints to determine if a vote should be cast. On a local scale, we use simple, low-level geometric invariants. On a global scale, we apply covariant constraints for finding compatible correspondences. We guide the sampling for collecting voters by downward dependencies on previous voting stages. All of this together results in an accurate matching procedure. We evaluate our algorithm by controlled and comparative testing on different datasets, giving superior performance compared to state of the art methods. In a final experiment, we apply our method for 3D object detection, showing potential use of our method within higher-level vision.",
author = "Buch, {Anders Glent} and Yang Yang and Norbert Kr{\"u}ger and Petersen, {Henrik Gordon}",
year = "2014",
doi = "10.1109/CVPR.2014.266",
language = "English",
series = "I E E E Conference on Computer Vision and Pattern Recognition. Proceedings",
publisher = "IEEE",
pages = "2075--2082",
booktitle = "IEEE Conference on Computer Vision and Pattern Recognition (CVPR)",
address = "United States",

}

Buch, AG, Yang, Y, Krüger, N & Petersen, HG 2014, In Search of Inliers: 3D Correspondence by Local and Global Voting. in IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, I E E E Conference on Computer Vision and Pattern Recognition. Proceedings, pp. 2075-2082, IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, United States, 23/06/2014. https://doi.org/10.1109/CVPR.2014.266

In Search of Inliers : 3D Correspondence by Local and Global Voting. / Buch, Anders Glent; Yang, Yang; Krüger, Norbert; Petersen, Henrik Gordon.

IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2014. p. 2075-2082 (I E E E Conference on Computer Vision and Pattern Recognition. Proceedings).

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

TY - GEN

T1 - In Search of Inliers

T2 - 3D Correspondence by Local and Global Voting

AU - Buch, Anders Glent

AU - Yang, Yang

AU - Krüger, Norbert

AU - Petersen, Henrik Gordon

PY - 2014

Y1 - 2014

N2 - We present a method for finding correspondence between 3D models. From an initial set of feature correspondences, our method uses a fast voting scheme to separate the inliers from the outliers. The novelty of our method lies in the use of a combination of local and global constraints to determine if a vote should be cast. On a local scale, we use simple, low-level geometric invariants. On a global scale, we apply covariant constraints for finding compatible correspondences. We guide the sampling for collecting voters by downward dependencies on previous voting stages. All of this together results in an accurate matching procedure. We evaluate our algorithm by controlled and comparative testing on different datasets, giving superior performance compared to state of the art methods. In a final experiment, we apply our method for 3D object detection, showing potential use of our method within higher-level vision.

AB - We present a method for finding correspondence between 3D models. From an initial set of feature correspondences, our method uses a fast voting scheme to separate the inliers from the outliers. The novelty of our method lies in the use of a combination of local and global constraints to determine if a vote should be cast. On a local scale, we use simple, low-level geometric invariants. On a global scale, we apply covariant constraints for finding compatible correspondences. We guide the sampling for collecting voters by downward dependencies on previous voting stages. All of this together results in an accurate matching procedure. We evaluate our algorithm by controlled and comparative testing on different datasets, giving superior performance compared to state of the art methods. In a final experiment, we apply our method for 3D object detection, showing potential use of our method within higher-level vision.

U2 - 10.1109/CVPR.2014.266

DO - 10.1109/CVPR.2014.266

M3 - Article in proceedings

T3 - I E E E Conference on Computer Vision and Pattern Recognition. Proceedings

SP - 2075

EP - 2082

BT - IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

PB - IEEE

ER -

Buch AG, Yang Y, Krüger N, Petersen HG. In Search of Inliers: 3D Correspondence by Local and Global Voting. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE. 2014. p. 2075-2082. (I E E E Conference on Computer Vision and Pattern Recognition. Proceedings). https://doi.org/10.1109/CVPR.2014.266