Exploiting uncertainty in regression forests for accurate camera relocalization

Julien Valentin; Matthias Nießner; Jamie Shotton; Andrew Fitzgibbon; Shahram Izadi; Philip Torr

doi:10.1109/CVPR.2015.7299069

Exploiting uncertainty in regression forests for accurate camera relocalization

Julien Valentin
, Matthias Nießner
, Jamie Shotton
, Andrew Fitzgibbon
, Shahram Izadi
, Philip Torr

University of Oxford
Stanford University
Microsoft Research

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

141 Scopus citations

Abstract

Recent advances in camera relocalization use predictions from a regression forest to guide the camera pose optimization procedure. In these methods, each tree associates one pixel with a point in the scene's 3D world coordinate frame. In previous work, these predictions were point estimates and the subsequent camera pose optimization implicitly assumed an isotropic distribution of these estimates. In this paper, we train a regression forest to predict mixtures of anisotropic 3D Gaussians and show how the predicted uncertainties can be taken into account for continuous pose optimization. Experiments show that our proposed method is able to relocalize up to 40% more frames than the state of the art.

Original language	English
Title of host publication	IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
Publisher	IEEE Computer Society
Pages	4400-4408
Number of pages	9
ISBN (Electronic)	9781467369640
DOIs	https://doi.org/10.1109/CVPR.2015.7299069
State	Published - 14 Oct 2015
Externally published	Yes
Event	IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 - Boston, United States Duration: 7 Jun 2015 → 12 Jun 2015

Publication series

Name	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume	07-12-June-2015
ISSN (Print)	1063-6919

Conference

Conference	IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
Country/Territory	United States
City	Boston
Period	7/06/15 → 12/06/15

Access to Document

10.1109/CVPR.2015.7299069

Cite this

Valentin, J., Nießner, M., Shotton, J., Fitzgibbon, A., Izadi, S., & Torr, P. (2015). Exploiting uncertainty in regression forests for accurate camera relocalization. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 (pp. 4400-4408). Article 7299069 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 07-12-June-2015). IEEE Computer Society. https://doi.org/10.1109/CVPR.2015.7299069

@inproceedings{301b03187b504b0093499a8099e5f94f,

title = "Exploiting uncertainty in regression forests for accurate camera relocalization",

abstract = "Recent advances in camera relocalization use predictions from a regression forest to guide the camera pose optimization procedure. In these methods, each tree associates one pixel with a point in the scene's 3D world coordinate frame. In previous work, these predictions were point estimates and the subsequent camera pose optimization implicitly assumed an isotropic distribution of these estimates. In this paper, we train a regression forest to predict mixtures of anisotropic 3D Gaussians and show how the predicted uncertainties can be taken into account for continuous pose optimization. Experiments show that our proposed method is able to relocalize up to 40\% more frames than the state of the art.",

author = "Julien Valentin and Matthias Nie{\ss}ner and Jamie Shotton and Andrew Fitzgibbon and Shahram Izadi and Philip Torr",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 ; Conference date: 07-06-2015 Through 12-06-2015",

year = "2015",

month = oct,

day = "14",

doi = "10.1109/CVPR.2015.7299069",

language = "English",

series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

publisher = "IEEE Computer Society",

pages = "4400--4408",

booktitle = "IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015",

}

Valentin, J, Nießner, M, Shotton, J, Fitzgibbon, A, Izadi, S & Torr, P 2015, Exploiting uncertainty in regression forests for accurate camera relocalization. in IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015., 7299069, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 07-12-June-2015, IEEE Computer Society, pp. 4400-4408, IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, United States, 7/06/15. https://doi.org/10.1109/CVPR.2015.7299069

Exploiting uncertainty in regression forests for accurate camera relocalization. / Valentin, Julien; Nießner, Matthias; Shotton, Jamie et al.
IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015. IEEE Computer Society, 2015. p. 4400-4408 7299069 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 07-12-June-2015).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Exploiting uncertainty in regression forests for accurate camera relocalization

AU - Valentin, Julien

AU - Nießner, Matthias

AU - Shotton, Jamie

AU - Fitzgibbon, Andrew

AU - Izadi, Shahram

AU - Torr, Philip

PY - 2015/10/14

Y1 - 2015/10/14

N2 - Recent advances in camera relocalization use predictions from a regression forest to guide the camera pose optimization procedure. In these methods, each tree associates one pixel with a point in the scene's 3D world coordinate frame. In previous work, these predictions were point estimates and the subsequent camera pose optimization implicitly assumed an isotropic distribution of these estimates. In this paper, we train a regression forest to predict mixtures of anisotropic 3D Gaussians and show how the predicted uncertainties can be taken into account for continuous pose optimization. Experiments show that our proposed method is able to relocalize up to 40% more frames than the state of the art.

AB - Recent advances in camera relocalization use predictions from a regression forest to guide the camera pose optimization procedure. In these methods, each tree associates one pixel with a point in the scene's 3D world coordinate frame. In previous work, these predictions were point estimates and the subsequent camera pose optimization implicitly assumed an isotropic distribution of these estimates. In this paper, we train a regression forest to predict mixtures of anisotropic 3D Gaussians and show how the predicted uncertainties can be taken into account for continuous pose optimization. Experiments show that our proposed method is able to relocalize up to 40% more frames than the state of the art.

UR - https://www.scopus.com/pages/publications/84959188069

U2 - 10.1109/CVPR.2015.7299069

DO - 10.1109/CVPR.2015.7299069

M3 - Conference contribution

AN - SCOPUS:84959188069

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 4400

EP - 4408

BT - IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015

PB - IEEE Computer Society

T2 - IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015

Y2 - 7 June 2015 through 12 June 2015

ER -

Valentin J, Nießner M, Shotton J, Fitzgibbon A, Izadi S, Torr P. Exploiting uncertainty in regression forests for accurate camera relocalization. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015. IEEE Computer Society. 2015. p. 4400-4408. 7299069. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). doi: 10.1109/CVPR.2015.7299069

Exploiting uncertainty in regression forests for accurate camera relocalization

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this