Deformable 3D fusion: From partial dynamic 3D observations to complete 4D models

Weipeng Xu; Mathieu Salzmann; Yongtian Wang; Yue Liu

doi:10.1109/ICCV.2015.252

Deformable 3D fusion: From partial dynamic 3D observations to complete 4D models

Weipeng Xu, Mathieu Salzmann, Yongtian Wang, Yue Liu

School of Optics and Photonics

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

12 Citations (Scopus)

Abstract

Capturing the 3D motion of dynamic, non-rigid objects has attracted significant attention in computer vision. Existing methods typically require either complete 3D volumetric observations, or a shape template. In this paper, we introduce a template-less 4D reconstruction method that incrementally fuses highly-incomplete 3D observations of a deforming object, and generates a complete, temporally-coherent shape representation of the object. To this end, we design an online algorithm that alternatively registers new observations to the current model estimate and updates the model. We demonstrate the effectiveness of our approach at reconstructing non-rigidly moving objects from highly-incomplete measurements on both sequences of partial 3D point clouds and Kinect videos.

Original language	English
Title of host publication	2015 International Conference on Computer Vision, ICCV 2015
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2183-2191
Number of pages	9
ISBN (Electronic)	9781467383912
DOIs	https://doi.org/10.1109/ICCV.2015.252
Publication status	Published - 17 Feb 2015
Event	15th IEEE International Conference on Computer Vision, ICCV 2015 - Santiago, Chile Duration: 11 Dec 2015 → 18 Dec 2015

Publication series

Name	Proceedings of the IEEE International Conference on Computer Vision
Volume	2015 International Conference on Computer Vision, ICCV 2015
ISSN (Print)	1550-5499

Conference

Conference	15th IEEE International Conference on Computer Vision, ICCV 2015
Country/Territory	Chile
City	Santiago
Period	11/12/15 → 18/12/15

Access to Document

10.1109/ICCV.2015.252

Cite this

Xu, W., Salzmann, M., Wang, Y., & Liu, Y. (2015). Deformable 3D fusion: From partial dynamic 3D observations to complete 4D models. In 2015 International Conference on Computer Vision, ICCV 2015 (pp. 2183-2191). Article 7410609 (Proceedings of the IEEE International Conference on Computer Vision; Vol. 2015 International Conference on Computer Vision, ICCV 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCV.2015.252

@inproceedings{7653403cf0f248b2b7957aa87207e75b,

title = "Deformable 3D fusion: From partial dynamic 3D observations to complete 4D models",

abstract = "Capturing the 3D motion of dynamic, non-rigid objects has attracted significant attention in computer vision. Existing methods typically require either complete 3D volumetric observations, or a shape template. In this paper, we introduce a template-less 4D reconstruction method that incrementally fuses highly-incomplete 3D observations of a deforming object, and generates a complete, temporally-coherent shape representation of the object. To this end, we design an online algorithm that alternatively registers new observations to the current model estimate and updates the model. We demonstrate the effectiveness of our approach at reconstructing non-rigidly moving objects from highly-incomplete measurements on both sequences of partial 3D point clouds and Kinect videos.",

author = "Weipeng Xu and Mathieu Salzmann and Yongtian Wang and Yue Liu",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 15th IEEE International Conference on Computer Vision, ICCV 2015 ; Conference date: 11-12-2015 Through 18-12-2015",

year = "2015",

month = feb,

day = "17",

doi = "10.1109/ICCV.2015.252",

language = "English",

series = "Proceedings of the IEEE International Conference on Computer Vision",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "2183--2191",

booktitle = "2015 International Conference on Computer Vision, ICCV 2015",

address = "United States",

}

Xu, W, Salzmann, M, Wang, Y & Liu, Y 2015, Deformable 3D fusion: From partial dynamic 3D observations to complete 4D models. in 2015 International Conference on Computer Vision, ICCV 2015., 7410609, Proceedings of the IEEE International Conference on Computer Vision, vol. 2015 International Conference on Computer Vision, ICCV 2015, Institute of Electrical and Electronics Engineers Inc., pp. 2183-2191, 15th IEEE International Conference on Computer Vision, ICCV 2015, Santiago, Chile, 11/12/15. https://doi.org/10.1109/ICCV.2015.252

Deformable 3D fusion: From partial dynamic 3D observations to complete 4D models. / Xu, Weipeng; Salzmann, Mathieu; Wang, Yongtian et al.
2015 International Conference on Computer Vision, ICCV 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 2183-2191 7410609 (Proceedings of the IEEE International Conference on Computer Vision; Vol. 2015 International Conference on Computer Vision, ICCV 2015).

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

TY - GEN

T1 - Deformable 3D fusion

T2 - 15th IEEE International Conference on Computer Vision, ICCV 2015

AU - Xu, Weipeng

AU - Salzmann, Mathieu

AU - Wang, Yongtian

AU - Liu, Yue

PY - 2015/2/17

Y1 - 2015/2/17

N2 - Capturing the 3D motion of dynamic, non-rigid objects has attracted significant attention in computer vision. Existing methods typically require either complete 3D volumetric observations, or a shape template. In this paper, we introduce a template-less 4D reconstruction method that incrementally fuses highly-incomplete 3D observations of a deforming object, and generates a complete, temporally-coherent shape representation of the object. To this end, we design an online algorithm that alternatively registers new observations to the current model estimate and updates the model. We demonstrate the effectiveness of our approach at reconstructing non-rigidly moving objects from highly-incomplete measurements on both sequences of partial 3D point clouds and Kinect videos.

AB - Capturing the 3D motion of dynamic, non-rigid objects has attracted significant attention in computer vision. Existing methods typically require either complete 3D volumetric observations, or a shape template. In this paper, we introduce a template-less 4D reconstruction method that incrementally fuses highly-incomplete 3D observations of a deforming object, and generates a complete, temporally-coherent shape representation of the object. To this end, we design an online algorithm that alternatively registers new observations to the current model estimate and updates the model. We demonstrate the effectiveness of our approach at reconstructing non-rigidly moving objects from highly-incomplete measurements on both sequences of partial 3D point clouds and Kinect videos.

UR - http://www.scopus.com/inward/record.url?scp=84973875577&partnerID=8YFLogxK

U2 - 10.1109/ICCV.2015.252

DO - 10.1109/ICCV.2015.252

M3 - Conference contribution

AN - SCOPUS:84973875577

T3 - Proceedings of the IEEE International Conference on Computer Vision

SP - 2183

EP - 2191

BT - 2015 International Conference on Computer Vision, ICCV 2015

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 11 December 2015 through 18 December 2015

ER -

Deformable 3D fusion: From partial dynamic 3D observations to complete 4D models

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this