MPI-INF Logo
Publications

Server    domino.mpi-inf.mpg.de

Proceedings Article, Paper
@InProceedings
Beitrag in Tagungsband, Workshop

Author, Editor
Author(s):
Zia, M. Zeeshan
Stark, Michael
Schiele, Bernt
Schindler, Konrad		dblp
dblp
dblp
dblp
Not MPG Author(s):
Zia, M. Zeeshan
Schindler, Konrad
Editor(s):
BibTeX cite key*:
Zia2011
Title, Booktitle
Title*:
Revisiting 3D Geometric Models for Accurate Object Shape and Pose
Booktitle*:
2011 IEEE International Conference on Computer Vision : WS08, Workshop on 3D representation and recognition (3dRR-11)
Event, URLs
Conference URL::
http://www.eecs.umich.edu/vision/3dRR11/3dRR11.html
Downloading URL:
http://dx.doi.org/10.1109/ICCVW.2011.6130294
Event Address*:
Barcelona, Spain
Language:
English
Event Date*
(no longer used):
Organization:
IEEE
Event Start Date:
7 November 2011
Event End Date:
7 November 2011
Publisher
Name*:
IEEE
URL:
http://ieeexplore.ieee.org
Address*:
Piscataway, NJ
Type:
Vol, No, Year, pp.
Series:
Volume:
Number:
Month:
November
Pages:
569-576
Year*:
2011
VG Wort Pages:
ISBN/ISSN:
Sequence Number:
DOI:
10.1109/ICCVW.2011.6130294
Note, Abstract, ©
Note:
won the 3rd International IEEE Workshop on 3D Representation and Recognition (3dRR-11) best paper award
(LaTeX) Abstract:
Geometric 3D reasoning has received renewed attention recently, in the context of visual scene understanding. The level of geometric detail, however, is typically limited to qualitative or coarse-grained quantitative representations. This is linked to the fact that today's object class detectors are tuned towards robust 2D matching rather than accurate 3D pose estimation, encouraged by 2D bounding box-based benchmarks such as Pascal VOC. In this paper, we therefore revisit ideas from the early days of computer vision, namely, 3D geometric object class representations for recognition. These representations can recover geometrically far more accurate object hypotheses than just 2D bounding boxes, including relative 3D positions of object parts. In combination with recent robust techniques for shape description and inference, our approach outperforms state-of-the-art results in 3D pose estimation, while at the same time improving 2D localization. In a series of experiments, we analyze our approach in detail, and demonstrate novel applications enabled by our geometric object class representation, such as fine-grained categorization of cars according to their 3D geometry and ultra-wide baseline matching.
Keywords:
computer vision, object class recognition, object class detection, shape, pose estimation, wide baseline matching
Download
Access Level:
Public

Correlation
MPG Unit:
Max-Planck-Institut für Informatik
MPG Subunit:
Computer Vision and Multimodal Computing
Appearance:
MPII WWW Server, MPII FTP Server, MPG publications list, university publications list, working group publication list, Fachbeirat, VG Wort



BibTeX Entry:

@INPROCEEDINGS{Zia2011,
AUTHOR = {Zia, M. Zeeshan and Stark, Michael and Schiele, Bernt and Schindler, Konrad},
 TITLE = {Revisiting {3D} Geometric Models for Accurate Object Shape and Pose},
 BOOKTITLE = {2011 IEEE International Conference on Computer Vision : WS08, Workshop on 3D representation and recognition (3dRR-11)},
 PUBLISHER = {IEEE},
 YEAR = {2011},
 ORGANIZATION = {IEEE},
 PAGES = {569--576},
 ADDRESS = {Barcelona, Spain},
 MONTH = {November},
 DOI = {10.1109/ICCVW.2011.6130294},
 NOTE = {won the 3rd International IEEE Workshop on 3D Representation and Recognition (3dRR-11) best paper award},
}

Entry last modified by Anja Becker, 03/19/2012
Hide details for Edit History (please click the blue arrow to see the details)Edit History (please click the blue arrow to see the details)

Editor(s)
[Library]		Created
01/07/2012 20:27:37
Revisions
2.
1.
0.

Editor(s)
Anja Becker
Anja Becker
Michael Stark

Edit Dates
19.03.2012 14:06:26
22.02.2012 12:57:30
01/07/2012 08:27:37 PM