MPI-INF D2 Publications: Electronic Proceedings Article: Back to the Future: Learning Shape Models from {3D} {CAD} Data

Electronic Proceedings Article
@InProceedings
Internet-Beitrag in Tagungsband, Workshop

Show entries of:

this year (2024) | last year (2023) | two years ago (2022) | Notes URL

Action:

Options:

Library locked

Goto entry point

Author, Editor

Author(s):

Stark, Michael
Goesele, Michael
Schiele, Bernt

dblp
dblp
dblp

Not MPG Author(s):

Goesele, Michael

Editor(s):

Labrosse, Frédéric
Zwiggelaar, Reyer
Liu, Yonghuai
Tiddeman, Bernie

dblp
dblp
dblp
dblp

Not MPII Editor(s):

Labrosse, Frédéric
Zwiggelaar, Reyer
Liu, Yonghuai
Tiddeman, Bernie

BibTeX cite key*:

Stark2010

Title, Conference

Title*:	Back to the Future: Learning Shape Models from 3D CAD Data
Booktitle*:	21st British Machine Vision Conference (BMVC)
Event Address*:	Aberystwyth, Wales	URL of the conference:	http://bmvc10.dcs.aber.ac.uk/
Event Date*: (no longer used):		URL for downloading the paper:	http://bmvc10.dcs.aber.ac.uk/proc/conference/paper106/paper106.pdf
Event Start Date:	31 August 2010	Event End Date:	3 August 2010
Language:	English	Organization:	British Machine Vision Association

Publisher

Publisher's Name:	BMVA	Publisher's URL:	http://www.bmva.org/
Address*:	Malvern, UK	Type:

Vol, No, pp., Year

Series:
Volume:		Number:
Month:	September	Pages:	106,1-106,11
		Sequence Number:	106
Year*:	2010	ISBN/ISSN:	1-901725-40-5
	10.5244/C.24.106

Abstract, Links, ©

URL for Reference:
Note:
(LaTeX) Abstract:	Recognizing 3D objects from arbitrary view points is one of the most fundamental problems in computer vision. A major challenge lies in the transition between the 3D geometry of objects and 2D representations that can be robustly matched to natural images. Most approaches thus rely on 2D natural images either as the sole source of training data for building an implicit 3D representation, or by enriching 3D models with natural image features. In this paper, we go back to the ideas from the early days of computer vision, by using 3D object models as the only source of information for building a multi-view object class detector. In particular, we use these models for learning 2D shape that can be robustly matched to 2D natural images. Our experiments confirm the validity of our approach, which outperforms current state-of-the-art techniques on a multi-view detection data set.
URL for the Abstract:	http://bmvc10.dcs.aber.ac.uk/proc/conference/paper106/abstract106.pdf

Tags, Categories, Keywords:	computer vision, multi-view object class detection
HyperLinks / References / URLs:
Copyright Message:
Personal Comments:
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{Stark2010,
AUTHOR = {Stark, Michael and Goesele, Michael and Schiele, Bernt},
EDITOR = {Labrosse, Fr{\'e}d{\'e}ric and Zwiggelaar, Reyer and Liu, Yonghuai and Tiddeman, Bernie},
TITLE = {Back to the Future: Learning Shape Models from {3D} {CAD} Data},
BOOKTITLE = {21st British Machine Vision Conference (BMVC)},
PUBLISHER = {BMVA},
YEAR = {2010},
ORGANIZATION = {British Machine Vision Association},
PAGES = {106,1--106,11},
ADDRESS = {Aberystwyth, Wales},
MONTH = {September},
ISBN = {1-901725-40-5},
DOI = {10.5244/C.24.106},
}

Entry last modified by Anja Becker, 04/11/2011

Edit History (please click the blue arrow to see the details)

	Editor(s) [Library]	Created 01/05/2011 11:34:44
Revisions 5. 4. 3. 2. 1.	Editor(s) Anja Becker Anja Becker Anja Becker Anja Becker Anja Becker	Edit Dates 11.04.2011 10:45:51 19.01.2011 11:12:06 19.01.2011 11:11:46 19.01.2011 11:10:23 19.01.2011 11:09:02

Attachment Section