English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Teaching 3D Geometry to Deformable Part Models

Pepik, B., Stark, M., Gehler, P., & Schiele, B. (2012). Teaching 3D Geometry to Deformable Part Models. In 2012 IEEE Conference on Computer Vision and Pattern Recognition (pp. 3362-3369). Piscataway, NJ: IEEE. doi:10.1109/CVPR.2012.6248075.

Item is

Basic

show hide
Genre: Conference Paper
Latex : Teaching {3D} Geometry to Deformable Part Models

Files

show Files
hide Files
:
pepik12cvpr.pdf (Preprint), 9MB
 
File Permalink:
-
Name:
pepik12cvpr.pdf
Description:
-
OA-Status:
Visibility:
Private
MIME-Type / Checksum:
application/pdf
Technical Metadata:
Copyright Date:
-
Copyright Info:
-
License:
-

Locators

show

Creators

show
hide
 Creators:
Pepik, Bojan1, Author           
Stark, Michael1, Author           
Gehler, Peter2, Author           
Schiele, Bernt1, Author           
Affiliations:
1Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society, ou_1116547              
2Dept. Perceiving Systems, Max Planck Institute for Intelligent Systems, Max Planck Society, ou_1497642              

Content

show
hide
Free keywords: Cognition , Design automation , Detectors , Estimation , Optimization , Solid modeling , Training geometry , image representation , object recognition , object tracking , teaching 2D bounding box localization , 3D geometric reasoning , 3D geometry teaching , 3D object tracking , 3D scene understanding , Pascal VOC , benchmark data set , deformable part model , higher-level application , individual object detection , object class detector output , object class recognition system , object hypothesis , representational gap , scene understanding system , ultra-wide baseline matching , viewpoint estimation
 Abstract: Current object class recognition systems typically target 2D bounding box localization, encouraged by benchmark data sets, such as Pascal VOC. While this seems suitable for the detection of individual objects, higher-level applications such as 3D scene understanding or 3D object tracking would benefit from more fine-grained object hypotheses incorporating 3D geometric information, such as viewpoints or the locations of individual parts. In this paper, we help narrowing the representational gap between the ideal input of a scene understanding system and object class detector output, by designing a detector particularly tailored towards 3D geometric reasoning. In particular, we extend the successful discriminatively trained deformable part models to include both estimates of viewpoint and 3D parts that are consistent across viewpoints. We experimentally verify that adding 3D geometric information comes at minimal performance loss w.r.t. 2D bounding box localization, but outperforms prior work in 3D viewpoint estimation and ultra-wide baseline matching.

Details

show
hide
Language(s): eng - English
 Dates: 20122012
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1109/CVPR.2012.6248075
BibTex Citekey: pepik12cvpr
Other: Local-ID: 69C776F3F5006035C12579C10041F4B2-pepik12cvpr
 Degree: -

Event

show
hide
Title: IEEE Conference on Computer Vision and Pattern Recognition
Place of Event: Providence, RI
Start-/End Date: 2012-06-16 - 2012-06-21

Legal Case

show

Project information

show

Source 1

show
hide
Title: 2012 IEEE Conference on Computer Vision and Pattern Recognition
  Abbreviation : CVPR 2012
Source Genre: Proceedings
 Creator(s):
Belongie, Serge1, Author
Blake, Andrew1, Author
Luo, Jiebo1, Author
Yuille, Alan1, Author
Affiliations:
1 External Organizations, ou_persistent22            
Publ. Info: Piscataway, NJ : IEEE
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 3362 - 3369 Identifier: ISBN: 978-1-4673-1226-4
ISSN: 1063-6919