English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Journal Article

A Correlated Parts Model for Object Detection in Large 3D Scans

MPS-Authors
/persons/resource/persons45577

Sunkel,  Martin
Computer Graphics, MPI for Informatics, Max Planck Society;

/persons/resource/persons44696

Jansen,  Silke
Computer Graphics, MPI for Informatics, Max Planck Society;

/persons/resource/persons45695

Wand,  Michael
Computer Graphics, MPI for Informatics, Max Planck Society;

/persons/resource/persons45449

Seidel,  Hans-Peter
Computer Graphics, MPI for Informatics, Max Planck Society;

Locator
There are no locators available
Fulltext (public)
There are no public fulltexts available
Supplementary Material (public)
There is no public supplementary material available
Citation

Sunkel, M., Jansen, S., Wand, M., & Seidel, H.-P. (2013). A Correlated Parts Model for Object Detection in Large 3D Scans. Computer Graphics Forum, 32(2), 205-214. doi:10.1111/cgf.12040.


Cite as: http://hdl.handle.net/11858/00-001M-0000-0015-1CE6-8
Abstract
This paper addresses the problem of detecting objects in 3D scans according to object classes learned from sparse user annotation. We model objects belonging to a class by a set of fully correlated parts, encoding dependencies between local shapes of different parts as well as their relative spatial arrangement. For an efficient and comprehensive retrieval of instances belonging to a class of interest, we introduce a new approximate inference scheme and a corresponding planning procedure. We extend our technique to hierarchical composite structures, reducing training effort and modeling spatial relations between detected instances. We evaluate our method on a number of real-world 3D scans and demonstrate its benefits as well as the performance of the new inference algorithm.