A Correlated Parts Model for Object Detection in Large 3D Scans
Loading...
Date
2013
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association and Blackwell Publishing Ltd.
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.
Description
@article{10.1111:cgf.12040,
journal = {Computer Graphics Forum},
title = {{A Correlated Parts Model for Object Detection in Large 3D Scans}},
author = {Sunkel, Martin and Jansen, Silke and Wand, Michael and Seidel, Hans-Peter},
year = {2013},
publisher = {The Eurographics Association and Blackwell Publishing Ltd.},
ISSN = {1467-8659},
DOI = {10.1111/cgf.12040}
}