EG2013

Permanent URI for this community

Now showing 1 - 1 of 1

A Correlated Parts Model for Object Detection in Large 3D Scans
(The Eurographics Association and Blackwell Publishing Ltd., 2013) Sunkel, Martin; Jansen, Silke; Wand, Michael; Seidel, Hans-Peter; I. Navazo, P. Poulin
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.