Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

SHREC'14 Track: Large scale comprehensive 3D shape retrieval

: Li, Bo; Lu, Yijuan; Li, Chunyuan; Godil, Afzal; Schreck, Tobias; Aono, Masaki; Chen, Qiang; Chowdhury, Nihad Karim; Fang, Bin; Furuya, Takahiko; Johan, Henry; Kosaka, Ryuichi; Koyanagi, Hitoshi; Ohbuchi, Ryutarou; Tatsuma, Atsushi


Bustos, Benjamin (Ed.) ; European Association for Computer Graphics -EUROGRAPHICS-:
Eurographics Workshop on 3D Object Retrieval, EG 3DOR 2014 : Strasbourg, France, April 6th, 2014
Aire-la-Ville: Eurographics Association, 2014
ISBN: 978-3-905674-58-3
Workshop on 3D Object Retrieval (EG 3DOR) <7, 2014, Straßbourg>
Conference Paper
Fraunhofer IDM@NTU ()
large scale retrieval; shape matching; shape retrieval; Business Field: Virtual engineering; Research Area: Computer graphics (CG); Research Area: Computer vision (CV)

The objective of this track is to evaluate the performance of 3D shape retrieval approaches on a large-sale comprehensive 3D shape database that contains different types of models, such as generic, articulated, CAD and architecture models. The track is based on a new comprehensive 3D shape benchmark, which contains 8,987 triangle meshes that are classified into 171 categories. The benchmark was compiled as a superset of existing benchmarks and presents a new challenge to retrieval methods as it comprises generic models as well as domainspecific model types. In this track, 14 runs have been submitted by 5 groups and their retrieval accuracies were evaluated using 7 commonly used performance metrics.