TY - GEN
T1 - SHREC'16 track large-scale 3D shape retrieval from ShapeNet Core55
AU - Savva, M.
AU - Yu, F.
AU - Su, Hao
AU - Aono, M.
AU - Chen, B.
AU - Cohen-Or, D.
AU - Deng, W.
AU - Su, Hang
AU - Bai, S.
AU - Bai, X.
AU - Fish, N.
AU - Han, J.
AU - Kalogerakis, E.
AU - Learned-Miller, E. G.
AU - Li, Y.
AU - Liao, M.
AU - Maji, S.
AU - Tatsuma, A.
AU - Wang, Y.
AU - Zhang, N.
AU - Zhou, Z.
N1 - Publisher Copyright:
© 2016 The Eurographics Association.
PY - 2016
Y1 - 2016
N2 - With the advent of commodity 3D capturing devices and better 3D modeling tools, 3D shape content is becoming increasingly prevalent. Therefore, the need for shape retrieval algorithms to handle large-scale shape repositories is more and more important. This track aims to provide a benchmark to evaluate large-scale shape retrieval based on the ShapeNet dataset. We use ShapeNet Core55, which provides more than 50 thousands models over 55 common categories in total for training and evaluating several algorithms. Five participating teams have submitted a variety of retrieval methods which were evaluated on several standard information retrieval performance metrics. We find the submitted methods work reasonably well on the track benchmark, but we also see significant space for improvement by future algorithms. We release all the data, results, and evaluation code for the benefit of the community.
AB - With the advent of commodity 3D capturing devices and better 3D modeling tools, 3D shape content is becoming increasingly prevalent. Therefore, the need for shape retrieval algorithms to handle large-scale shape repositories is more and more important. This track aims to provide a benchmark to evaluate large-scale shape retrieval based on the ShapeNet dataset. We use ShapeNet Core55, which provides more than 50 thousands models over 55 common categories in total for training and evaluating several algorithms. Five participating teams have submitted a variety of retrieval methods which were evaluated on several standard information retrieval performance metrics. We find the submitted methods work reasonably well on the track benchmark, but we also see significant space for improvement by future algorithms. We release all the data, results, and evaluation code for the benefit of the community.
UR - http://www.scopus.com/inward/record.url?scp=85018208348&partnerID=8YFLogxK
U2 - 10.2312/3dor.20161092
DO - 10.2312/3dor.20161092
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:85018208348
T3 - Eurographics Workshop on 3D Object Retrieval, EG 3DOR
SP - 89
EP - 98
BT - EG 3DOR 2016 - Eurographics 2016 Workshop on 3D Object Retrieval
A2 - Ferreira, Alfredo
A2 - Giorgi, Daniela
A2 - Giachetti, Andrea
PB - Eurographics Association
T2 - 9th Eurographics Workshop on 3D Object Retrieval, 3DOR 2016
Y2 - 8 May 2016
ER -