TY - JOUR
T1 - SHREC’22 track
T2 - Sketch-based 3D shape retrieval in the wild
AU - Qin, Jie
AU - Yuan, Shuaihang
AU - Chen, Jiaxin
AU - Ben Amor, Boulbaba
AU - Fang, Yi
AU - Hoang-Xuan, Nhat
AU - Chu, Chi Bien
AU - Nguyen-Ngoc, Khoi Nguyen
AU - Cao, Thien Tri
AU - Ngo, Nhat Khang
AU - Huynh, Tuan Luc
AU - Nguyen, Hai Dang
AU - Tran, Minh Triet
AU - Luo, Haoyang
AU - Wang, Jianning
AU - Zhang, Zheng
AU - Xin, Zihao
AU - Wang, Yang
AU - Wang, Feng
AU - Tang, Ying
AU - Chen, Haiqin
AU - Wang, Yan
AU - Zhou, Qunying
AU - Zhang, Ji
AU - Wang, Hongyuan
N1 - Publisher Copyright:
© 2022 Elsevier Ltd
PY - 2022/10
Y1 - 2022/10
N2 - Sketch-based 3D shape retrieval (SBSR) is an important yet challenging task, which has drawn more and more attention in recent years. Existing approaches address the problem in a restricted setting, without appropriately simulating real application scenarios. To mimic the realistic setting, in this track, we adopt large-scale sketches drawn by amateurs of different levels of drawing skills, as well as a variety of 3D shapes including not only CAD models but also models scanned from real objects. We define two SBSR tasks and construct two benchmarks consisting of more than 46,000 CAD models, 1700 realistic models, and 145,000 sketches in total. Four teams participated in this track and submitted 15 runs for the two tasks, evaluated by 7 commonly-adopted metrics. We hope that, the benchmarks, the comparative results, and the open-sourced evaluation code will foster future research in this direction among the 3D object retrieval community.
AB - Sketch-based 3D shape retrieval (SBSR) is an important yet challenging task, which has drawn more and more attention in recent years. Existing approaches address the problem in a restricted setting, without appropriately simulating real application scenarios. To mimic the realistic setting, in this track, we adopt large-scale sketches drawn by amateurs of different levels of drawing skills, as well as a variety of 3D shapes including not only CAD models but also models scanned from real objects. We define two SBSR tasks and construct two benchmarks consisting of more than 46,000 CAD models, 1700 realistic models, and 145,000 sketches in total. Four teams participated in this track and submitted 15 runs for the two tasks, evaluated by 7 commonly-adopted metrics. We hope that, the benchmarks, the comparative results, and the open-sourced evaluation code will foster future research in this direction among the 3D object retrieval community.
KW - Cross-modality retrieval
KW - Point cloud classification
KW - Shape retrieval in the wild
KW - Sketch-based 3D shape retrieval
UR - http://www.scopus.com/inward/record.url?scp=85134810866&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85134810866&partnerID=8YFLogxK
U2 - 10.1016/j.cag.2022.07.009
DO - 10.1016/j.cag.2022.07.009
M3 - Article
AN - SCOPUS:85134810866
SN - 0097-8493
VL - 107
SP - 104
EP - 115
JO - Computers and Graphics (Pergamon)
JF - Computers and Graphics (Pergamon)
ER -