TY - JOUR
T1 - Deep Learning for 3D Point Clouds
T2 - A Survey
AU - Guo, Yulan
AU - Wang, Hanyun
AU - Hu, Qingyong
AU - Liu, Hao
AU - Liu, Li
AU - Bennamoun, Mohammed
PY - 2021/12/1
Y1 - 2021/12/1
N2 - Point cloud learning has lately attracted increasing attention due to its wide applications in many areas, such as computer vision, autonomous driving, and robotics. As a dominating technique in AI, deep learning has been successfully used to solve various 2D vision problems. However, deep learning on point clouds is still in its infancy due to the unique challenges faced by the processing of point clouds with deep neural networks. Recently, deep learning on point clouds has become even thriving, with numerous methods being proposed to address different problems in this area. To stimulate future research, this paper presents a comprehensive review of recent progress in deep learning methods for point clouds. It covers three major tasks, including 3D shape classification, 3D object detection and tracking, and 3D point cloud segmentation. It also presents comparative results on several publicly available datasets, together with insightful observations and inspiring future research directions.
AB - Point cloud learning has lately attracted increasing attention due to its wide applications in many areas, such as computer vision, autonomous driving, and robotics. As a dominating technique in AI, deep learning has been successfully used to solve various 2D vision problems. However, deep learning on point clouds is still in its infancy due to the unique challenges faced by the processing of point clouds with deep neural networks. Recently, deep learning on point clouds has become even thriving, with numerous methods being proposed to address different problems in this area. To stimulate future research, this paper presents a comprehensive review of recent progress in deep learning methods for point clouds. It covers three major tasks, including 3D shape classification, 3D object detection and tracking, and 3D point cloud segmentation. It also presents comparative results on several publicly available datasets, together with insightful observations and inspiring future research directions.
KW - 3D data
KW - Deep learning
KW - instance segmentation
KW - object detection
KW - object tracking
KW - part segmentation
KW - point clouds
KW - scene flow
KW - semantic segmentation
KW - shape classification
KW - shape retrieval
UR - http://www.scopus.com/inward/record.url?scp=85118607559&partnerID=8YFLogxK
U2 - 10.1109/TPAMI.2020.3005434
DO - 10.1109/TPAMI.2020.3005434
M3 - Review article
C2 - 32750799
AN - SCOPUS:85118607559
SN - 0162-8828
VL - 43
SP - 4338
EP - 4364
JO - IEEE Transactions on Pattern Analysis and Machine Intelligence
JF - IEEE Transactions on Pattern Analysis and Machine Intelligence
IS - 12
ER -