TY - JOUR
T1 - A Large-Scale Network Construction and Lightweighting Method for Point Cloud Semantic Segmentation
AU - Han, Jiawei
AU - Liu, Kaiqi
AU - Li, Wei
AU - Chen, Guangzhi
AU - Wang, Wenguang
AU - Zhang, Feng
N1 - Publisher Copyright:
© 1992-2012 IEEE.
PY - 2024
Y1 - 2024
N2 - To significantly enhance the performance of point cloud semantic segmentation, this manuscript presents a novel method for constructing large-scale networks and offers an effective lightweighting technique. First, a latent point feature processing (LPFP) module is utilized to interconnect base networks such as PointNet++ and Point Transformer. This intermediate module serves both as a feature information transfer and a ground truth supervision function. Furthermore, in order to alleviate the increase in computational costs brought by constructing large-scale networks and better adapt to the demand for terminal deployment, a novel point cloud lightweighting method for semantic segmentation network (PCLN) is proposed to compress the network by transferring multidimensional feature information of large-scale networks. Specifically, at different stages of the large-scale network, the structure and attention information of the point features are selectively transferred to guide the compressed network to train in the direction of the large-scale network. This paper also solves the problem of representing global structure information of large-scale point clouds through feature sampling and aggregation. Extensive experiments on public datasets and real-world data demonstrate that the proposed method can significantly improve the performance of different base networks and outperform the state-of-the-art.
AB - To significantly enhance the performance of point cloud semantic segmentation, this manuscript presents a novel method for constructing large-scale networks and offers an effective lightweighting technique. First, a latent point feature processing (LPFP) module is utilized to interconnect base networks such as PointNet++ and Point Transformer. This intermediate module serves both as a feature information transfer and a ground truth supervision function. Furthermore, in order to alleviate the increase in computational costs brought by constructing large-scale networks and better adapt to the demand for terminal deployment, a novel point cloud lightweighting method for semantic segmentation network (PCLN) is proposed to compress the network by transferring multidimensional feature information of large-scale networks. Specifically, at different stages of the large-scale network, the structure and attention information of the point features are selectively transferred to guide the compressed network to train in the direction of the large-scale network. This paper also solves the problem of representing global structure information of large-scale point clouds through feature sampling and aggregation. Extensive experiments on public datasets and real-world data demonstrate that the proposed method can significantly improve the performance of different base networks and outperform the state-of-the-art.
KW - Point cloud semantic segmentation
KW - information combination
KW - large-scale network
KW - lightweighting technique
UR - http://www.scopus.com/inward/record.url?scp=85187978232&partnerID=8YFLogxK
U2 - 10.1109/TIP.2024.3372446
DO - 10.1109/TIP.2024.3372446
M3 - Article
C2 - 38451762
AN - SCOPUS:85187978232
SN - 1057-7149
VL - 33
SP - 2004
EP - 2017
JO - IEEE Transactions on Image Processing
JF - IEEE Transactions on Image Processing
ER -