TY - GEN
T1 - Multi-Scope Feature Extraction for Point Cloud Completion
AU - Ma, Wuwei
AU - Wang, Qiu Feng
AU - Huang, Kaizhu
AU - Huang, Xiaowei
N1 - Funding Information:
The work was supported by the following grants: National Natural Science Foundation of China under no.61876155 and 61876154; Jiangsu Science and Technology Programme (Natural Science Foundation of Jiangsu Province) under no. BE2020006-4.
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Point cloud completion aims to predict a complete geometric shape based on a partial point cloud. Recent methods often adopt an encoder-decoder framework, where the encoder extracts global features from the partial points and the decoder utilizes a folding-based model to reform multiple 2D grids to 3D surfaces. To effectively explore local features in the partial points, we propose a multi-scope feature extraction method in the encoder, where multiple k-nearest neighbors are considered in the edge convolution. Furthermore, we integrate the original partial point cloud in the decoder to maintain the given geometric shape information. Finally, we refine those coarse points from the decoder by both the merging and sampling operations to output the final completed point cloud. Extensive experiments verify the effectiveness of the proposed approach where both the multi-scope feature extraction and the integration of partial point cloud improve the performance. Overall, our method achieves better performance than the existing methods in both the Earth Mover's Distance (EMD) and the F-score.
AB - Point cloud completion aims to predict a complete geometric shape based on a partial point cloud. Recent methods often adopt an encoder-decoder framework, where the encoder extracts global features from the partial points and the decoder utilizes a folding-based model to reform multiple 2D grids to 3D surfaces. To effectively explore local features in the partial points, we propose a multi-scope feature extraction method in the encoder, where multiple k-nearest neighbors are considered in the edge convolution. Furthermore, we integrate the original partial point cloud in the decoder to maintain the given geometric shape information. Finally, we refine those coarse points from the decoder by both the merging and sampling operations to output the final completed point cloud. Extensive experiments verify the effectiveness of the proposed approach where both the multi-scope feature extraction and the integration of partial point cloud improve the performance. Overall, our method achieves better performance than the existing methods in both the Earth Mover's Distance (EMD) and the F-score.
KW - Coarse-to-fine
KW - Folding-based decoder
KW - Multi-scope feature
KW - Point cloud completion
UR - http://www.scopus.com/inward/record.url?scp=85145666139&partnerID=8YFLogxK
U2 - 10.1109/ICCSI55536.2022.9970616
DO - 10.1109/ICCSI55536.2022.9970616
M3 - Conference Proceeding
AN - SCOPUS:85145666139
T3 - Proceedings of the International Conference on Cyber-Physical Social Intelligence, ICCSI 2022
SP - 727
EP - 732
BT - Proceedings of the International Conference on Cyber-Physical Social Intelligence, ICCSI 2022
A2 - Chen, Xuemin
A2 - Wang, Jun
A2 - Wang, Jiacun
A2 - Tang, Ying
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 International Conference on Cyber-Physical Social Intelligence, ICCSI 2022
Y2 - 18 November 2022 through 21 November 2022
ER -