|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM355267152 |
| 003 |
DE-627 |
| 005 |
20231226064005.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231226s2023 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2023.3238516
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1184.xml
|
| 035 |
|
|
|a (DE-627)NLM355267152
|
| 035 |
|
|
|a (NLM)37022019
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Wei, Mingqiang
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a AGConv
|b Adaptive Graph Convolution on 3D Point Clouds
|
| 264 |
|
1 |
|c 2023
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Completed 03.07.2023
|
| 500 |
|
|
|a Date Revised 03.07.2023
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a Convolution on 3D point clouds is widely researched yet far from perfect in geometric deep learning. The traditional wisdom of convolution characterises feature correspondences indistinguishably among 3D points, arising an intrinsic limitation of poor distinctive feature learning. In this article, we propose Adaptive Graph Convolution (AGConv) for wide applications of point cloud analysis. AGConv generates adaptive kernels for points according to their dynamically learned features. Compared with the solution of using fixed/isotropic kernels, AGConv improves the flexibility of point cloud convolutions, effectively and precisely capturing the diverse relations between points from different semantic parts. Unlike the popular attentional weight schemes, AGConv implements the adaptiveness inside the convolution operation instead of simply assigning different weights to the neighboring points. Extensive evaluations clearly show that our method outperforms state-of-the-arts of point cloud classification and segmentation on various benchmark datasets. Meanwhile, AGConv can flexibly serve more point cloud analysis approaches to boost their performance. To validate its flexibility and effectiveness, we explore AGConv-based paradigms of completion, denoising, upsampling, registration and circle extraction, which are comparable or even superior to their competitors
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Wei, Zeyong
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhou, Haoran
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Hu, Fei
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Si, Huajian
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Chen, Zhilei
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhu, Zhe
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Qiu, Jingbo
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Yan, Xuefeng
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Guo, Yanwen
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Wang, Jun
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Qin, Jing
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 45(2023), 8 vom: 20. Aug., Seite 9374-9392
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:45
|g year:2023
|g number:8
|g day:20
|g month:08
|g pages:9374-9392
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2023.3238516
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 45
|j 2023
|e 8
|b 20
|c 08
|h 9374-9392
|