Variational Relational Point Completion Network for Robust 3D Classification
Real-scanned point clouds are often incomplete due to viewpoint, occlusion, and noise, which hampers 3D geometric modeling and perception. Existing point cloud completion methods tend to generate global shape skeletons and hence lack fine local details. Furthermore, they mostly learn a deterministic...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 45(2023), 9 vom: 21. Sept., Seite 11340-11351
|
|---|
| 1. Verfasser: |
Pan, Liang
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Chen, Xinyi,
Cai, Zhongang,
Zhang, Junzhe,
Zhao, Haiyu,
Yi, Shuai,
Liu, Ziwei |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2023
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article |
|---|