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...
Main Authors: | Pan, Liang, Chen, Xinyi, Cai, Zhongang, Zhang, Junzhe, Zhao, Haiyu, Yi, Shuai, Liu, Ziwei |
---|---|
Other Authors: | School of Computer Science and Engineering |
Format: | Journal Article |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/172185 |
Similar Items
-
3D object recovery and stylization with limited supervision
by: Zhang, Junzhe
Published: (2024) -
BEACon : a boundary embedded attentional convolution network for point cloud instance segmentation
by: Liu, Tianrui, et al.
Published: (2021) -
Robust partial-to-partial point cloud registration in a full range
by: Pan, Liang, et al.
Published: (2024) -
3D point cloud attribute compression using geometry-guided sparse representation
by: Gu, Shuai, et al.
Published: (2021) -
Pyramidal optical flow method-based lightweight monocular 3D vascular point cloud reconstruction
by: Liu, Chang, et al.
Published: (2021)