V2PNet: Voxel-to-Point Feature Propagation and Fusion That Improves Feature Representation for Point Cloud Registration
Point-based and voxel-based methods can learn the local features of point clouds. However, although point-based methods are geometrically precise, the discrete nature of point clouds negatively affects feature learning performance. Moreover, although voxel-based methods can exploit the learning powe...
Main Authors: | Han Hu, Yongkuo Hou, Yulin Ding, Guoqiang Pan, Min Chen, Xuming Ge |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2023-01-01
|
Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10130555/ |
Similar Items
-
MSPR-Net: A Multi-Scale Features Based Point Cloud Registration Network
by: Jinjin Yu, et al.
Published: (2022-09-01) -
Fast adaptive multimodal feature registration (FAMFR): an effective high-resolution point clouds registration workflow for cultural heritage interiors
by: Piotr Foryś, et al.
Published: (2023-09-01) -
Point Cloud Registration Based on Fast Point Feature Histogram Descriptors for 3D Reconstruction of Trees
by: Yeping Peng, et al.
Published: (2023-07-01) -
SHC: soft-hard correspondences framework for simplifying point cloud registration
by: Zhaoxiang Chen, et al.
Published: (2024-01-01) -
A Point Cloud Registration Framework with Color Information Integration
by: Tianyu Han, et al.
Published: (2024-02-01)