MSPR-Net: A Multi-Scale Features Based Point Cloud Registration Network
Point-cloud registration is a fundamental task in computer vision. However, most point clouds are partially overlapping, corrupted by noise and comprised of indistinguishable surfaces, especially for complexly distributed outdoor LiDAR point clouds, which makes registration challenging. In this pape...
Main Authors: | Jinjin Yu, Fenghao Zhang, Zhi Chen, Liman Liu |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-09-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/14/19/4874 |
Similar Items
-
Robust Point Cloud Registration Network for Complex Conditions
by: Ruidong Hao, et al.
Published: (2023-12-01) -
3D Convex Hull-Based Registration Method for Point Cloud Watermark Extraction
by: Bogdan Lipuš, et al.
Published: (2019-07-01) -
Automatic marker-free registration of single tree point-cloud data based on rotating projection
by: Xiuxian Xu, et al.
Published: (2022-01-01) -
TIF-Reg: Point Cloud Registration with Transform-Invariant Features in SE(3)
by: Baifan Chen, et al.
Published: (2021-08-01) -
Linear-Based Incremental Co-Registration of MLS and Photogrammetric Point Clouds
by: Shiming Li, et al.
Published: (2021-06-01)