.png){kind=icon}
Return
Low Overlapping Point Cloud Registration Using Mutual Prior Based Completion Network
.png){kind=icon}
PRE
AI
DOI：10.1109/TIP.2024.3437234.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This work presents a new completion method that specifically designed for low-overlapping partial point cloud registration. Based on the assumption that the candidate partial point clouds to be registered belong to the same target, the proposed mutual prior based completion (MPC) method uses these candidate partial point clouds as completion reference for each other to extend their overlapping regions. Without relying on shape prior knowledge, MPC can work for different types of point clouds, such as object, room scene, and street view. The main challenge of this mutual reference approach is that partial clouds without spatial alignment cannot provide a reliable completion reference. Based on the mutual information maximization, a progressive completion structure is developed to achieve pose, feature representation and completion alignment between input point clouds. Experiments on public datasets show encouraging results. Especially for the low-overlapping cases, compared with the state-of-the-art (SOTA) models, the size of overlapping regions can be increased by about 15.0%, and the rotation and translation error can be reduced by 30.8% and 57.7% respectively.
Keywords:
Point cloud compression
Task analysis
Feature extraction
Training
Shape
Reliability
Mutual information
Point cloud registration
point cloud completion
mutual prior
Journal
IF:
13.7
Papers:
1.0W
Citations:
8.4W
Organization
No organization information available
Cited Papers
Efficacy of parenteral vaccination against tuberculosis with heat-inactivated Mycobacterium bovis in experimentally challenged goats.png)
PLOS ONE
OAAI
PLOS ONEIF0
OAAIShareSaveShareSaveA Modified Two-Portion Absorption Model to Describe Double-Peak Absorption Profiles of Ranitidine
PREAI
ShareSaveShareSaveShareSave
View more