.png){kind=icon}
.png){kind=icon}
Return
RES: Reconstruction-based sampling for point cloud learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.displa.2025.103322.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A novel reconstruction-based sampling (RES) framework for point cloud learning is proposed. • Point and shape reconstruction modules enable detail-preserving downsampling. • Point salience is measured via reconstruction errors for effective point selection. • A Local-Global Feature Aggregation (LGFA) module extracts both local and global features.