.png){kind=icon}
.png){kind=icon}
Return
A lightweight depth completion network with spatial efficient fusion
.png){kind=icon}
PRE
AI
DOI：10.1016/j.imavis.2024.105335.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Depth completion is a low-level task rebuilding the dense depth from a sparse set of measurements from LiDAR sensors and corresponding RGB images. Current state-of-the-art depth completion methods used complicated network designs with much computational cost increase, which is incompatible with the realistic-scenario limited computational environment. In this paper, we explore a lightweight and efficient depth completion model named Light-SEF. Light-SEF is a two-stage framework that introduces local fusion and global fusion modules to extract and fuse local and global information in the sparse LiDAR data and RGB images. We also propose a unit convolutional structure named spatial efficient block (SEB), which has a lightweight design and extracts spatial features efficiently. As the unit block of the whole network, SEB is much more cost-efficient compared to the baseline design. Experimental results on the KITTI benchmark demonstrate that our LightSEF achieves significant declines in computational cost (about 53% parameters, 50% FLOPs & MACs, and 36% running time) while showing competitive results compared to state-of-the-art methods.
Keywords:
Depth completion
LiDAR data processing
Lightweight network
Spatial efficient
Multi-modal fusion
Journal
IF:
4.2
Papers:
4.0K
Citations:
6.7K