.png){kind=icon}
.png){kind=icon}
Return
Lightweight self-supervised monocular depth estimation based on a conditional diffusion model
.png){kind=icon}
PRE
AI
DOI：10.1016/j.engappai.2026.115067.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A lightweight self-supervised MDE framework is proposed via diffusion model. • Lightweight noise predictor (LNP) reduces the computational burden of diffusion. • Efficient context prior attention (ECPA) enhances depth estimation in complex region.
Keywords:
Monocular depth estimation
Self-supervised learning
Diffusion model
Lightweight network
Depth estimation
Journal
IF:
8
Papers:
5.3K
Citations:
3.5W