.png){kind=icon}
.png){kind=icon}
Return
Blind light field image quality assessment with bidirectional angular features and diffusion model-based quality perception
.png){kind=icon}
PRE
AI
DOI：10.1016/j.displa.2025.103127.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A novel method for angle feature extraction and fusion is designed for light field image quality assessment. • A multi-scale feature fusion approach based on visual perception is employed to integrate angular and spatial features. • Pseudo-reference is generated based on diffusion model, and used to assess the quality of light field images.