.png){kind=icon}
.png){kind=icon}
Return
A geometry-aware implicit–explicit framework for light field angular super-resolution
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2026.113691.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• We propose GIENet, a geometry-aware implicit–explicit LFASR framework. • An implicit module captures geometry without explicit depth-estimation branch. • An explicit module enriches features with self-inferred depth cues. • An axis-aligned aggregation module balances efficiency and performance. • GIENet outperforms state-of-the-art methods on synthetic and real datasets.
Keywords:
GIENet
implicit-explicit framework
light field angular super-resolution
geometry-aware
depth cues
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W