AGLC-GAN: Attention-based global-local cycle-consistent generative adversarial networks for unpaired single image dehazing.
R. S. JaisuryaSnehasis MukherjeePublished in: Image Vis. Comput. (2023)
Keyphrases
- single image
- shape recovery
- multiple images
- d scene
- image pairs
- partially occluded
- light source
- indoor scenes
- shape from shading
- generative model
- structured light
- super resolution
- vanishing points
- spherical harmonics
- motion estimation
- information from multiple images
- manhattan world
- visual attention
- image classification