Vision Transformer with Key-select Routing Attention for Single Image Dehazing.
Lihan TongWeijia LiQingxia YangLiyuan ChenPeng ChenPublished in: CoRR (2024)
Keyphrases
- single image
- multiple images
- d scene
- shape recovery
- computer vision
- partially occluded
- light source
- image pairs
- super resolution
- shape from shading
- image processing
- structured light
- vision system
- colour images
- scene geometry
- intrinsic images
- visual attention
- vanishing points
- spherical harmonics
- three dimensional
- lambertian surface