A Decoder-free Transformer-like Architecture for High-efficiency Single Image Deraining.
Xiao WuTing-Zhu HuangLiang-Jian DengTian-Jing ZhangPublished in: IJCAI (2022)
Keyphrases
- single image
- high efficiency
- d scene
- shape recovery
- multiple images
- high accuracy
- light source
- image pairs
- partially occluded
- super resolution
- spherical harmonics
- structured light
- scene geometry
- shape from shading
- video sequences
- indoor scenes
- intrinsic images
- vanishing points
- object detection
- high quality
- outdoor images