Multi-Scale Progressive Fusion Network for Single Image Deraining
Wuhan University · University of North Carolina at Charlotte · +2 more institutions
Abstract
Rain streaks in the air appear in various blurring degrees and resolutions due to different distances from their positions to the camera. Similar rain patterns are visible in a rain image as well as its multi-scale (or multi-resolution) versions, which makes it possible to exploit such complementary information for rain streak representation. In this work, we explore the multi-scale collaborative representation for rain streaks from the perspective of input image scales and hierarchical deep features in a unified framework, termed multi-scale progressive fusion network (MSPFN) for single image rain streak removal. For the similar rain streaks at different positions, we employ recurrent calculation to capture…
Citation impact
- FWCI
- 38.05
- Percentile
- 100%
- References
- 54
Authors
8Topics & keywords
- Computer science
- Streak
- Pyramid (geometry)
- Artificial intelligence
- Representation (politics)
- Benchmark (surveying)
- Scale (ratio)
- Computer vision