Single image rain removal via multi-module deep grid network
Rain streaks severely degenerate the performances of image/video processing tasks, therefore effective methods for removing rain streaks are required for a wide range of practical applications. In this paper, we introduce an end-to-end deep network, called GridDerainNet, to remove rain streaks withi...
Saved in:
Published in | Computer vision and image understanding Vol. 202; p. 103106 |
---|---|
Main Authors | , , , |
Format | Journal Article |
Language | English |
Published |
Elsevier Inc
01.01.2021
|
Online Access | Get full text |
Cover
Loading…
Summary: | Rain streaks severely degenerate the performances of image/video processing tasks, therefore effective methods for removing rain streaks are required for a wide range of practical applications. In this paper, we introduce an end-to-end deep network, called GridDerainNet, to remove rain streaks within single image under different conditions. The architecture of GridDerainNet consists of three modules: pre-processing, multi-scale attentive module and post-processing. The pre-processing module can effectively generate several variants of the given rainy image, in order to extract more key features from the input. The multi-scale attentive module implements a novel attention mechanism, which allows more flexible information exchange and aggregation, taking full use of diversities of a given image. In the end, post-processing module furthers to reduce residual artifacts after previous two steps. Quantitative and qualitative experimental results demonstrate that the proposed algorithm outperforms several state-of-the-art methods on both synthetic and real-world images.
•In this paper, we design a GridDerainNet, which is composed of multi-module. The useful information for deraining can be incorporated based on the interactions of multi modules.•The rainy image features are extracted by incorporating multiple residual dense blocks at different scales, it furthers to make effective use of multi-scale information to remove rain streaks.•Qualitative and quantitative experiments show that our proposed method outperforms several popular state-of-the-art methods on both synthetic and real images. |
---|---|
ISSN: | 1077-3142 1090-235X |
DOI: | 10.1016/j.cviu.2020.103106 |