EfficientDeRain: Learning pixel-wise dilation filtering for high-efficiency single-Image deraining
Single-image deraining is rather challenging due to the unknown rain model. Existing methods often make specific assumptions of the rain model, which can hardly cover many diverse circumstances in the real world, compelling them to employ complex optimization or progressive refinement. This, however...
Saved in:
Main Authors: | , , , , , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2021
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/7112 https://ink.library.smu.edu.sg/context/sis_research/article/8115/viewcontent/16239_Article_Text_19733_1_2_20210518.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-8115 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-81152023-03-21T00:40:32Z EfficientDeRain: Learning pixel-wise dilation filtering for high-efficiency single-Image deraining GUO, Qing SUN, Jingyang JUEFEI-XU, Felix MA, Lei XIE, Xiaofei FENG, Wei LIU, Yang ZHAO, Jianjun Single-image deraining is rather challenging due to the unknown rain model. Existing methods often make specific assumptions of the rain model, which can hardly cover many diverse circumstances in the real world, compelling them to employ complex optimization or progressive refinement. This, however, significantly affects these methods’ efficiency and effectiveness for many efficiency-critical applications. To fill this gap, in this paper, we regard the single-image deraining as a general image-enhancing problem and originally propose a model-free deraining method, i.e., EfficientDeRain, which is able to process a rainy image within 10 ms (i.e., around 6 ms on average), over 80 times faster than the state-of-the-art method (i.e., RCDNet), while achieving similar de-rain effects. We first propose the novel pixel-wise dilation filtering. In particular, a rainy image is filtered with the pixel-wise kernels estimated from a kernel prediction network, by which suitable multi-scale kernels for each pixel can be efficiently predicted. Then, to eliminate the gap between synthetic and real data, we further propose an effective data augmentation method (i.e., RainMix) that helps to train network for handling real rainy images. We perform comprehensive evaluation on both synthetic and realworld rainy datasets to demonstrate the effectiveness and efficiency of our method. We release the model and code in https://github.com/tsingqguo/efficientderain.git. 2021-02-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/7112 https://ink.library.smu.edu.sg/context/sis_research/article/8115/viewcontent/16239_Article_Text_19733_1_2_20210518.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Graphics and Human Computer Interfaces Software Engineering |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Graphics and Human Computer Interfaces Software Engineering |
spellingShingle |
Graphics and Human Computer Interfaces Software Engineering GUO, Qing SUN, Jingyang JUEFEI-XU, Felix MA, Lei XIE, Xiaofei FENG, Wei LIU, Yang ZHAO, Jianjun EfficientDeRain: Learning pixel-wise dilation filtering for high-efficiency single-Image deraining |
description |
Single-image deraining is rather challenging due to the unknown rain model. Existing methods often make specific assumptions of the rain model, which can hardly cover many diverse circumstances in the real world, compelling them to employ complex optimization or progressive refinement. This, however, significantly affects these methods’ efficiency and effectiveness for many efficiency-critical applications. To fill this gap, in this paper, we regard the single-image deraining as a general image-enhancing problem and originally propose a model-free deraining method, i.e., EfficientDeRain, which is able to process a rainy image within 10 ms (i.e., around 6 ms on average), over 80 times faster than the state-of-the-art method (i.e., RCDNet), while achieving similar de-rain effects. We first propose the novel pixel-wise dilation filtering. In particular, a rainy image is filtered with the pixel-wise kernels estimated from a kernel prediction network, by which suitable multi-scale kernels for each pixel can be efficiently predicted. Then, to eliminate the gap between synthetic and real data, we further propose an effective data augmentation method (i.e., RainMix) that helps to train network for handling real rainy images. We perform comprehensive evaluation on both synthetic and realworld rainy datasets to demonstrate the effectiveness and efficiency of our method. We release the model and code in https://github.com/tsingqguo/efficientderain.git. |
format |
text |
author |
GUO, Qing SUN, Jingyang JUEFEI-XU, Felix MA, Lei XIE, Xiaofei FENG, Wei LIU, Yang ZHAO, Jianjun |
author_facet |
GUO, Qing SUN, Jingyang JUEFEI-XU, Felix MA, Lei XIE, Xiaofei FENG, Wei LIU, Yang ZHAO, Jianjun |
author_sort |
GUO, Qing |
title |
EfficientDeRain: Learning pixel-wise dilation filtering for high-efficiency single-Image deraining |
title_short |
EfficientDeRain: Learning pixel-wise dilation filtering for high-efficiency single-Image deraining |
title_full |
EfficientDeRain: Learning pixel-wise dilation filtering for high-efficiency single-Image deraining |
title_fullStr |
EfficientDeRain: Learning pixel-wise dilation filtering for high-efficiency single-Image deraining |
title_full_unstemmed |
EfficientDeRain: Learning pixel-wise dilation filtering for high-efficiency single-Image deraining |
title_sort |
efficientderain: learning pixel-wise dilation filtering for high-efficiency single-image deraining |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2021 |
url |
https://ink.library.smu.edu.sg/sis_research/7112 https://ink.library.smu.edu.sg/context/sis_research/article/8115/viewcontent/16239_Article_Text_19733_1_2_20210518.pdf |
_version_ |
1770576214686171136 |