By Xing Liu1, Masanori Suganuma1,2, Zhun Sun2, Takayuki Okatani1,2
Tohoku University1, RIKEN Center for AIP2
i) A summary of experimental settings for training is added.
ii) Some mistakes in ./train/raindrop.py are fixed.
-
Abstract
-
Citation
-
Numerical Results
-
Models
-
Datasets
-
Test
-
Train
-
Visual Results
In this paper, we study design of deep neural networks for tasks of image restoration. We propose a novel style of residual connections dubbed “dual residual connection”, which exploits the potential of paired operations, e.g., upand down-sampling or convolution with large- and smallsize kernels. We design a modular block implementing this connection style; it is equipped with two containers to which arbitrary paired operations are inserted. Adopting the “unraveled” view of the residual networks proposed by Veit et al., we point out that a stack of the proposed modular blocks allows the first operation in a block interact with the second operation in any subsequent blocks. Specifying the two operations in each of the stacked blocks, we build a complete network for each individual task of image restoration. We experimentally evaluate the proposed approach on five image restoration tasks using nine datasets. The results show that the proposed networks with properly chosen paired operations outperform previous methods on almost all of the tasks and datasets.
@inproceedings{DuRN_arxiv,
title={Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration},
author={Liu, Xing and Suganuma, Masanori and Sun, Zhun and Okatani, Takayuki},
booktitle={arXiv preprint arXiv:1903.08817},
year={2019},
}
@inproceedings{DuRN_cvpr19,
title={Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration},
author={Liu, Xing and Suganuma, Masanori and Sun, Zhun and Okatani, Takayuki},
booktitle={Proc. Conference on Computer Vision and Pattern Recognition},
pages={7007-7016},
year={2019},
}
Please find them in the test/results_confirmed.txt file.
Please find them here.
- BSD500-gray (used in our paper)
If you also want the original BSD500, click here.
-
RealNoise-test
This is the test-set used in our paper. It is generated by randomly cropping 10 HR samples of RealNoise-HKPolyU.
- python 3.7
- pytorch 1.2.0
- Download and un-zip the models, and put the
trainedmodelsin the project folder. - Download and put the datasets into the
datafolder. Please also set the names for a dataset and its sub-folder(s) correctly, according to the currentdatafolder. - Go to the
testfolder, and run the scripts.
Some examples for object detection
The images are taken by iphone 6 plus
Compare inside-feature maps with transmission map
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent