Home

Awesome

IDN-Caffe

Caffe implementation of "Fast and Accurate Single Image Super-Resolution via Information Distillation Network"

[arXiv] [CVF] [Poster] [TensorFlow version]

<p align="center"> <img src="files/whole architecture.jpg" width="800"> <br /> <em> The schematics of the proposed Information Distillation Network</em> </p> <p align="center"> <em> The average feature maps of enhancement units </em> <img src="files/lenna.jpg" width="640"> <br /> <em> The average feature maps of compression units </em> </p> <p align="center"> <img src="files/visualization.jpg" width="800"> <br /> <em> Visualization of the output feature maps of the third convolution in each enhancement unit </em> </p>

Testing

$ cd ./test
$ matlab
>> test_IDN

Note: Please make sure the matcaffe is complied successfully.

./test/caffemodel/IDN_x2.caffemodel, ./test/caffemodel/IDN_x3.caffmodel and ./test/caffemodel/IDN_x4.caffemodel are obtained by training the model with 291 images, and ./test/caffemodel/IDN_x4_mscoco.caffemodel is got through training the same model with mscoco dataset.

The results are stored in "results" folder, with both reconstructed images and PSNR/SSIM/IFCs.

Training

Results

Set5,Set14,B100,Urban100,Manga109

With regard to the visualization of mean feature maps, you can run test_IDN first and then execute the following code in Matlab.

inspect = cell(4, 1);
for i = 1:4
    inspect{i} = net.blobs(['down' num2str(i)]).get_data();
    figure;
    imagesc(mean(inspect{i}, 3)')
end

Model Parameters

<sub>Scale</sub><sub>Model Size</sub>
<sub>×2</sub><sub>552,769</sub>
<sub>×3</sub><sub>552,769</sub>
<sub>×4</sub><sub>552,769</sub>

Citation

If you find IDN useful in your research, please consider citing:

@inproceedings{Hui-IDN-2018,
  title={Fast and Accurate Single Image Super-Resolution via Information Distillation Network},
  author={Hui, Zheng and Wang, Xiumei and Gao, Xinbo},
  booktitle={CVPR},
  pages = {723--731},
  year={2018}
}