• Stars
    star
    519
  • Rank 85,261 (Top 2 %)
  • Language
    Python
  • Created over 5 years ago
  • Updated over 5 years ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

PyTorch implementation of Image Super-Resolution Using Deep Convolutional Networks (ECCV 2014)

SRCNN

This repository is implementation of the "Image Super-Resolution Using Deep Convolutional Networks".

Differences from the original

  • Added the zero-padding
  • Used the Adam instead of the SGD
  • Removed the weights initialization

Requirements

  • PyTorch 1.0.0
  • Numpy 1.15.4
  • Pillow 5.4.1
  • h5py 2.8.0
  • tqdm 4.30.0

Train

The 91-image, Set5 dataset converted to HDF5 can be downloaded from the links below.

Dataset Scale Type Link
91-image 2 Train Download
91-image 3 Train Download
91-image 4 Train Download
Set5 2 Eval Download
Set5 3 Eval Download
Set5 4 Eval Download

Otherwise, you can use prepare.py to create custom dataset.

python train.py --train-file "BLAH_BLAH/91-image_x3.h5" \
                --eval-file "BLAH_BLAH/Set5_x3.h5" \
                --outputs-dir "BLAH_BLAH/outputs" \
                --scale 3 \
                --lr 1e-4 \
                --batch-size 16 \
                --num-epochs 400 \
                --num-workers 8 \
                --seed 123                

Test

Pre-trained weights can be downloaded from the links below.

Model Scale Link
9-5-5 2 Download
9-5-5 3 Download
9-5-5 4 Download

The results are stored in the same path as the query image.

python test.py --weights-file "BLAH_BLAH/srcnn_x3.pth" \
               --image-file "data/butterfly_GT.bmp" \
               --scale 3

Results

We used the network settings for experiments, i.e., .

PSNR was calculated on the Y channel.

Set5

Eval. Mat Scale SRCNN SRCNN (Ours)
PSNR 2 36.66 36.65
PSNR 3 32.75 33.29
PSNR 4 30.49 30.25
Original BICUBIC x3 SRCNN x3 (27.53 dB)
Original BICUBIC x3 SRCNN x3 (29.30 dB)
Original BICUBIC x3 SRCNN x3 (28.58 dB)

More Repositories

1

FSRCNN-pytorch

PyTorch implementation of Accelerating the Super-Resolution Convolutional Neural Network (ECCV 2016)
Python
211
star
2

RDN-pytorch

PyTorch implementation of Residual Dense Network for Image Super-Resolution (CVPR 2018)
Python
123
star
3

REDNet-pytorch

PyTorch Implementation of image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections (NIPS 2016)
Python
98
star
4

ESPCN-pytorch

PyTorch implementation of Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network (CVPR 2016)
Python
63
star
5

RCAN-pytorch

PyTorch implementation of Image Super-Resolution Using Very Deep Residual Channel Attention Networks (ECCV 2018)
Python
40
star
6

ARCNN-pytorch

PyTorch implementation of Deep Convolution Networks for Compression Artifacts Reduction (ICCV 2015)
Python
38
star
7

DnCNN-pytorch

PyTorch implementation of Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising (TIP 2017)
Python
26
star
8

SRDenseNet-pytorch

PyTorch implementation of Image Super-Resolution Using Dense Skip Connections (ICCV 2017)
Python
20
star
9

DRRN-pytorch

PyTorch implementation of Image Super-Resolution via Deep Recursive Residual Network (CVPR 2017)
Python
19
star
10

WDSR-pytorch

PyTorch implementation of Wide Activation for Efficient and Accurate Image Super-Resolution (CVPR Workshop 2018)
Python
15
star
11

SNet-pytorch

PyTorch implementation of S-Net: A Scalable Convolutional Neural Network for JPEG Compression Artifact Reduction (2018)
Python
13
star
12

IDN-pytorch

PyTorch Implementation of Fast and Accurate Single Image Super-Resolution via Information Distillation Network (CVPR 2018)
Python
8
star