This is a Tensorflow implementation for "Accurate Image Super-Resolution Using Very Deep Convolutional Networks", CVPR 16'.
# if start from scratch
python VDSR.py
# if start with a checkpoint
python VDSR.py --model_path ./checkpoints/CHECKPOINT_NAME.ckpt
# this will test all the checkpoint in ./checkpoint directory.
# and save the results in ./psnr directory
python TEST.py
# plot the psnr result stored in ./psnr directory
python PLOT.py
The checkpoint is file is here
Scale | Bicubic | VDSR | tf_VDSR |
---|---|---|---|
2x - PSNR/SSIM | 33.66/0.9929 | 37.53/0.9587 | 37.24 |
3x - PSNR/SSIM | 30.39/0.8682 | 33.66/0.9213 | 33.37 |
4x - PSNR/SSIM | 28.42/0.8104 | 31.35/0.8838 | 31.09 |
Scale | Bicubic | VDSR | tf_VDSR |
---|---|---|---|
2x - PSNR/SSIM | 30.24/0.8688 | 33.03/0.9124 | 32.80 |
3x - PSNR/SSIM | 27.55/0.7742 | 29.77/0.8314 | 29.67 |
4x - PSNR/SSIM | 26.00/0.7027 | 28.01/0.7674 | 27.87 |
tf.nn.depthwise_conv2d
and 1x1 convolution, but not so effective.