what's the upscaling factor of SFTGAN model?

xinntao / SFTGAN

CVPR18 - Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform

559 stars 100 forks source link

what's the upscaling factor of SFTGAN model? #12

Open vhank opened 5 years ago

vhank commented 5 years ago

why the size of output is same as that of input when I run SFTGAN test code with pretrained models?

xinntao commented 5 years ago

The codes first down-sample the input image with the Bicubic kernel to simulate the downsampling processing. We treat the downsampled images as the inputs and the model will upsample it with the upscaling factor of 4.

xinntao commented 5 years ago

You need to train/fine-tune a new model without upsampling.

jiequanz commented 5 years ago

So the input image should actually be a HR image, because the code will automatically use the bicubic kernel to generate the LR image. is that right?

xinntao commented 5 years ago

Yes, you are right.