search

vinthony / deep-blind-watermark-removal

[AAAI 2021] Split then Refine: Stacked Attention-guided ResUNets for Blind Single Image Visible Watermark Removal
https://arxiv.org/abs/2012.07007
223 stars 55 forks source link

Support for variable sized input images? #7

Open shashankvasisht opened 2 years ago

shashankvasisht commented 2 years ago

Hi Vinthony,

I saw that you are resizing the input image to 256x256. Is there any support for variable size inputs?

vinthony commented 2 years ago

hi, thanks for your attention. Actually, our model is fully convolutional which can be tested in any resolution directly. Currently, 256x256 is just a good choice for evaluation.