Scene-Text-Removal

Scene-Text-Removal copied to clipboard

hi, I have already sent the request email to [email protected] a month ago, but still no reply now. Could you please check the email and send me the decompression password?...

misery0424

Does L_total = 0.5 * L_perceptual + 50.0 * L_style + 25.0 * L_tv only apply to optimize VGG?

2

https://github.com/HCIILAB/Scene-Text-Removal/blob/master/network.py#L78 https://github.com/HCIILAB/Scene-Text-Removal/blob/master/train.py#L167 The trainerV seems to only optimize parameters of VGG. So why this loss is needed? https://github.com/HCIILAB/Scene-Text-Removal/blob/master/train.py#L157 This line I_comp = where(mask, real, fake) contradicts to the description in...

lovecambi

Quick question on loss function

1

Where is the code for the scaling factor in Eq (9)? In addition, where is the code for the loss function in Eq (2)? It seems that the following line...

lovecambi

Something else than Baidu upload?

1

Could you please upload the ImageNet pretrained VGG weights also somewhere else than on Baidu?

janzd

have you tested your model on the 1000 MLT dataset you mentioned in your paper?

1

Hi there, I see that you mentioned in your paper that you prepared 1000 images based on MLT-2017 dataset, have you tested your model on these images? What's the mean-PSNR?...

muyue1238

About PSNR and l2

10

Hi, I am checking your results provided in Table1. I find the PSNR is not corresponding to l2. For example, 0.2465 l2 is corresponding to 25.60 PSNR, while 0.0627 l2...

neouyghur

could you share the pretrained model?

2

Hi, you have shared the code. It is very nice. However, it would be much better if you share the pre-trained model. Thanks.

neouyghur