search

chaofengc / PSFRGAN

PyTorch codes for "Progressive Semantic-Aware Style Transformation for Blind Face Restoration", CVPR2021
Other
370 stars 68 forks source link

a question about the result of Figure 6(b) #27

Closed happyday521 closed 3 years ago

happyday521 commented 3 years ago

Great work！ I have a question about the result of Figure 6(b). Figure 6(b) shows the progressive restoration process when adding multi-scale inputs progressively. However, since the intermediate feature Fi doesn't goes through the ToRGB convolution layer, it is not in RGB format. How do you get the intermediate image result in the Figure，as follows: image

Thanks!

chaofengc commented 3 years ago

The visualisation result is obtained through a styleganv2 like framework which has a torgb block at each scale. To reduce computation complexity, we remove them in the released version because it does not affect the performance.

happyday521 commented 3 years ago

Got it. Thanks.