search

NVlabs / SPADE

Semantic Image Synthesis with SPADE
https://nvlabs.github.io/SPADE/
Other
7.61k stars 980 forks source link

Issue a black background is added to the transparent image #167

Open Ghaleb-alnakhlani opened 2 years ago

Ghaleb-alnakhlani commented 2 years ago

I am using the SPADE model to generate objects from a label mask. The model is training and everything is running smoothly, however, I have noticed that the images are not the same as the input image, I have prepared the dataset and made the background transparent, but when the model loads the images it adds a black background, thus the generated images will have a black background as well. If you don`t mind helping me to overcome this issue. Input in train_B looks like this

Generated images in checkpoints have been changed to this (added black background)

Synthesized - Real - Label So how do I get the images back to the original form similar to the image in train_B, without a background?

Best regards, Ghaleb

Ukuer commented 1 year ago

the transparent region can not be converted to RGB space. you can make it with white or black bg, and post-process the final outputs.