[Question] What is the highest quality I can run a image through the model?

zsyzzsoft / co-mod-gan

[ICLR 2021, Spotlight] Large Scale Image Completion via Co-Modulated Generative Adversarial Networks

Other

444 stars 67 forks source link

[Question] What is the highest quality I can run a image through the model? #17

Open roimulia2 opened 3 years ago

roimulia2 commented 3 years ago

Hey there, great paper!

I'm wondering what should one do when a higher quality image needs to be the input (full HD or higher). Is it a limitation of the model? Can it be adjusted to support any kind of resolution?

Thank you!

zsyzzsoft commented 3 years ago

This is indeed a limitation in the current model. One solution to support multi-resolution inputs is to prepend a global (average) pooling layer before the fully connected layer when transforming the encoder features to the style vector. A workaround without retraining is to run inference on a crop of the full image for each masked region.

roimulia2 commented 3 years ago

Hey, thanks for replying!

Should we expect worse/better/same results doing so or it's unknown?