Luminohope

FYI We added additional scripts that can preprocess in-the-wild images compatible with the FFHQ checkpoints. https://github.com/NVlabs/eg3d/issues/18#issuecomment-1200366872

FYI We added additional scripts that can preprocess in-the-wild images compatible with the FFHQ checkpoints. Hope that is useful. https://github.com/NVlabs/eg3d/issues/18#issuecomment-1200366872

Hi all, I just pushed additional scripts that can crop and extract poses from in-the-wild portrait images in a way that is compatible with the FFHQ checkpoints. Hope that is...

Hi blandocs, we have a preliminary in the wild preprocessing script and you will see some translation adjustment etc we did in the script. Perhaps it might be related? https://github.com/NVlabs/eg3d/blob/FFHQ_preprocess/dataset_preprocessing/ffhq/preprocess_in_the_wild.py

Please see the relevant post here: https://github.com/NVlabs/eg3d/issues/67

@usmancheema89 can you send me a few of these original pictures?

@usmancheema89 it seems most likely that the landmarks from MTCNN are failing for the incorrectly aligned examples. Below is some debugging images. The ones where the landmarks look correct appear...

Hi, we used an in-house FACS tracker. This one might be a similar implementation if it is already released: https://docs.nvidia.com/deeplearning/maxine/ar-sdk-system-guide/index.html#expressionapp-sample-app