There is no landmark for the position of the pupils... so how is this parsed in the conversion?
Where does the eye direction get stored for the training/conversion?
Read the FAQs and search the forum before posting a new topic.
This forum is for discussing tips and understanding the process involved for Extracting and preparing face sets for training a model in Faceswap.
If you have found a bug are having issues with the Extraction process not working, then you should post in the Extract Support forum.
Please mark any answers that fixed your problems so others can find the solutions.
- bryanlyon
- Site Admin
- Posts: 793
- Joined: Fri Jul 12, 2019 12:49 am
- Location: San Francisco
- Has thanked: 4 times
- Been thanked: 218 times
- Contact:
Re: Where does the eye direction get stored for the training/conversion?
It's not provided explicitly to the model. It learns to find it by itself from the data.
Re: Where does the eye direction get stored for the training/conversion?
To expand on this, whilst alignments are extremely important, they are actually only used for 3 reasons.
1) To be able to generate masks landmark based masks (uses all 68 points)
2) To align faces for training (uses the core central face landmarks. i.e. all landmarks except for the jawline)
3) To tell convert where a face is in the frame (this is actually the same as 2, but from a workflow perspective, it makes sense to separate it to its own item).
My word is final