Open szh-bash opened 1 year ago
But it does roughly transfered expression and pose from driver frame
@szh-bash - did you figure it out?
@szh-bash - did you figure it out?
no further progress
Tips for cross subject reenactment would be to select a neutral expression looking frame from each, and then only transfer the deltas from that. This reduces the domain gap.
if the heads are very different in size between different models/identities, it could happen that with poses from one you will be rendering previously unseen regions, or get repeating artefacts in some regions due to positional encoding. Try to use just the rotation from the driving frame, but the intrinsics and translation from the actor.
Model: 400k iters trained with 8x1080TI on Person_1 train dataset Test: Person_2 test dataset Simply modified basedir in load_flame_data(basedir,...) (eval_transformed_rays.py) from cfg.dataset to cfg.dataset.basedir[:-1]+'2' (which means "..../dataset/person_2/") and got cross-id face reenactment results below. We can easily find there're huge Artifacts in the generated video. Did i do anything wrong here? Or is the model behaving as expected? @gafniguy
https://user-images.githubusercontent.com/27895812/233761082-ddf517b2-6eae-403c-9a80-7f082351f142.mp4
Compared with Same-ID-Reenactment, it is found that the size of the Source face is entangled with the expression and posture parameters, and it tends to be adjusted to the Driver Face
https://user-images.githubusercontent.com/27895812/233763377-8443d762-d69a-41e1-bbfb-6ed2751585d2.mp4