Open TianxiangMa opened 1 year ago
Hi,
Unfortunately, no. The method is designed for videos, so the Emotion Manipulator expects a sequence of length >= 10. The only implicit way to make it work for images would be to create a short video by copying the image 10 times. Still, you would have to train the neural face renderer (assuming you test on a different celebrity than the ones provided), which, given only 1 image, would not generalize well.
Can the method be tested directly on images (not videos)? For example, two images are used to test expression transfer.