cassiePython

@lubovbyc Hi. I have tried to alleviate this. You can add more MLP layers for the APNet and use the PDC loss to improve robustness.

@lubovbyc I am still confused with the problem. I did not find this problem on my dataset. I attached the dataset with 4K images and the corresponding checkpoint. Please check...

> I also struggle in finding the good results of APNet. Should I use the renderer, landmark loss as well? 1. Before using the pseudo gt to train the APNet,...

@roundchuan Can you get results like this: 

TO ALL: Recently, I generate more datasets with different sizes (e.g. 4K, 6K, 8K, 1W, 1.5W, 2W), and find a local minimum (e.g. the mean face) will appear during training...

@JiejiangWu For expression editing, you should modify the value (pca_val) of the expression-related 3DMM parameters (pca_id).