Thanks for sharing this work, good insight and inspiring.
But I'm unable to perceive improvement of the pretrained model.
My inference of E_expression:
For images, inputs: just concat same image (1, 5, 224, 224), output: Flame parameters (5, 53), chose the center one's param ouput[2, :]
For videos, inputs: just concat same frame (1, 5, 224, 224), output: Flame parameters (5, 53), chose the center one's param ouput[2, :]. Or maybe I should try to concat continous 5 frames for E_expression input ?
My mean_shape for alignment is consist with author's.
Comparison of the results (talkinghead videos and single image reconstruction) between E_flame_without_E_expression and E_flame_with_expression:

E_flame_without_E_expression:

E_flame_with_expression:

Sorry, my test maybe not sufficient，and my preprocess maybe not accurate.