Any reason that VOCA does not output FLAME parameters?

[bing-jian]

Hi Timo,

First thanks for sharing the code for VOCA, very impressive work. I am wondering why VOCA does not output FLAME parameters (at least expression parameters). Can the current VOCA network be modified such that the model will output expression parameters?

"VOCA outputs meshes in FLAME mesh topology. However, it does not directly output FLAME parameters but you can easily compute this using this code TF_FLAME. The demo to fit the 3D model to registered 3D meshes should do the job"

Originally posted by @TimoBolkart in #21 (comment)

[TimoBolkart]

Hi,
sure, alternatively one can directly output FLAME parameters (i.e. expression and jaw pose). However, we have tried this but ended up directly outputting vertex offsets due to performance reasons. Having just one trainable linear FC layer instead of a fixed FLAME layer as decoder significantly reduced the training time and produced favorable results.

[bing-jian]

Timo, that makes sense. Thanks for the explanation!

[kk66668]

Have you tryied add FLAME layer as decoder to train VOCA?