Using SMIL instead of SMPL

Question

Using SMIL instead of SMPL

Closed this issue a year ago · 3 comments

Hi!
I was wondering whether it is possible to somehow easily exchange the SMPL model for SMIL to get better results on infants. I have just tried using the SMIL model (in place of SMPL), but it gives me completely the same results as with SMPL. I guess I am missing something...
Thanks

Answer 1 · 2023-08-30T19:50:39.000Z

HMR2.0 predicts shape parameters for the SMPL model. The SMIL model has a different shape space, so you will not get something meaningful by just using the parameters from HMR2.0.

Answer 2 · 2023-08-31T12:05:26.000Z

So theoretically if I changed the output shape parameters to SMIL and retrained it on my dataset, I could get something meaningful?

Answer 3 · 2023-08-31T17:17:25.000Z

Yes, that could work, but you need to retrain or finetune on the appropriate data.