Apply motion reconstruction on top of the HMMR outputs

[ZhengyiLuo]

Thanks a ton for the great work!

I am trying to apply the motion reconstruction to the output of HMMR as a smoothing stage, as well as converting the repo to python3. Though I have a few questions regarding the refinement pipeline. 1. It is mentioned in the paper that the optimization is done in the latent space of HMR's. Does this corresponds to the f_movie output in HMMR, and one can directly optimize that part of the output?
2. I am wondering how is the optimization stepped, as in is there a regressor trained here to revise the previous output? Just reading the paper which describes the losses confuses me how this is done (or maybe it is due to my lack of knowledge in this field :(

Appreciate it!

[acoMCMXCVI]

Hi @ZhengyiLuo ! Did you find a way to integrate HMMR? :)

[ZhengyiLuo]

Hi @ZhengyiLuo ! Did you find a way to integrate HMMR? :)

Nah I didn't end up using HMR/HMMR for my project. Used VIBE for my pose estimation need.