Vassilis Choutas
Vassilis Choutas
@gngdb can you update the description for the Trust NCG optimizer? I fixed the packaging in that repo, so the rollback is no longer needed. The two hand joints that...
@GuyTevet the SMPL+H AMASS data do not use the gender-neutral model. Each file contains a 'gender' key that tells you which SMPL+H gender model to use. You should load both...
I have tested this with Pytorch 0.4.1 / CUDA 9.2 and Pytorch 1.1 / CUDA 10. I will make sure to update the README. @mehameha998 Could you please share the...
@dongliangcao Sorry for that, I just pushed a fix. Please try to run it again.
@BboyHanat Does the issue still exist? This [line](https://github.com/vchoutas/smplify-x/blob/d0d096f6a1edb85ddc398a8d4e2005dc3b7f19ff/smplifyx/cmd_parser.py#L292) should convert the input body_tri_idxs to a list of pairs.
Do you have 2D or 3D joints? What do you mean that the body mesh is not right?
Hi everyone, sorry for the delay. Could you please provide me some samples inputs (images + keypoints) that cause the problem (e-mail, comment, whatever suits you best) ? I will...
@mikeburon The given data runs without any issue for me. Could you try @torpor29 solution?
@Lotayou this is running without any issue for me. Might it be because you are using CUDA 9.0 instead of CUDA 10?
@Lotayou you can set interpenetration=False to disable the self intersection term. The results should be more or less the same.