Mayank Kumar

Ig you can use something like[VIBE](https://github.com/mkocabas/VIBE). But it does not have the parameter `trans` . I haven't yet figured out how to get that.

Have you checked the `new_joints` folder ? Im not sure but it may be what you are looking for.

What about SMPL to HumanML3D @EricGuo5513 ?

Yeah. Idk if I just pad the next frame with zeros, the output will make any sense.

@jojo978 did you find any solution to this ?

@EricGuo5513 I see. so to get the single pose, will I have to append maybe a dummy second pose so that the sequence is overall of length 2 ? also...

+1

What tutorials ?

Hey @nghorbani I don't know what I am doing wrong but I am getting this rendering: https://drive.google.com/file/d/1qWnBMS52CSd5yRf_jEWElo8FzZXWiSjC/view?usp=drive_link for this sequence: https://github.com/GuyTevet/motion-diffusion-model/assets/43180708/1e38542c-b6e8-4cf6-baa9-ae781af7e660

I tried with converting a single frame to HumanML3D format (by keeping the next frame as all zeros). But I don't think it worked :( .