-
I'd like to extract SMPL coefficients like humannerf did (https://github.com/chungyiweng/humannerf?tab=readme-ov-file#metadatajson)
after WHAM, I could get results `(['poses_body', 'poses_root_cam'…
-
I tried the [humannerf](https://github.com/chungyiweng/humannerf), but I don't know why something went wrong [my issue](https://github.com/chungyiweng/humannerf/issues/49), so I'm trying to use humann…
-
I train humannerf with snap_shot, but produce empty image. Could you tell me how to train humannerf with snap_shot?
-
I am trying to train the humannerf model on a custom video. I have followed all the steps to extract frames, generate masks, get matadata and used it to prepare dataset. The dataset was prepared prope…
-
hello, thanks for your great work. I am curious of the source of `smpl_numpy.py`, as it seems is a script form third parties, can you provide some information about where did you access the code? than…
-
Thank you very much!
-
Hi chungyi,
I'd like to ask does humannerf support SMPL-X model?
-
Hi Yu, thanks for your work and such an organized repo!
I'm now using ROMP to get SMPL poses and would like to visualize the meshes via a perspective camera. I usually use a similar way as https:/…
-
Thanks for the amazing work! I meet a problem when I try to generate the canonical pose.
I down load the smplx models which named as 'SMPLX_XXX.pkl' and run 'python prepare_canonical_pose.py'
but…
-
I find that in the **freeview.py**, the rotation axes of different datasets are different. I wonder why are they different. Is the zju_mocap's world coordinates are different from the common-used on…