Compatibility with ZJU format

Hi, thank you for your work.

Currently, I am training [GauHuman](https://github.com/skhu101/GauHuman) on your dataset. I tried to reuse the Dataloader for ZJU, however the training result is always black. It seems that your dataset is using a different format with the ZJU Monocap dataset.

I only modify the data of camera translation by multiplying with `camera_scale.pkl`. The way I convert original data of MVHuman to ZJU format is:
1) `new_params`: taken from `smpl/smplx`.
2) `new_vertices`: taken from `smpl_param`
3) `cams`: taken from `camera_intrinsics`, `camera_extrinsics`
4) `kpts2d`: taken from `openpose`

Questions/notices:
1) The SMPL parameters has shape of (1, 87), while it is (1, 72) in ZJU.
2) Is the camera convention in MVHuman the same as in ZJU?
3) How can I convert the MVHuman data to the exact format of ZJU?

Thank you!

Start by comparing the MVHuman data fields listed in the issue with the ZJU Monocap dataloader and the use of camera_scale.pkl. Check the SMPL parameter shape, camera convention, and conversions for new_params, new_vertices, cams, and kpts2d. Done means the conversion procedure is documented and produces usable, non-black GauHuman training results.

Written by the indexing model from the issue text.