[Feature] Add PARE

[WYJSJTU]

Feature:

• Training and testing code for PARE: Part Attention Regressor for 3D Human Body Estimation [ICCV 2021].
• Achieving 49.35mm PA-MPJPE, 81.79 MPJPE on 3DPW, compared to the original implementation with 50.9mm PA-MPJPE, 82 MPJPE.
• Provided with detailed pre-train and training config.

[caizhongang]

Please also add

1. README in configs/pare.
2. unit tests

[codecov]

Codecov Report

Merging #161 (740bece) into main (0f41db2) will increase coverage by 0.07%.
The diff coverage is 86.56%.

@@            Coverage Diff             @@
##             main     #161      +/-   ##
==========================================
+ Coverage   85.12%   85.19%   +0.07%     
==========================================
  Files         169      173       +4     
  Lines       13788    14707     +919     
==========================================
+ Hits        11737    12530     +793     
- Misses       2051     2177     +126     

Flag	Coverage Δ
unittests	85.19% <86.56%> (+0.07%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files	Coverage Δ
mmhuman3d/apis/train.py	20.63% <ø> (ø)
mmhuman3d/core/visualization/visualize_smpl.py	82.81% <ø> (+0.41%)	⬆️
mmhuman3d/data/datasets/__init__.py	100.00% <ø> (ø)
mmhuman3d/models/backbones/resnet.py	97.12% <50.00%> (-0.69%)	⬇️
mmhuman3d/utils/geometry.py	92.76% <50.00%> (-1.20%)	⬇️
mmhuman3d/models/heads/pare_head.py	78.01% <78.01%> (ø)
mmhuman3d/models/losses/cross_entropy_loss.py	83.33% <83.33%> (ø)
...sets/pipelines/synthetic_occlusion_augmentation.py	87.50% <87.50%> (ø)
mmhuman3d/models/architectures/mesh_estimator.py	74.10% <90.76%> (+2.09%)	⬆️
mmhuman3d/models/backbones/hrnet.py	93.52% <93.52%> (ø)
... and 26 more

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 0f41db2...740bece. Read the comment docs.

[OpenMMLab-Assistant-004]

Hi @WYJSJTU ！First of all, we want to express our gratitude for your significant PR in the mmhuman3d project. Your contribution is highly appreciated, and we are grateful for your efforts in helping improve this open-source project during your personal time. We believe that many developers will benefit from your PR.

We would also like to invite you to join our Special Interest Group (SIG) private channel on Discord, where you can share your experiences, ideas, and build connections with like-minded peers. To join the SIG channel, simply message moderator— OpenMMLab on Discord or briefly share your open-source contributions in the #introductions channel and we will assist you. Look forward to seeing you there! Join us ：https://discord.gg/raweFPmdzG

If you have WeChat，welcome to join our community on WeChat. You can add our assistant ：openmmlabwx. Please add "mmsig + Github ID" as a remark when adding friends：）
Thank you again for your contribution❤