Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Code for ICCV2021 paper PARE: Part Attention Regressor for 3D Human Body Estimation
| Date | Stars |
|---|---|
| 2026-07-24 | 416 |
| 2026-07-25 | 416 |
| 2026-07-28 | 416 |
| 2026-07-30 | 416 |
| 2026-08-06 | 416 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# PARE: Part Attention Regressor for 3D Human Body Estimation [ICCV 2021]
[]()
[](https://pare.is.tue.mpg.de/)
[](https://arxiv.org/abs/2104.08527)
> [**PARE: Part Attention Regressor for 3D Human Body Estimation**](https://arxiv.org/abs/2104.08527),
> [Muhammed Kocabas](https://ps.is.tuebingen.mpg.de/person/mkocabas),
> [Chun-Hao Paul Huang](https://ps.is.tuebingen.mpg.de/person/chuang2),
> [Otmar Hilliges](https://ait.ethz.ch/people/hilliges/)
[Michael J. Black](https://ps.is.tuebingen.mpg.de/person/black),
> *International Conference on Computer Vision (ICCV), 2021*
<p float="left">
<img src="docs/assets/vibe_vs_pare_p1.gif" width="49%" />
<img src="docs/assets/vibe_vs_pare_p2.gif" width="49%" />
</p>
## Features
PARE is an occlusion-robust human pose and shape estimation method. This implementation includes the demo and evaluation code for
PARE implemented in PyTorch.
## Updates
- 13/10/2021: Demo and evaluation code is released.
## Getting Started
PARE has been implemented and tested on Ubuntu 18.04 with
python >= 3.7. If you don't have a suitable device,
try running our Colab demo.
Clone the repo:
```shell
git clone https://github.com/mkocabas/PARE.git
```
Install the requirements using virtualenv or conda:
```shell
# pip
source scripts/install_pip.sh
# conda
source scripts/install_conda.sh
```
## Demo
First, you need to download the required data
(i.e our trained model and SMPL model parameters). It is approximately 1.3GB.
To do this you can just run:
```shell
source scripts/prepare_data.sh
```
### Video Demo
Run the command below. See `scripts/demo.py` for more options.
```shell script
python scripts/demo.py --vid_file data/sample_video.mp4 --output_folder logs/demo
```
Sample demo output:
<p float="left">
<img src="docs/assets/demo_output.gif" width="30%" />
</p>
### Image Folder Demo
```shell script
python scripts/demo.py --image_folder <path to image folder> --output_folder logs/demo
```
#### Output format
If demo finishes succesfully, it needs to create a file named `pare_output.pkl` in the `--output_folder`.
We can inspect what this file contains by:
```
>>> import joblib # you may also use native pickle here as well
>>> output = joblib.load('pare_output.pkl')
>>> print(output.keys())
dict_keys([1, 2, 3, 4]) # these are the track ids for each subject appearing in the video
>>> for k,v in output[1].items(): print(k,v.shape)
pred_cam (n_frames, 3) # weak perspective camera parameters in cropped image space (s,tx,ty)
orig_cam (n_frames, 4) # weak perspective camera parameters in original image space (sx,sy,tx,ty)
verts (n_frames, 6890, 3) # SMPL mesh vertices
pose (n_frames, 72) # SMPL pose parameters
betas (n_frames, 10) # SMPL body shape parameters
joints3d (n_frames, 49, 3) # SMPL 3D joints
joints2d (n_frames, 21, 3) # 2D keypoint detections by STAF if pose tracking enabled otherwise None
bboxes (n_frames, 4) # bbox detections (cx,cy,w,h)
frame_ids (n_frames,) # frame ids in which subject with tracking id #1 appears
smpl_joints2d (n_frames, 49, 2) # SMPL 2D joints
```
## Google Colab
## Training
Training instructions will follow soon.
## Evaluation
You need to download [3DPW](https://virtualhumans.mpi-inf.mpg.de/3DPW/)
and [3DOH](https://www.yangangwang.com/papers/ZHANG-OOH-2020-03.html)
datasets before runnExcerpt of 6,253 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:11f42c5d0587c973, topic:computer-vision, readme:computer vision