Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/Jeff-sjtu/res-loglikelihood-regression
Code for "Human Pose Regression with Residual Log-likelihood Estimation", ICCV 2021 Oral
https://github.com/Jeff-sjtu/res-loglikelihood-regression
2d-human-pose 3d-human-pose human-pose-estimation iccv iccv2021 pytorch regression
Last synced: about 2 months ago
JSON representation
Code for "Human Pose Regression with Residual Log-likelihood Estimation", ICCV 2021 Oral
- Host: GitHub
- URL: https://github.com/Jeff-sjtu/res-loglikelihood-regression
- Owner: Jeff-sjtu
- Created: 2021-07-23T09:07:34.000Z (about 3 years ago)
- Default Branch: master
- Last Pushed: 2021-11-25T03:47:29.000Z (almost 3 years ago)
- Last Synced: 2024-07-30T08:42:11.274Z (about 2 months ago)
- Topics: 2d-human-pose, 3d-human-pose, human-pose-estimation, iccv, iccv2021, pytorch, regression
- Language: Python
- Homepage:
- Size: 63.2 MB
- Stars: 421
- Watchers: 7
- Forks: 43
- Open Issues: 32
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-human-pose-estimation - [code - ICCV 21, RLE (Multi-Person 2D Pose Estimation / 2021)
README
# Human Pose Regression with Residual Log-likelihood Estimation
[[`Paper`](https://jeffli.site/res-loglikelihood-regression/resources/ICCV21-RLE.pdf)]
[[`arXiv`](https://arxiv.org/abs/2107.11291)]
[[`Project Page`](https://jeffli.site/res-loglikelihood-regression/)]
> [Human Pose Regression with Residual Log-likelihood Estimation](https://jeffli.site/res-loglikelihood-regression/resources/ICCV21-RLE.pdf)
> Jiefeng Li, Siyuan Bian, Ailing Zeng, Can Wang, Bo Pang, Wentao Liu, Cewu Lu
> ICCV 2021 Oral
Regression with Residual Log-likelihood Estimation
## TODO
- [ ] Provide minimal implementation of RLE loss.
- [ ] Add model zoo.
- [x] Provide implementation on Human3.6M dataset.
- [x] Provide implementation on COCO dataset.
### Installation
1. Install pytorch >= 1.1.0 following official instruction.
2. Install `rlepose`:
``` bash
pip install cython
python setup.py develop
```
3. Install [COCOAPI](https://github.com/cocodataset/cocoapi).
``` bash
pip install -U 'git+https://github.com/cocodataset/cocoapi.git#subdirectory=PythonAPI'
```
4. Init `data` directory:
``` bash
mkdir data
```
5. Download [COCO](https://cocodataset.org/#download) data, [MPII](http://human-pose.mpi-inf.mpg.de/#download) ([annotations](https://drive.google.com/file/d/1--EQZnCJI_XJIc9_bw-dzw3MrRFLMptw/view?usp=sharing)) and [Human3.6M](https://drive.google.com/drive/folders/1kgVH-GugrLoc9XyvP6nRoaFpw3TmM5xK) data (from [PoseNet](https://github.com/mks0601/3DMPPE_POSENET_RELEASE) or [ours](https://drive.google.com/drive/folders/1sF2xjAfvEw7rvNaQJqadAU2QDUVFfhQH?usp=sharing)):
```
|-- data
`-- |-- coco
| |-- annotations
| | |-- person_keypoints_train2017.json
| | `-- person_keypoints_val2017.json
| `-- images
| |-- train2017
| | |-- 000000000009.jpg
| | |-- 000000000025.jpg
| | |-- 000000000030.jpg
| | |-- ...
| `-- val2017
| |-- 000000000139.jpg
| |-- 000000000285.jpg
| |-- 000000000632.jpg
| |-- ...
|-- mpii
| |-- annotations
| | `-- annot_mpii.json
| `-- images
|-- 000001163.jpg
|-- 000003072.jpg
|-- 000004812.jpg
|--- ...
|-- h36m
`-- |-- annotations
| |-- Sample_trainmin_train_Human36M_protocol_2.json
| `-- Sample_64_test_Human36M_protocol_2.json
`-- images
|-- s_01_act_02_subact_01_ca_01
| |-- ...
|-- s_01_act_02_subact_01_ca_02
| |-- ...
`-- ...
```
## Training
### Train on MSCOCO
``` bash
./scripts/train.sh ./configs/256x192_res50_regress-flow.yaml train_rle_coco
```
### Train on Human3.6M
``` bash
./scripts/train.sh ./configs/256x192_res50_3d_h36mmpii-flow.yaml train_rle_h36m
```
## Evaluation
### Validate on MSCOCO
Download the pretrained model from [Google Drive](https://drive.google.com/file/d/1YBHqNKkxIVv8CqgDxkezC-4vyKpx-zXK/view?usp=sharing).
``` bash
./scripts/validate.sh ./configs/256x192_res50_regress-flow.yaml ./coco-laplace-rle.pth
```
### Validate on Human3.6M
Download the pretrained model from [Google Drive](https://drive.google.com/file/d/1v2ZhembnFyJ_FXGHEOCzGaM-tAVFMy7A/view?usp=sharing).
``` bash
./scripts/validate.sh ./configs/256x192_res50_3d_h36mmpii-flow.yaml ./h36m-laplace-rle.pth
```
### Citing
If our code helps your research, please consider citing the following paper:
```
@inproceedings{li2021human,
title={Human Pose Regression with Residual Log-likelihood Estimation},
author={Li, Jiefeng and Bian, Siyuan and Zeng, Ailing and Wang, Can and Pang, Bo and Liu, Wentao and Lu, Cewu},
booktitle={ICCV},
year={2021}
}
```