Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/thohemp/6drepnet
Official Pytorch implementation of 6DRepNet: 6D Rotation representation for unconstrained head pose estimation.
https://github.com/thohemp/6drepnet
6d aflw2000 analysis biwi estimation facial head head-pose head-pose-estimation orientation pose pytorch pytorch-implementation
Last synced: 1 day ago
JSON representation
Official Pytorch implementation of 6DRepNet: 6D Rotation representation for unconstrained head pose estimation.
- Host: GitHub
- URL: https://github.com/thohemp/6drepnet
- Owner: thohemp
- License: mit
- Created: 2022-02-21T13:07:08.000Z (almost 3 years ago)
- Default Branch: master
- Last Pushed: 2024-07-02T14:10:30.000Z (7 months ago)
- Last Synced: 2025-01-19T03:51:46.163Z (8 days ago)
- Topics: 6d, aflw2000, analysis, biwi, estimation, facial, head, head-pose, head-pose-estimation, orientation, pose, pytorch, pytorch-implementation
- Language: Python
- Homepage:
- Size: 102 KB
- Stars: 565
- Watchers: 11
- Forks: 77
- Open Issues: 20
-
Metadata Files:
- Readme: README.MD
- License: LICENSE
Awesome Lists containing this project
README
[](https://paperswithcode.com/sota/head-pose-estimation-on-biwi?p=6d-rotation-representation-for-unconstrained)
[](https://paperswithcode.com/sota/head-pose-estimation-on-aflw2000?p=6d-rotation-representation-for-unconstrained)
[](https://huggingface.co/spaces/osanseviero/6DRepNet)
#
**6D Rotation Representation for Unconstrained Head Pose Estimation (Pytorch)**
## **Citing**
If you find our work useful, please cite the paper:
```BibTeX
@ARTICLE{10477888,
author={Hempel, Thorsten and Abdelrahman, Ahmed A. and Al-Hamadi, Ayoub},
journal={IEEE Transactions on Image Processing},
title={Toward Robust and Unconstrained Full Range of Rotation Head Pose Estimation},
year={2024},
volume={33},
number={},
pages={2377-2387},
keywords={Head;Training;Predictive models;Pose estimation;Quaternions;Three-dimensional displays;Training data;Head pose estimation;full range of rotation;rotation matrix;6D representation;geodesic loss},
doi={10.1109/TIP.2024.3378180}}
```
```BibTeX
@INPROCEEDINGS{9897219,
author={Hempel, Thorsten and Abdelrahman, Ahmed A. and Al-Hamadi, Ayoub},
booktitle={2022 IEEE International Conference on Image Processing (ICIP)},
title={6d Rotation Representation For Unconstrained Head Pose Estimation},
year={2022},
volume={},
number={},
pages={2496-2500},
doi={10.1109/ICIP46576.2022.9897219}}
```
## Updates
### 18.09.2023
* We present **6DRepNet360**! Checkout our **new version** of 6DRepNet tackling the prediction of the entire range of head pose orientations: https://github.com/thohemp/6DRepNet360
### 13.09.2022
* 6DRepNet is now avaiable as pip package for even more accessable usage: *pip3 install SixDRepNet*
### 20.06.2022
* 6DRepNet has been accepted to ICIP 2022.
### 29.05.2022
* Simplified training script
* Updated default training configuration for more robust results
##
**Paper**
> Thorsten Hempel and Ahmed A. Abdelrahman and Ayoub Al-Hamadi, "6D Rotation Representation for Unconstrained Head Pose Estimation", *accepted to ICIP 2022*. [[ResearchGate]](https://www.researchgate.net/publication/358898627_6D_Rotation_Representation_For_Unconstrained_Head_Pose_Estimation)[[Arxiv]](https://arxiv.org/abs/2202.12555)
###
**Abstract**
> In this paper, we present a method for unconstrained end-to-end head pose estimation. We address the problem of ambiguous rotation labels by introducing the rotation matrix formalism for our ground truth data and propose a continuous 6D rotation matrix representation for efficient and robust direct regression. This way, our method can learn the full rotation appearance which is contrary to previous approaches that restrict the pose prediction to a narrow-angle for satisfactory results. In addition, we propose a geodesic distance-based loss to penalize our network with respect to the )
manifold geometry. Experiments on the public AFLW2000 and BIWI datasets demonstrate that our proposed method significantly outperforms other state-of-the-art methods by up to 20\%.
___
## **Trained on 300W-LP, Test on AFLW2000 and BIWI**
| | | || | | | | | | |
| --------------------- | -------------- |--- | ------- | ------ | ------ | ------ | ------ | ------ | ------ | ------ |
| | **Full Range** | **Yaw** | **Pitch** | **Roll** | **MAE** | | **Yaw** | **Pitch** | **Roll** | **MAE** |
| HopeNet (
=2) | N | 6.47 | 6.56 | 5.44 | 6.16 || 5.17 | 6.98 | 3.39 | 5.18 |
| HopeNet ( =1)| N | 6.92 | 6.64 | 5.67 | 6.41 || 4.81 | 6.61 | 3.27 | 4.90 |
| FSA-Net | N | 4.50 | 6.08 | 4.64 | 5.07 || 4.27 | 4.96 | 2.76 | 4.00 |
| HPE | N | 4.80 | 6.18 | 4.87 | 5.28 || 3.12 | 5.18 | 4.57 | 4.29 |
| QuatNet | N | 3.97 | 5.62 | 3.92 | 4.50 || **2.94** | 5.49 | 4.01 | 4.15 |
| WHENet-V | N | 4.44 | 5.75 | 4.31 | 4.83 || 3.60 | **4.10** | 2.73 | 3.48 |
| WHENet | Y/N | 5.11 | 6.24 | 4.92 | 5.42 || 3.99 | 4.39 | 3.06 | 3.81 |
| TriNet | Y | 4.04 | 5.77 | 4.20 | 4.67 || 4.11 | 4.76 | 3.05 | 3.97 |
| FDN | N | 3.78 | 5.61 | 3.88 | 4.42 | | 4.52 | 4.70 | **2.56** | 3.93 |
| | | | | | | | | | |
| **6DRepNet** | Y | **3.63** | **4.91** | **3.37** | **3.97** || 3.24 | 4.48 | 2.68 | **3.47** |
| | | | | | | | | | | |
## **BIWI 70/30**
| | | | | |
| :---------------------- | :------: | :------: | :------: | :------: |
| | **Yaw** | **Pitch** | **Roll** | **MAE** |
| HopeNet ( =1) | 3.29 | 3.39 | 3.00 | 3.23 |
| FSA-Net | 2.89 | 4.29 | 3.60 | 3.60 |
| TriNet | 2.93 | 3.04 | 2.44 | 2.80 |
| FDN | 3.00 | 3.98 | 2.88 | 3.29 |
| | | | | |
| **6DRepNet** | **2.69** | **2.92** | **2.36** | **2.66** |
| | | | | |
## **Fine-tuned Models**
Fine-tuned models can be download from here: https://drive.google.com/drive/folders/1V1pCV0BEW3mD-B9MogGrz_P91UhTtuE_?usp=sharing
#
**Quick Start**:
## Pip install:
```sh
pip3 install sixdrepnet
```
Example usage:
```py
# Import SixDRepNet
from sixdrepnet import SixDRepNet
import cv2
# Create model
# Weights are automatically downloaded
model = SixDRepNet()
img = cv2.imread('/path/to/image.jpg')
pitch, yaw, roll = model.predict(img)
model.draw_axis(img, yaw, pitch, roll)
cv2.imshow("test_window", img)
cv2.waitKey(0)
```
## Setting it up your own:
```sh
git clone https://github.com/thohemp/6DRepNet
cd 6DRepNet
```
### Set up a virtual environment:
```sh
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt # Install required packages
```
In order to run the demo scripts you need to install the face detector
```sh
pip install git+https://github.com/elliottzheng/face-detection.git@master
```
## **Camera Demo**:
```sh
python ./sixdrepnet/demo.py --snapshot 6DRepNet_300W_LP_AFLW2000.pth \
--cam 0
```
___
#
**Test/Train 3DRepNet**
## **Preparing datasets**
Download datasets:
* **300W-LP**, **AFLW2000** from [here](http://www.cbsr.ia.ac.cn/users/xiangyuzhu/projects/3DDFA/main.htm).
* **BIWI** (Biwi Kinect Head Pose Database) from [here](https://icu.ee.ethz.ch/research/datsets.html)
Store them in the *datasets* directory.
For 300W-LP and AFLW2000 we need to create a *filenamelist*.
```
python create_filename_list.py --root_dir datasets/300W_LP
```
The BIWI datasets needs be preprocessed by a face detector to cut out the faces from the images. You can use the script provided [here](https://github.com/shamangary/FSA-Net/blob/master/data/TYY_create_db_biwi.py). For 7:3 splitting of the BIWI dataset you can use the equivalent script [here](https://github.com/shamangary/FSA-Net/blob/master/data/TYY_create_db_biwi_70_30.py). We set the cropped image size to *256*.
## **Testing**:
```sh
python test.py --batch_size 64 \
--dataset AFLW2000 \
--data_dir datasets/AFLW2000 \
--filename_list datasets/AFLW2000/files.txt \
--snapshot output/snapshots/1.pth \
--show_viz False
```
## **Training**
Download pre-trained RepVGG model '**RepVGG-B1g2-train.pth**' from [here](https://drive.google.com/drive/folders/1Avome4KvNp0Lqh2QwhXO6L5URQjzCjUq) and save it in the root directory.
```sh
python sixdrepnet/train.py
```
## **Deploy models**
For reparameterization the trained models into inference-models use the convert script.
```
python convert.py input-model.tar output-model.pth
```
Inference-models are loaded with the flag ```deploy=True```.
```python
model = SixDRepNet(backbone_name='RepVGG-B1g2',
backbone_file='',
deploy=True,
pretrained=False)
```