Minimal Hand Pytorch

Unofficial PyTorch reimplementation of minimal-hand (CVPR2020).

you can also find in youtube or bilibili

• bare hand youtube or bilibili
• hand-object intercation youtube or bilibili

This project reimplement following components :

1. Training (DetNet) and Evaluation Code
2. Shape Estimation
3. Pose Estimation: Instead of IKNet in original paper, an analytical inverse kinematics method is used.

Offical project link: [minimal-hand]

Update

• 2021/03/09 update about utils/LM.py, time cost drop from 12s/item to 1.57s/item

• 2021/03/12 update about utils/LM.py, time cost drop from 1.57s/item to 0.27s/item

• 2021/03/17 realtime perfomance is achieved when using PSO to estimate shape, coming soon

• 2021/03/20 Add PSO to estimate shape. AUC is decreased by about 0.01 on STB and RHD datasets, and increased a little on EO and do datasets. Modifiy utlis/vis.py to improve realtime perfomance

• 2021/03/24 Fixed some errors in calculating AUC. Update the 3D PCK AUC Diffenence.

Usage

• Retrieve the code

git clone https://github.com/MengHao666/Minimal-Hand-pytorch
cd Minimal-Hand-pytorch

• Create and activate the virtual environment with python dependencies

conda env create --file=environment.yml
conda activate minimal-hand-torch

Prepare MANO hand model

1. Download MANO model from here and unzip it.

2. Create an account by clicking Sign Up and provide your information

3. Download Models and Code (the downloaded file should have the format mano_v*_*.zip). Note that all code and data from this download falls under the MANO license.

4. unzip and copy the content of the models folder into the mano folder

5. Your structure should look like this:

Minimal-Hand-pytorch/
   mano/
      models/
      webuser/

Download and Prepare datasets

Training dataset

• CMU HandDB part1 ; part2
• Rendered Handpose Dataset
• GANerated Hands Dataset

Evaluation dataset

• STB Dataset ;

  STB_supp: for license reason, download link could be found in bihand

• DexterObjectDataset ;

  DO_supp: Google Drive or Baidu Pan (s892)

• EgoDexterDataset

  EO_supp: Google Drive or Baidu Pan (axkm)

Processing

• Create a data directory, extract all above datasets or additional materials in it

Now your data folder structure should like this:

data/

    CMU/
        hand143_panopticdb/
            datasets/
            ...
        hand_labels/
            datasets/
            ...

    RHD/
        RHD_published_v2/
            evaluation/
            training/
            view_sample.py
            ...

    GANeratedHands_Release/
        data/
        ...

    STB/
        images/
            B1Counting/
                SK_color_0.png
                SK_depth_0.png
                SK_depth_seg_0.png  <-- merged from STB_supp
                ...
            ...
        labels/
            B1Counting_BB.mat
            ...

    dexter+object/
        calibration/
        bbox_dexter+object.csv
        DO_pred_2d.npy
        data/
            Grasp1/
                annotations/
                    Grasp13D.txt
                    my_Grasp13D.txt
                    ...
                ...
            Grasp2/
                annotations/
                    Grasp23D.txt
                    my_Grasp23D.txt
                    ...
                ...
            Occlusion/
                annotations/
                    Occlusion3D.txt
                    my_Occlusion3D.txt
                    ...
                ...
            Pinch/
                annotations/
                    Pinch3D.txt
                    my_Pinch3D.txt
                    ...
                ...
            Rigid/
                annotations/
                    Rigid3D.txt
                    my_Rigid3D.txt
                    ...
                ...
            Rotate/
                                annotations/
                    Rotate3D.txt
                    my_Rotate3D.txt
                    ...
                ...
        

    EgoDexter/
        preview/
        data/
            Desk/
                annotation.txt_3D.txt
                my_annotation.txt_3D.txt
                ...
            Fruits/
                annotation.txt_3D.txt
                my_annotation.txt_3D.txt
                ...
            Kitchen/
                annotation.txt_3D.txt
                my_annotation.txt_3D.txt
                ...
            Rotunda/
                annotation.txt_3D.txt
                my_annotation.txt_3D.txt
                ...
        

Note

• All code and data from these download falls under their own licenses.
• DO represents "dexter+object" dataset; EO represents "EgoDexter" dataset
• DO_supp and EO_supp are modified from original ones.
• DO_pred_2d.npy are 2D predictions from 2D part of DetNet.
• some labels of DO and EO is obviously wrong (u could find some examples with original labels from dexter_object.py or egodexter.py), when projected into image plane, thus should be omitted. Here come my_{}3D.txt and my_annotation.txt_3D.txt.

Download my Results

• my_results: Google Drive or Baidu Pan (2rv7)
• extract it in project folder
• The parameters used in the real-time demo can be found google_drive or baidu (un06). It is provided by Hand-BMC-pytorch

realtime demo

python demo.py

DetNet Training and Evaluation

Run the training code

python train_detnet.py --data_root data/

Run the evaluation code

python train_detnet.py --data_root data/  --datasets_test testset_name_to_test   --evaluate  --evaluate_id checkpoints_id_to_load 

or use my results

python train_detnet.py --checkpoint my_results/checkpoints  --datasets_test "rhd" --evaluate  --evaluate_id 106

python train_detnet.py --checkpoint my_results/checkpoints  --datasets_test "stb" --evaluate  --evaluate_id 71

python train_detnet.py --checkpoint my_results/checkpoints  --datasets_test "do" --evaluate  --evaluate_id 68

python train_detnet.py --checkpoint my_results/checkpoints  --datasets_test "eo" --evaluate  --evaluate_id 101

Shape Estimation

Run the shape optimization code. This can be very time consuming when the weight parameter is quite small.

python optimize_shape.py --weight 1e-5

or use my results

python optimize_shape.py --path my_results/out_testset/

Pose Estimation

Run the following code which uses a analytical inverse kinematics method.

python aik_pose.py

or use my results

python aik_pose.py --path my_results/out_testset/

Detnet training and evaluation curve

Run the following code to see my results

python plot.py --path my_results/out_loss_auc

(AUC means 3D PCK, and ACC_HM means 2D PCK)

3D PCK AUC Diffenence

* means this project

Note

• Adjusting training parameters carefully, longer training time, more complicated network or Biomechanical Constraint Losses could further boost accuracy.
• As there is no official open source of original paper, above comparison is a little rough.

Citation

This is the unofficial pytorch reimplementation of the paper "Monocular Real-time Hand Shape and Motion Capture using Multi-modal Data" (CVPR 2020).

If you find the project helpful, please star this project and cite them:

@inproceedings{zhou2020monocular,
  title={Monocular Real-time Hand Shape and Motion Capture using Multi-modal Data},
  author={Zhou, Yuxiao and Habermann, Marc and Xu, Weipeng and Habibie, Ikhsanul and Theobalt, Christian and Xu, Feng},
  booktitle={Proceedings of the IEEE International Conference on Computer Vision},
  pages={0--0},
  year={2020}
}

Acknowledgement

• Code of Mano Pytorch Layer was adapted from manopth.

• Code for evaluating the hand PCK and AUC in utils/eval/zimeval.py was adapted from hand3d.

• Part code of data augmentation, dataset parsing and utils were adapted from bihand and 3D-Hand-Pose-Estimation.

• Code of network model was adapted from Minimal-Hand.

• @Mrsirovo for the starter code of the utils/LM.py, @maitetsu update it later.

• @maitetsu for the starter code of the utils/AIK.py