Finishing my PhD this will probably be the final version of MocapNET! MocapNET 4 will deal with upperbody / lowerbody / hands / eye tracking and / facial capture It has a written from scratch python interface, but maintain the same compatible BVH output format. It will also be compatible with Raspberry Pi 4 and use Tensorflow /Tf-Lite / ONNX backends
This branch is still under construction, and has been ported to Python to boost usability so if you want the older C/C++ version of MocapNET you ignore it for now..!
Click here for one click setup :
| Download Paper | Year | Conference | Title |
|---|---|---|---|
| 2023 | AMFG@ICCV | A Unified Approach for Occlusion Tolerant 3D Facial Pose Capture and Gaze Estimation using MocapNETs | |
| 2023 | PeTRA | Compacting MocapNET-based 3D Human Pose Estimation via Dimensionality Reduction | |
| 2021 | BMVC | Towards Holistic Real-time Human 3D Pose Estimation using MocapNETs | |
| 2021 | ICPR | Occlusion-tolerant and personalized 3D human pose estimation in RGB images | |
| 2019 | BMVC | MocapNET: Ensemble of SNN Encoders for 3D Human Pose Estimation in RGB Images |
Please cite the following papers if this work helps your research :
@inproceedings{Qammaz2023b,
author = {Qammaz, Ammar and Argyros, Antonis},
title = {A Unified Approach for Occlusion Tolerant 3D Facial Pose Capture and Gaze Estimation using MocapNETs},
booktitle = {International Conference on Computer Vision Workshops (AMFG 2023 - ICCVW 2023), (to appear)},
publisher = {IEEE},
year = {2023},
month = {October},
address = {Paris, France},
projects = {VMWARE,I.C.HUMANS},
pdflink = {http://users.ics.forth.gr/ argyros/mypapers/2023_10_AMFG_Qammaz.pdf}
}
@inproceedings{Qammaz2021,
author = {Qammaz, Ammar and Argyros, Antonis A},
title = {Towards Holistic Real-time Human 3D Pose Estimation using MocapNETs},
booktitle = {British Machine Vision Conference (BMVC 2021)},
publisher = {BMVA},
year = {2021},
month = {November},
projects = {I.C.HUMANS},
videolink = {https://www.youtube.com/watch?v=aaLOSY_p6Zc}
}
For the BMVC21 version of MocapNET please switch to the MNET3 branch
@inproceedings{Qammaz2020,
author = {Ammar Qammaz and Antonis A. Argyros},
title = {Occlusion-tolerant and personalized 3D human pose estimation in RGB images},
booktitle = {IEEE International Conference on Pattern Recognition (ICPR 2020), (to appear)},
year = {2021},
month = {January},
url = {http://users.ics.forth.gr/argyros/res_mocapnet_II.html},
projects = {Co4Robots},
pdflink = {http://users.ics.forth.gr/argyros/mypapers/2021_01_ICPR_Qammaz.pdf},
videolink = {https://youtu.be/Jgz1MRq-I-k}
}
For the original BMVC19 version of MocapNET please switch to the MNET1 branch, unfortunately Tensorflow 1 is not well supported in recent environments so it is difficult to set it up
@inproceedings{Qammaz2019,
author = {Qammaz, Ammar and Argyros, Antonis A},
title = {MocapNET: Ensemble of SNN Encoders for 3D Human Pose Estimation in RGB Images},
booktitle = {British Machine Vision Conference (BMVC 2019)},
publisher = {BMVA},
year = {2019},
month = {September},
address = {Cardiff, UK},
url = {http://users.ics.forth.gr/argyros/res_mocapnet.html},
projects = {CO4ROBOTS,MINGEI},
pdflink = {http://users.ics.forth.gr/argyros/mypapers/2019_09_BMVC_mocapnet.pdf},
videolink = {https://youtu.be/fH5e-KMBvM0}
}
This library is provided under the FORTH license