Body(3D,Kpt,Mview,Img)¶
Campus Dataset¶
Voxelpose + Voxelpose on Campus¶
VoxelPose (ECCV'2020)
@inproceedings{tumultipose,
title={VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment},
author={Tu, Hanyue and Wang, Chunyu and Zeng, Wenjun},
booktitle={ECCV},
year={2020}
}
Campus (CVPR'2014)
@inproceedings {belagian14multi,
title = {{3D} Pictorial Structures for Multiple Human Pose Estimation},
author = {Belagiannis, Vasileios and Amin, Sikandar and Andriluka, Mykhaylo and Schiele, Bernt and Navab
Nassir and Ilic, Slobodan},
booktitle = {IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2014},
month = {June},
organization={IEEE}
}
Results on Campus dataset.
Arch | Actor 1 | Actor 2 | Actor 3 | Average | ckpt | log |
---|---|---|---|---|---|---|
prn32_cpn80_res50 | 97.76 | 93.92 | 98.48 | 96.72 | ckpt | log |
prn64_cpn80_res50 | 97.76 | 93.33 | 98.77 | 96.62 | ckpt | log |
Panoptic Dataset¶
Voxelpose + Voxelpose + Prn64x64x64 + Cpn80x80x20 + Panoptic on Panoptic¶
VoxelPose (ECCV'2020)
@inproceedings{tumultipose,
title={VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment},
author={Tu, Hanyue and Wang, Chunyu and Zeng, Wenjun},
booktitle={ECCV},
year={2020}
}
CMU Panoptic (ICCV'2015)
@Article = {joo_iccv_2015,
author = {Hanbyul Joo, Hao Liu, Lei Tan, Lin Gui, Bart Nabbe, Iain Matthews, Takeo Kanade, Shohei Nobuhara, and Yaser Sheikh},
title = {Panoptic Studio: A Massively Multiview System for Social Motion Capture},
booktitle = {ICCV},
year = {2015}
}
Results on CMU Panoptic dataset.
Arch | mAP | mAR | MPJPE | Recall@500mm | ckpt | log |
---|---|---|---|---|---|---|
prn64_cpn80_res50 | 97.31 | 97.99 | 17.57 | 99.85 | ckpt | log |
Shelf Dataset¶
Voxelpose + Voxelpose on Shelf¶
VoxelPose (ECCV'2020)
@inproceedings{tumultipose,
title={VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment},
author={Tu, Hanyue and Wang, Chunyu and Zeng, Wenjun},
booktitle={ECCV},
year={2020}
}
Shelf (CVPR'2014)
@inproceedings {belagian14multi,
title = {{3D} Pictorial Structures for Multiple Human Pose Estimation},
author = {Belagiannis, Vasileios and Amin, Sikandar and Andriluka, Mykhaylo and Schiele, Bernt and Navab
Nassir and Ilic, Slobo
booktitle = {IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2014},
month = {June},
organization={IEEE}
}
Results on Shelf dataset.
Arch | Actor 1 | Actor 2 | Actor 3 | Average | ckpt | log |
---|---|---|---|---|---|---|
prn32_cpn48_res50 | 99.10 | 94.86 | 97.52 | 97.16 | ckpt | log |
prn64_cpn80_res50 | 99.00 | 94.59 | 97.64 | 97.08 | ckpt | log |