3dpose

目录

3dpose

视频直接输出3d姿态

---

3dpose

Here we compare VIBE with recent state-of-the-art methods on 3D pose estimation datasets. Evaluation metric is Procrustes Aligned Mean Per Joint Position Error (PA-MPJPE) in mm.

Models    3DPW ↓    MPI-INF-3DHP ↓    H36M ↓
SPIN    59.2    67.5    41.1
Temporal HMR    76.7    89.8    56.8
VIBE    56.5    63.4    41.5

有权重，100m

GitHub - mkocabas/VIBE: Official implementation of CVPR2020 paper "VIBE: Video Inference for Human Body Pose and Shape Estimation"

1070跑不起来

smplx==0.1.13
gdown==3.6.4
joblib==0.14.1
pytube==9.5.3
trimesh==3.5.25
pyrender==0.1.36
progress==1.5
filterpy==1.4.5
matplotlib==3.1.3
torchvision==0.5.0
scikit-image==0.16.2
scikit-video==1.1.11
pillow==6.2.1
opencv-python==4.1.2.30
git+https://github.com/mattloper/chumpy.git
git+https://github.com/mkocabas/yolov3-pytorch.git
git+https://github.com/mkocabas/multi-person-tracker.git

视频直接输出3d姿态

b. 通过⼆维图像，以端到端的⽅式直接预测三维⼈体姿态

▪ HMR

▪ NBF

▪ MonoPerfCap

vibe也是