Skip to content
The authors' implementation of Unsupervised Adversarial Learning of 3D Human Pose from 2D Joint Locations
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
bin Bug fix for demo Jun 19, 2018
data
projection_gan
sample Bug fix for demo Jun 19, 2018
.gitattributes ⭐️ pretrained model for demo Apr 2, 2018
.gitignore
LICENSE Initial commit Dec 4, 2017
README.md
requirements.txt
setup.py

README.md

Unsupervised Adversarial Learning of 3D Human Pose from 2D Joint Locations

This is the authors' implementation of Unsupervised Adversarial Learning of 3D Human Pose from 2D Joint Locations

Run Inference for demo (with openpose)

  1. Download openpose pretrained model
  2. Run Inference
    • python bin/demo.py sample/image.png --lift_model sample/gen_epoch_500.npz --model2d pose_iter_440000.caffemodel --proto2d openpose_pose_coco.prototxt
    • Need OpenCV >= 3.4
      • < 3.3 results extreamly wrong estimation

Dependencies(Recommended versions)

Training

Human3.6M dataset

  • Unsupervised learning of 3D points from ground truth 2D points

    python bin/train.py --gpu 0 --mode unsupervised --dataset h36m --use_heuristic_loss
    
  • Unsupervised learning of 3D points from detected 2D points by Stacked Hourglass

    TBA

  • Supervised learning of 3D points from ground truth 2D points

    python bin/train.py --gpu 0 --mode supervised --activate_func relu --use_bn
    

MPII dataset

TBA

MPI-INF-3DHP dataset

TBA

Evaluation

python bin/eval.py results/hoge/gen_epoch_*.npz
You can’t perform that action at this time.