Quick Start

  1. Demo for Motion Capture
    1. Demo on multiple calibrated cameras
    2. Demo on monocular videos
    3. Demo on monocular+mirror videos
  2. Demo for Novel View Synthesis
    1. Demo for NeuralBody

Please check EasyMoCap v0.3 for more details.

Demo for Motion Capture

Demo on multiple calibrated cameras

The example dataset can be download from 01_triangulate/street_dance.zip. After downloading, unzip it to the data/examples folder.

data=data/examples/street_dance
emc --data config/datasets/mvimage.yml --exp config/mv1p/detect_triangulate_fitSMPL.yml --root ${data} --subs_vis 07 01 05 03

The results can be found in output/detect_triangulate_fitSMPL.


Video are captured outdoors using 9 smartphones.

Our method only takes 30 seconds to optimize the SMPL model of 800 frames. As rendering the results takes the longest time, you can add flag ` –skip_vis` to skip this.

Demo on monocular videos

The example dataset can be download from 03_fitmono/internet-rotate.zip. After downloading, unzip it to the data/examples folder.

data=data/examples/internet-rotate
emc --data config/datasets/svimage.yml --exp config/1v1p/hrnet_pare_finetune.yml --root ${data} --ranges 0 500 1 --subs 23EfsN7vEOA+003170+003670

The raw video is from Youtube.

Demo on monocular+mirror videos

Download example dataset here and extract the dataset.

data=<path/to/data>
python3 apps/demo/mocap.py ${data} --work mirror --fps 30 --vis_scale 0.5

Videos come from Youtube.

Demo for Novel View Synthesis

Demo for NeuralBody

Download example dataset here and extract the dataset.

data=/path/to/data
# Train Neuralbody:
python3 apps/neuralbody/demo.py ${data} --mode neuralbody --gpus 0,
# Render Neuralbody:
python3 apps/neuralbody/demo.py ${data} --mode neuralbody --gpus 0, --demo

Full step of motion capture and data preparation:

# motion capture
python3 apps/demo/mocap.py ${data} --work lightstage-dense-unsync --subs_vis 01 07 13 19 --disable_crop

Table of contents