GitHub - liubindlut/SilhouettesbasedHSE: Test code for 'Consice and effective network for 3D human modeling from orthogonal silhouettes'

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 7 Commits
Images		Images
Models		Models
realData		realData
train		train
demo_real.py		demo_real.py
readme.txt		readme.txt
regressCNN.py		regressCNN.py
widgets_HSE.py		widgets_HSE.py

Repository files navigation

This is a demo for testing our algorithm 
"Concise and effective network for 3D human modeling from orthogonal sihouettes".

(1) The main function is in demo_real.py.
    It has thress parameters.
    Default output position:
            output_dir = './Image/'
    front and side view images as a list
            img_filenames = ['./Image/5front.jpg', './Image/5side.jpg']
    Body height is specified(m)
            body_height = 1.6

    The final result is 'name.obj', in the Image file.