app.py

# install


import glob
import gradio as gr
import os
import random

import subprocess

if os.getenv('SYSTEM') == 'spaces':
    subprocess.run('pip install pyembree'.split())
    subprocess.run('pip install rembg'.split())
    subprocess.run(
        'pip install torch==1.11.0+cu113 torchvision==0.12.0+cu113 -f https://download.pytorch.org/whl/cu113/torch_stable.html'.split())
    subprocess.run(
        'pip install git+https://github.com/YuliangXiu/kaolin.git'.split())
    subprocess.run('pip install --no-index --no-cache-dir pytorch3d -f https://dl.fbaipublicfiles.com/pytorch3d/packaging/wheels/py38_cu113_pyt1110/download.html'.split())
    subprocess.run(
        'pip install git+https://github.com/Project-Splinter/human_det.git'.split())
    subprocess.run(
        'pip install git+https://github.com/YuliangXiu/neural_voxelization_layer.git'.split())

from apps.infer import generate_model

# running

description = '''
# ICON Clothed Human Digitization 
### ICON: Implicit Clothed humans Obtained from Normals (CVPR 2022)

<table>
<th>
<ul>
<li><strong>Homepage</strong> <a href="http://icon.is.tue.mpg.de">icon.is.tue.mpg.de</a></li>
<li><strong>Code</strong> <a href="https://github.com/YuliangXiu/ICON">YuliangXiu/ICON</a>
<li><strong>Paper</strong> <a href="https://arxiv.org/abs/2112.09127">arXiv</a>, <a href="https://readpaper.com/paper/4569785684533977089">ReadPaper</a>
<li><strong>Chatroom</strong> <a href="https://discord.gg/Vqa7KBGRyk">Discord</a>
</ul>
<a href="https://twitter.com/yuliangxiu"><img alt="Twitter Follow" src="https://img.shields.io/twitter/follow/yuliangxiu?style=social"></a>
<iframe src="https://ghbtns.com/github-btn.html?user=yuliangxiu&repo=ICON&type=star&count=true&v=2&size=small" frameborder="0" scrolling="0" width="100" height="20"></iframe>
<a href="https://youtu.be/hZd6AYin2DE"><img alt="YouTube Video Views" src="https://img.shields.io/youtube/views/hZd6AYin2DE?style=social"></a>
</th>
<th>
<iframe width="560" height="315" src="https://www.youtube.com/embed/hZd6AYin2DE" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>
</th>
</table>

<h4> The reconstruction + refinement + video take about 80~200 seconds for single image. <span style="color:red"> If ERROR, try "Submit Image" again.</span></h4>

<details>

<summary>More</summary>

#### Citation
```
@inproceedings{xiu2022icon,
  title     = {{ICON}: {I}mplicit {C}lothed humans {O}btained from {N}ormals},
  author    = {Xiu, Yuliang and Yang, Jinlong and Tzionas, Dimitrios and Black, Michael J.},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  month     = {June},
  year      = {2022},
  pages     = {13296-13306}
} 
```

#### Acknowledgments:

- [StyleGAN-Human, ECCV 2022](https://stylegan-human.github.io/)
- [nagolinc/styleGanHuman_and_PIFu](https://huggingface.co/spaces/nagolinc/styleGanHuman_and_PIFu)
- [radames/PIFu-Clothed-Human-Digitization](https://huggingface.co/spaces/radames/PIFu-Clothed-Human-Digitization)

#### Image Credits

* [Pinterest](https://www.pinterest.com/search/pins/?q=parkour&rs=sitelinks_searchbox)

#### Related works

* [ICON @ MPI](https://icon.is.tue.mpg.de/)
* [MonoPort @ USC](https://xiuyuliang.cn/monoport)
* [Phorhum @ Google](https://phorhum.github.io/)
* [PIFuHD @ Meta](https://shunsukesaito.github.io/PIFuHD/)
* [PaMIR @ Tsinghua](http://www.liuyebin.com/pamir/pamir.html)

</details>
'''


def generate_image(seed, psi):
    iface = gr.Interface.load("spaces/hysts/StyleGAN-Human")
    img = iface(seed, psi)
    return img


random.seed(2022)
model_types = ['icon-filter', 'pifu', 'pamir']
examples = [[item, random.choice(model_types)] for item in glob.glob('examples/*.png')]

with gr.Blocks() as demo:
    gr.Markdown(description)

    out_lst = []
    with gr.Row():
        with gr.Column():
            with gr.Row():
                with gr.Column():
                    seed = gr.inputs.Slider(
                        0, 100, step=1, default=0, label='Seed (For Image Generation)')
                    psi = gr.inputs.Slider(
                        0, 2, step=0.05, default=0.7, label='Truncation psi (For Image Generation)')
                    radio_choice = gr.Radio(
                        model_types, label='Method (For Reconstruction)', value='icon-filter')
                inp = gr.Image(type="filepath", label="Input Image")
            with gr.Row():
                btn_sample = gr.Button("Sample Image")
                btn_submit = gr.Button("Submit Image")

            gr.Examples(examples=examples,
                        inputs=[inp, radio_choice],
                        cache_examples=True,
                        fn=generate_model,
                        outputs=out_lst)

            out_vid = gr.Video(label="Image + Normal + Recon + Refined Recon")
            out_vid_download = gr.File(
                label="Download Video, welcome share on Twitter with #ICON")

        with gr.Column():
            overlap_inp = gr.Image(
                type="filepath", label="Image Normal Overlap")
            out_smpl = gr.Model3D(
                clear_color=[0.0, 0.0, 0.0, 0.0],  label="SMPL")
            out_smpl_download = gr.File(label="Download SMPL mesh")
            out_smpl_npy_download = gr.File(label="Download SMPL params")
            out_recon = gr.Model3D(
                clear_color=[0.0, 0.0, 0.0, 0.0],  label="Recon")
            out_recon_download = gr.File(label="Download clothed human mesh")
            out_final = gr.Model3D(
                clear_color=[0.0, 0.0, 0.0, 0.0],  label="Refined Recon")
            out_final_download = gr.File(
                label="Download refined clothed human mesh")

    out_lst = [out_smpl, out_smpl_download, out_smpl_npy_download, out_recon, out_recon_download,
               out_final, out_final_download, out_vid, out_vid_download, overlap_inp]

    btn_submit.click(fn=generate_model, inputs=[
                     inp, radio_choice], outputs=out_lst)
    btn_sample.click(fn=generate_image, inputs=[seed, psi], outputs=inp)

if __name__ == "__main__":

    # demo.launch(debug=False, enable_queue=False,
    #             auth=(os.environ['USER'], os.environ['PASSWORD']),
    #             auth_message="Register at icon.is.tue.mpg.de to get HuggingFace username and password.")

    demo.launch(debug=True, enable_queue=True)