sketch2pose / app.py
kbrodt's picture
Update app.py
b601d4d
raw
history blame
4.22 kB
import os
import shutil
import subprocess
import textwrap
from pathlib import Path
import gradio as gr
import torch
from huggingface_hub import hf_hub_download
REPO_ID = "kbrodt/sketch2pose"
API_TOKEN = os.environ["sketch2pose"]
ASSET_DIR = Path("./assets")
SAVE_DIR = "output"
CMD = textwrap.dedent("""
python src/pose.py
--save-path {}
--img-path {}
""")
TITLE = "Sketch2Pose: Estimating a 3D Character Pose from a Bitmap Sketch"
DESCRIPTION = '''
<head>
<style>
html {
margin: 0;
padding: 0;
}
body {
margin: 0 auto;
padding: 0.5em;
text-align: justify;
max-width: 800px;
}
figure {
margin: 0;
font-size: smaller;
text-align: justify;
}
img {
width: auto;
max-width: 100%;
height: auto;
}
video {
width: auto;
max-width: 100%;
height: auto;
}
ul.horizontal {
padding: 0;
}
ul.horizontal li {
padding: 0 1em 0 0;
display: inline-block;
}
</style>
</head>
<figure>
<img src="http://www-labs.iro.umontreal.ca/~bmpix/sketch2pose/teaser.png" alt="sketch2pose">
<figcaption>
Given a single natural <b>bitmap</b> sketch of a character (a), our
learning-based approach allows to automatically, with no additional input,
recover the 3D pose consistent with the viewer expectation (b). This pose can
be then automatically copied a custom rigged and skinned 3D character (c) using
standard retargeting tools (d). Input image &copy;&nbsp;Olga Posukh.
</figcaption>
</figure>
<p>
<ul class="horizontal">
<li><a href="https://dl.acm.org/doi/10.1145/3528223.3530106">[paper acm siggraph 2022]</a></li>
<li><a href="https://github.com/kbrodt/sketch2pose">[code.git]</a>
<iframe src="https://ghbtns.com/github-btn.html?user=kbrodt&repo=sketch2pose&type=star&count=true&v=2&size=small" frameborder="0" scrolling="0" width="100" height="20"></iframe>
</li>
</ul>
</p>
<video width="560" height="315" controls autoplay muted loop>
<source src="http://www-labs.iro.umontreal.ca/~bmpix/sketch2pose/sketch2pose.webm" type="video/mp4">
</video>
'''
def prepare():
filename = "models_smplx_v1_1.zip"
smpl_path = hf_hub_download(
repo_id=REPO_ID,
repo_type="model",
filename=filename,
use_auth_token=API_TOKEN,
cache_dir=ASSET_DIR,
)
if not (ASSET_DIR / filename).is_file():
shutil.copy(smpl_path, ASSET_DIR)
subprocess.run("bash ./scripts/download.sh".split())
subprocess.run("bash ./scripts/prepare.sh".split())
def main():
prepare()
save_dir = Path(SAVE_DIR)
save_dir.mkdir(parents=True, exist_ok=True)
def pose(img_path, use_cos=True, use_angle_transf=True, use_contacts=False, use_natural=True):
if use_cos == False:
use_angle_transf = False
cmd = CMD.format(save_dir, img_path)
if use_cos:
cmd = cmd + " --use-cos"
if use_angle_transf:
cmd = cmd + " --use-angle-transf"
if use_contacts:
cmd = cmd + " --use-contacts"
if use_natural:
cmd = cmd + " --use-natural"
out_dir = (save_dir / Path(img_path).name).with_suffix("")
mesh_path = out_dir / "us.glb"
if not mesh_path.is_file():
subprocess.call(cmd.split())
return str(mesh_path)
examples = []
for img_path in Path("./data/images").glob("*"):
examples.append([str(img_path), True, True, False, True])
break
demo = gr.Interface(
fn=pose,
inputs=[
gr.Image(type="filepath", label="Image"),
gr.Checkbox(value=True, label="Bone lenghts"),
gr.Checkbox(value=True, label="Foreshortening"),
gr.Checkbox(value=False, label="Self-contacts (available with cuda)", interactive=torch.cuda.is_available()),
gr.Checkbox(value=True, label="Pose naturalness"),
],
outputs=gr.Model3D(clear_color=[0.0, 0.0, 0.0, 0.0], label="SMPL 3D pose"),
examples=examples,
title=TITLE,
description=DESCRIPTION,
)
demo.launch()
if __name__ == "__main__":
main()