Home

Awesome

Im2Pencil

Pytorch implementation of our CVPR19 paper on controllable pencil illustration from photographs. More results and comparisons are shown here.

<p> <img src='output/mouse_outline.gif' width=800 /> </p>

A line input (left) and two pencil outline results (middle: clean, right: rough)

<p> <img src='output/15--104.png' height=275 /> <img src='output/15--104_shading.png' height=275 /> </p>

A photo input (left) and four pencil shading results (right: [hatching, crosshatching; blending, stippling])

Getting started

git clone https://github.com/Yijunmaverick/Im2Pencil
cd Im2Pencil

Preparation

sh pretrained_models/download_models.sh

cd extract_edge_tone
Im2Pencil_get_edge_tone.m

Testing

python test.py  --outline_style 1  --shading_style 1

Outline style: 0 for rough and 1 for clean

Shading style: 0, 1, 2, 3 for hatching, crosshatching, stippling, and blending respectively

For other controllable parameters, check options/test_options.py

Citation

@inproceedings{Im2Pencil-CVPR-2019,
    author = {Li, Yijun and Fang, Chen and Hertzmann, Aaron and Shechtman, Eli and Yang, Ming-Hsuan},
    title = {Im2Pencil: Controllable Pencil Illustration from Photographs},
    booktitle = {IEEE Conference on Computer Vision and Pattern Recognition},
    year = {2019}
}

Acknowledgement