virtual_sketching - GitLite

KO | EN

gitlite — search

#ai-agents #rag #python #claude-code #kotlin #svg #graphql #ai #react-native #vue

virtual_sketching

(★ 269)

[SIGGRAPH 2021] General Virtual Sketching Framework for Vector Line Art

File Explorer

ZIP Download

- - bootstrap.min.css
  - font.css
  - style.css
- - 1390.png
  - face-blue-1390-simplest.gif
  - muten-black-full-simplest.gif
  - muten.png
  - rocket-blue-simplest.gif
  - rocket.png
- index.html
- NeuralRenderer.py
- RealRenderer.py
- - banana_tree.png
  - dracolion.png
  - duck.png
  - elephant.png
  - hippo.png
  - kitten.png
  - mouse.png
  - muten.png
  - penguin.png
  - puppy.png
  - sheriff.png
- - 1190.png
  - 120.png
  - 1390.png
  - 1490.png
  - 150.png
  - 1540.png
  - 1840.png
  - 1860.png
  - 1910.png
  - 230.png
  - 460.png
  - 500.png
  - 60.png
  - 610.png
  - 690.png
  - 910.png
  - ffhq148.png
  - ffhq194.png
  - ffhq368.png
- - bird.png
  - duck.png
  - hand.png
  - house.png
  - kitten.png
  - penguin1.png
  - penguin2.png
  - rocket.png
- gif_making.py
- svg_conversion.py
- visualize_drawing.py
- VGG16.py
.gitignore
dataset_utils.py
hyper_parameters.py
launch_gui.bat
LICENSE
model_common_test.py
model_common_train.py
README.md
README.md.backup
README_CN.md
rnn.py
subnet_tf_utils.py
test_photograph_to_line.py
test_rough_sketch_simplification.py
test_vectorization.py
train_rough_photograph.py
train_vectorization.py
utils.py
virtual_sketch_gui.py
WINDOWS_INSTALL_GUIDE.md

# Use via CDN

jsDelivr

jsDelivr serves any public GitHub repository as a CDN with zero setup. Pick a version and a file to get a ready-to-paste link and snippet.

Version

File

Link

Example

Command Glossary

Commands referenced in this DOCs, explained below.

🔍

`cluster`

View Details ▼

Find clusters in a graph and augment the graph with this information.

cluster {{input.gv}}

Generate clusters that optimize modularity and print the result to `stdout`:

cluster -C {{5}} {{input.gv}}

Specify a target number of [C]lusters (approximate) to generate (0 by default, meaning a number that approximately optimizes the modularity):

cluster -c {{0|1}} {{input.gv}}

Use a different [c]lustering method (0: modularity clustering, 1: modularity quality):

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

[[Paper]](https://esslab.jp/publications/HaoranSIGRAPH2021.pdf) | [[Project Page]](https://markmohr.github.io/virtual_sketching/) | [[中文Readme]](/README_CN.md) | [[中文论文介绍]](https://blog.csdn.net/qq_33000225/article/details/118883153)

This code is used for **line drawing vectorization**, **rough sketch simplification** and **photograph to vector line drawing**.

<img src='docs/figures/muten.png' height=300><img src='docs/figures/muten-black-full-simplest.gif' height=300>

<img src='docs/figures/rocket.png' height=150><img src='docs/figures/rocket-blue-simplest.gif' height=150>&nbsp;&nbsp;&nbsp;&nbsp;<img src='docs/figures/1390.png' height=150><img src='docs/figures/face-blue-1390-simplest.gif' height=150>

## Outline
- [Dependencies](#dependencies)
- [Testing with Trained Weights](#testing-with-trained-weights)
- [Training](#training)
- [Citation](#citation)
- [Projects Using this Model/Method](#projects-using-this-modelmethod)
- [Blogs Mentioning this Paper](#blogs-mentioning-this-paper)
- [For Windows users](#-windows-users)

## Dependencies
 - [Tensorflow](https://www.tensorflow.org/) (1.12.0 <= version <=1.15.0)
 - [opencv](https://opencv.org/) == 3.4.2
 - [pillow](https://pillow.readthedocs.io/en/latest/index.html) == 6.2.0
 - [scipy](https://www.scipy.org/) == 1.5.2
 - [gizeh](https://github.com/Zulko/gizeh) == 0.1.11

## Testing with Trained Weights
### Model Preparation

Download the models [here](https://drive.google.com/drive/folders/1-hi2cl8joZ6oMOp4yvk_hObJGAK6ELHB?usp=sharing): 
  - `pretrain_clean_line_drawings` (105 MB): for vectorization
  - `pretrain_rough_sketches` (105 MB): for rough sketch simplification
  - `pretrain_faces` (105 MB): for photograph to line drawing

Then, place them in this file structure:
```
outputs/
    snapshot/
        pretrain_clean_line_drawings/
        pretrain_rough_sketches/
        pretrain_faces/
```

### Usage
Choose the image in the `sample_inputs/` directory, and run one of the following commands for each task. The results will be under `outputs/sampling/`.

``` python
python3 test_vectorization.py --input muten.png

python3 test_rough_sketch_simplification.py --input rocket.png

python3 test_photograph_to_line.py --input 1390.png
```

**Note!!!** Our approach starts drawing from a randomly selected initial position, so it outputs different results in every testing trial (some might be fine and some might not be good enough). It is recommended to do several trials to select the visually best result. The number of outputs can be defined by the `--sample` argument:

``` python
python3 test_vectorization.py --input muten.png --sample 10

python3 test_rough_sketch_simplification.py --input rocket.png --sample 10

python3 test_photograph_to_line.py --input 1390.png --sample 10
```

**Reproducing Paper Figures:** our results (download from [here](https://drive.google.com/drive/folders/1-hi2cl8joZ6oMOp4yvk_hObJGAK6ELHB?usp=sharing)) are selected by doing a certain number of trials. Apparently, it is required to use the same initial drawing positions to reproduce our results.

### Additional Tools

#### a) Visualization

Our vector output is stored in a `npz` package. Run the following command to obtain the rendered output and the drawing order. Results will be under the same directory of the `npz` file.
``` python
python3 tools/visualize_drawing.py --file path/to/the/result.npz 
```

#### b) GIF Making

To see the dynamic drawing procedure, run the following command to obtain the `gif`. Result will be under the same directory of the `npz` file.
``` python
python3 tools/gif_making.py --file path/to/the/result.npz 
```

#### c) Conversion to SVG

Our vector output in a `npz` package is stored as Eq.(1) in the main paper. Run the following command to convert it to the `svg` format. Result will be under the same directory of the `npz` file.

``` python
python3 tools/svg_conversion.py --file path/to/the/result.npz 
```
  - The conversion is implemented in two modes (by setting the `--svg_type` argument):
    - `single` (default): each stroke (a single segment) forms a path in the SVG file
    - `cluster`: each continuous curve (with multiple strokes) forms a path in the SVG file

**Important Notes**

In SVG format, all the segments on a path share the same *stroke-width*. While in our stroke design,  strokes on a common curve have different widths. Inside a stroke (a single segment), the thickness also changes linearly from an endpoint to another. 
Therefore, neither of the two conversion methods above generate visually the same results as the ones in our paper.
*(Please mention this issue in your paper if you do qualitative comparisons with our results in SVG format.)*

<br>

## Training

### Preparations

Download the models [here](https://drive.google.com/drive/folders/1-hi2cl8joZ6oMOp4yvk_hObJGAK6ELHB?usp=sharing): 
  - `pretrain_neural_renderer` (40 MB): the pre-trained neural renderer
  - `pretrain_perceptual_model` (691 MB): the pre-trained perceptual model for raster loss

Download the datasets [here](https://drive.google.com/drive/folders/1-hi2cl8joZ6oMOp4yvk_hObJGAK6ELHB?usp=sharing): 
  - `QuickDraw-clean` (14 MB): for clean line drawing vectorization. Taken from [QuickDraw](https://github.com/googlecreativelab/quickdraw-dataset) dataset.
  - `QuickDraw-rough` (361 MB): for rough sketch simplification. Synthesized by the pencil drawing generation method from [Sketch Simplification](https://github.com/bobbens/sketch_simplification#pencil-drawing-generation).
  - `CelebAMask-faces` (370 MB): for photograph to line drawing. Processed from the [CelebAMask-HQ](https://github.com/switchablenorms/CelebAMask-HQ) dataset.

Then, place them in this file structure:
```
datasets/
    QuickDraw-clean/
    QuickDraw-rough/
    CelebAMask-faces/
outputs/
    snapshot/
        pretrain_neural_renderer/
        pretrain_perceptual_model/
```

### Running

It is recommended to train with multi-GPU. We train each task with 2 GPUs (each with 11 GB).

``` python
python3 train_vectorization.py

python3 train_rough_photograph.py --data rough

python3 train_rough_photograph.py --data face
```

<br>

## Citation

If you use the code and models please cite:

```
@article{mo2021virtualsketching,
  title   = {General Virtual Sketching Framework for Vector Line Art},
  author  = {Mo, Haoran and Simo-Serra, Edgar and Gao, Chengying and Zou, Changqing and Wang, Ruomei},
  journal = {ACM Transactions on Graphics (Proceedings of ACM SIGGRAPH 2021)},
  year    = {2021},
  volume  = {40},
  number  = {4},
  pages   = {51:1--51:14}
}
```

<br>

## Projects Using this Model/Method

| **[Painterly style transfer](https://github.com/xch-liu/Painterly-Style-Transfer) (TVCG 2023)**  | **[Scene sketching](https://github.com/yael-vinker/SceneSketch) (ICCV 2023)** | 
|:-------------:|:-------------------:|
| <img src="docs/figures/applications/Painterly-Style-Transfer.png" style="height: 170px"> | <img src="docs/figures/applications/iccv2023scenesketch.png" style="height: 170px"> |
| **[Geometrized cartoon line inbetweening](https://github.com/lisiyao21/AnimeInbet) (ICCV 2023)**  | **[Stroke correspondence and inbetweening](https://github.com/MarkMoHR/JoSTC) (TOG 2024)** | 
| <img src="docs/figures/applications/Geometrized-Cartoon-Line-Inbetweening.png" style="height: 170px"> | <img src="docs/figures/applications/Vector-Line-Inbetweening2.png" style="height: 170px"><img src="docs/figures/applications/Vector-Line-Inbetweening-dynamic1.gif" style="height: 170px"> |
| **[Modelling complex vector drawings](https://github.com/Co-do/Stroke-Cloud) (ICLR 2024)**  | **[Sketch-to-Image Generation](https://github.com/BlockDetail/Block-and-Detail) (UIST 2024)** | 
| <img src="docs/figures/applications/complex-vector-drawings.png" style="height: 170px"> | <img src="docs/figures/applications/sketch-to-image.png" style="height: 170px"> |
| **[Robot calligraphy](https://github.com/LoYuXr/CalliRewrite) (ICRA 2024)**  | **[Human-Like Robot Handwriting](https://github.com/RittoQin/CHTR) (CVPR 2026)** | 
| <img src="docs/figures/applications/robot-calligraphy.png" style="height: 170px"> | <img src="docs/figures/applications/cvpr2026.png" style="height: 170px"> |

## Blogs Mentioning this Paper

- [The state of AI for hand-drawn animation inbetweening](https://yosefk.com/blog/the-state-of-ai-for-hand-drawn-animation-inbetweening.html)

## 🪟 Windows users

See [WINDOWS_INSTALL_GUIDE.md](WINDOWS_INSTALL_GUIDE.md) for a complete Windows installation guide and GUI usage.