anopara/genetic-drawing

Stars
2,173
Rank 21,224 (Top 0.5 %)
Language
Python
License
MIT License
Created over 4 years ago
Updated over 4 years ago

anopara/genetic-drawing

anopara

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

A genetic algorithm toy project for drawing

Genetic Drawing

This is a toy project I did around 2017 for imitating a drawing process given a target image (inspired by many examples of genetic drawing on the internet, and this was my take on it, mostly as an exercise).

Due to a popular request, it is now opensource 🙂

Examples of generated images:

It also supports user-created sampling masks, in case you'd like to specify regions where more brushstrokes are needed (for ex, to allocate more finer details)

Python

you would need the following python 3 libraries:

opencv 3.4.1
numpy 1.16.2
matplotlib 3.0.3
and Jupyter Notebook

To start, open the GeneticDrawing.ipynb and run the example code

country-slice

patch-based-texture-synthesis

Based on "Image Quilting for Texture Synthesis and Transfer" and "Real-Time Texture Synthesis by Patch-Based Sampling" papers

Jupyter Notebook

texture-synthesis-nonparametric-sampling

Implementation of "Texture Synthesis with Non-Parametric Sampling" paper by Alexei A. Efros and Thomas K. Leung

Jupyter Notebook

multi-resolution-texture-synthesis

Based on “Fast Texture Synthesis using Tree-structured Vector Quantization” and “Multiresolution Sampling Procedure for Analysis and Synthesis of Texture Images” papers

Jupyter Notebook

presentation-houdini-vis

Houdini files of visualizations from my presentation "Place like I do! Example-based procedural placements in a dialogue system"

example-based-procedural-placement

A description and links to the Example-based Procedural Placement algorithm slides and presentation

texture-optimization

Based on "Texture optimization for example-based synthesis" by Vivek Kwatra, Irfan Essa, Aaron Bobick, and Nipun Kwatra

spectral-processing

personal tests/experiments/exercises connected with spectral mesh processing

Jupyter Notebook