/doodle_texture_synthesis

Masked Texture Synthesis with Multiresolution Pyramid Rendering

Primary LanguageJupyter Notebook

Masked Texture Synthesis with Multiresolution Pyramid Rendering

This repository contains a Tensorflow implementation which performs texture analysis given a doodle drawing and some input textures corresponding to the colors in this drawing. The algorithm will then create a composition using these input textures and the given drawing.

This algorithm makes use of Multiresolution Pyramid Rendering to improve the quality and increased resolution of the result. To further improve the quality of the resulting composition we make use of several loss functions, including Gram, Histogram and Total Variance loss.

Setup

Dependencies:

Optional (but recommended) dependencies:

After installing the dependencies:

Usage

Run the iPython notebook transfer.ipynb and change the parameters. The code is sufficiently commented to explain itself.

Examples

Loss functions

Input imageGramGram + Histogram + TV

Doodle masking

Input imageCorresponding maskSynthesizedPyramid