MUNIT-Tensorflow

Simple Tensorflow implementation of "Multimodal Unsupervised Image-to-Image Translation"

Requirements

• Tensorflow 1.4
• Python 3.6

Issue

• Author uses so many iterations (1M = 1,000,000)
• Author uses LSGAN, but do not multiply each of G and D by 0.5

Usage

├── dataset
   └── YOUR_DATASET_NAME
       ├── trainA
           ├── xxx.jpg (name, format doesn't matter)
           ├── yyy.png
           └── ...
       ├── trainB
           ├── zzz.jpg
           ├── www.png
           └── ...
       ├── testA
           ├── aaa.jpg 
           ├── bbb.png
           └── ...
       └── testB
           ├── ccc.jpg 
           ├── ddd.png
           └── ...
           
├── guide.jpg (example for guided image translation task)

Train

• python main.py --phase train --dataset summer2winter --batch_size 1

Test

• python main.py --phase test --dataset summer2winter --batch_size 1 --num_style 3

Guided Image Translation

• python main.py --phase guide --dataset summer2winter --batch_size 1 --direction a2b --guide_img guide.jpg

Summary

Architecture

Model Overview

Results

Edges to Shoes/handbags Translation

Animal Image Translation

Street Scene Translation

Yosemite Summer to Winter Translation (HD)

Example-guided Image Translation

Related works

• CycleGAN-Tensorflow
• DiscoGAN-Tensorflow
• UNIT-Tensorflow
• StarGAN-Tensorflow
• DRIT-Tensorflow

Reference

• MUNIT-Pytorch (Author implementation)

Author

Junho Kim