peterzs / savi2i

Continuous and Diverse Image-to-Image Translation via Signed Attribute Vectors

SAVI2I: Continuous and Diverse Image-to-Image Translation via Signed Attribute Vectors

[Paper] [Project Website]

Pytorch implementation for SAVI2I. We propose a simple yet effective signed attribute vector (SAV) that facilitates continuous translation on diverse mapping paths across multiple domains.
More video results please see Our Webpage
Contact: Qi Mao ([email protected])

Paper

Continuous and Diverse Image-to-Image Translation via Signed Attribute Vectors
Qi Mao, Hsin-Ying Lee, Hung-Yu Tseng, Jia-Bin Huang, Siwei Ma, and Ming-Hsuan Yang
In arXiv 2020

Citation

If you find this work useful for your research, please cite our paper:

    @article{mao2020continuous,
      author       = "Mao, Qi and Lee, Hsin-Ying and Tseng, Hung-Yu and Huang, Jia-Bin and Ma, Siwei and Yang, Ming-Hsuan",
      title        = "Continuous and Diverse Image-to-Image Translation via Signed Attribute Vectors",
      journal    = "arXiv preprint 2011.01215",
      year         = "2020"
    }

Quick Start

Prerequisites

• Linux or Windows
• Python 3+
• Suggest to use two P100 16GB GPUs or One V100 32GB GPU.

Install

• Clone this repo:

git clone https://github.com/HelenMao/SAVI2I.git
cd SAVI2I

• This code requires Pytorch 0.4.0+ and Python 3+. Please install dependencies by

conda create -n SAVI2I python=3.6
source activate SAVI2I
pip install -r requirements.txt 

Training Datasets

Download datasets for each task into the dataset folder

./datasets

• Style translation: Yosemite (summer <-> winter) and Photo2Artwork (Photo, Monet, Van Gogh and Ukiyo-e)
  

• You can follow the instructions of CycleGAN datasets to download Yosemite and Photo2artwork datasets.

• Shape-variation translation: CelebA-HQ (Male <-> Female) and AFHQ (Cat, Dog and WildLife)
  

• We split CelebA-HQ into male and female domains according to the annotated label and fine-tune the images manaully.
• You can follow the instructions of StarGAN-v2 datasets to download CelebA-HQ and AFHQ datasets.

Training

Notes

For low-level style translation tasks, you suggest to set --type=1 to use corresponding network architectures.
For shape-variation translation tasks, you suggest to set --type=0 to use corresponding network architectures.

• Yosemite

python train.py --dataroot ./datasets/Yosemite/ --phase train --type 1 --name Yosemite --n_ep 700 --n_ep_decay 500 --lambda_r1 10 --lambda_mmd 1 --num_domains 2

• Photo2artwork

python train.py --dataroot ./datasets/Photo2artwork/ --phase train --type 1 --name Photo2artwork --n_ep 100 --n_ep_decay 0 --lambda_r1 10 --lambda_mmd 1 --num_domains 4

• CelebAHQ

python train.py --dataroot ./datasets/CelebAHQ/ --phase train --type 0 --name CelebAHQ --n_ep 30 --n_ep_decay 0 --lambda_r1 1 --lambda_mmd 1 --num_domains 2

• AFHQ

python train.py --dataroot ./datasets/AFHQ/ --phase train --type 0 --name AFHQ --n_ep 100 --n_ep_decay 0 --lambda_r1 1 --lambda_mmd 10 --num_domains 3

Pre-trained Models

• Yosemite
• Photo2artwork
• CelebAHQ
• AFHQ

Download and save them into

./models

or download the pre-trained models with the following script.

bash ./download_models.sh

Testing

Reference-guided

python test_reference_save.py --dataroot ./datasets/CelebAHQ --resume ./models/CelebAHQ/00029.pth --phase test --type 0 --num_domains 2 --index_s A --index_t B --num 5 --name CelebAHQ_ref  

Latent-guided

python test_latent_rdm_save.py --dataroot ./datasets/CelebAHQ --resume ./models/CelebAHQ/00029.pth --phase test --type 0 --num_domains 2 --index_s A --index_t B --num 5 --name CelebAHQ_rdm  

License

All rights reserved.
Licensed under the CC BY-NC-SA 4.0 (Attribution-NonCommercial-ShareAlike 4.0 International).
The codes are only for academical research use. For commercial use, please contact [email protected].

Acknowledgements

Codes and network architectures inspired from:

• DRIT++
• StarGAN-v2