Awesome
IrwGAN (ICCV2021)
Unaligned Image-to-Image Translation by Learning to Reweight
[Update] 12/15/2021 All dataset are released, trained models and generated images of IrwGAN are released
[Update] 11/16/2021 Code is pushed, selfie2anime-danbooru dataset released.
Dataset
selfie2anime-danbooru | selfie-horse2zebra-dog | horse-cat2dog-anime | beetle-tiger2lion-sealion
Trained Models and Generated Images
- selfie2anime-danbooru IrwGAN | [Baseline] | [CycleGAN] | [MUNIT] | [GcGAN] | [NICE-GAN]
- selfie-horse2zebra-dog IrwGAN | [Baseline] | [CycleGAN] | [MUNIT] | [GcGAN] | [NICE-GAN]
- horse-cat2dog-anime IrwGAN | [Baseline] | [CycleGAN] | [MUNIT] | [GcGAN] | [NICE-GAN]
- beetle-tiger2lion-sealion IrwGAN | [Baseline] | [CycleGAN] | [MUNIT] | [GcGAN] | [NICE-GAN]
Basic Usage
- Training:
python main.py --dataroot=datasets/selfie2anime-danbooru
- Resume:
python main.py --dataroot=datasets/selfie2anime-danbooru --phase=resume
- Test:
python main.py --dataroot=datasets/selfie2anime-danbooru --phase=test
- Beta Mode
--beta_mode=A
if domain A is unaligned,--beta_mode=B
if domain B is unaligned,--beta_mode=AB
if two domains are unaligned - Effective Sample Size
lambda_nos_A
andlambda_nos_B
are used to control how many samples are selected. The higher the weight, more samples are selected. We use1.0
across all experiments.
Example Results
<img src='imgs/selfie2anime-danbooru.jpg' width=600> <img src='imgs/tiger2lion.jpg' width=600>Citation
If you use this code for your research, please cite our paper:
@inproceedings{xie2021unaligned,
title={Unaligned Image-to-Image Translation by Learning to Reweight},
author={Xie, Shaoan and Gong, Mingming and Xu, Yanwu and Zhang, Kun},
booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
pages={14174--14184},
year={2021}
}