UVCGAN: UNet Vision Transformer cycle-consistent GAN for unpaired image-to-image translation

2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)(2023)

引用 21|浏览69
暂无评分
摘要
Unpaired image-to-image translation has broad applications in art, design, and scientific simulations. One early breakthrough was CycleGAN that emphasizes one-to-one mappings between two unpaired image domains via generative-adversarial networks (GAN) coupled with the cycle-consistency constraint, while more recent works promote one-to-many mapping to boost diversity of the translated images. Motivated by scientific simulation and one-to-one needs, this work revisits the classic CycleGAN framework and boosts its performance to outperform more contemporary models without relaxing the cycle-consistency constraint. To achieve this, we equip the generator with a Vision Transformer (ViT) and employ necessary training and regularization techniques. Compared to previous best-performing models, our model performs better and retains a strong correlation between the original and translated image. An accompanying ablation study shows that both the gradient penalty and self-supervised pre-training are crucial to the improvement. To promote reproducibility and open science, the source code, hyperparameter configurations, and pre-trained model are available at https: //github.com/LS4GAN/uvcgan.
更多
查看译文
关键词
Algorithms: Computational photography,image and video synthesis,Explainable,fair,accountable,privacy-preserving,ethical computer vision,Machine learning architectures,formulations,and algorithms (including transfer,low-shot,semi-,self-,and un-supervised learning)
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要