Detail Fusion GAN: High-Quality Translation for Unpaired Images with GAN-based Data Augmentation
发布时间：2025-04-30
点击次数：
- 发布时间：
- 2025-04-30
- 论文名称：
- Detail Fusion GAN: High-Quality Translation for Unpaired Images with GAN-based Data Augmentation
- 发表刊物：
- ICPR 2020
- 摘要：
- Image-to-image translation is a rapid-growing research field in deep learning. It aims to learn the mapping relation between two different domains. Although the existing Generative Adversarial Network(GAN)-based methods have achieved respectable results in this field, there are still some limitations in generating high-quality images for data augmentation. In this work, we focus on image-to-image translation task with the presence of artifacts and the lack of details. To solve these issues, we propose a details fusion generative adversarial network,which consists of details branch,transfer branch, adaptive module and fusion module. By introducing the dual branch design, the proposed model could enhance the generated results with corresponding style and content. Extensive experiments suggest that our model generates more satisfactory images than the competing methods on data augmentation task.
- 合写作者：
- L Li, Y Li, C Wu, H Dong, P Jiang and F Wang
- 是否译文：
- 否
- 发表时间：
- 2021-01-15