期刊
PROCEEDINGS OF THE 27TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA (MM'19)
卷 -, 期 -, 页码 1267-1276出版社
ASSOC COMPUTING MACHINERY
DOI: 10.1145/3343031.3351004
关键词
Generative adversarial networks; Image generation; Image translation
资金
- Chinese Scholarship Council (CSC) [201507040048]
- European Union research and innovation program under the Marie Sklodowska-Curie grant [6655919]
- Spanish Ministry, the CERCA Program of the Generalitat de Catalunya [TIN2016-79717-R]
- CHISTERA project M2CR of the Spanish Ministry, the CERCA Program of the Generalitat de Catalunya [PCIN-2015-251]
- NVIDIA
Recently, image-to-image translation research has witnessed remarkable progress. Although current approaches successfully generate diverse outputs or perform scalable image transfer, these properties have not been combined into a single method. To address this limitation, we propose SDIT: Scalable and Diverse image-to-image translation. These properties are combined into a single generator. The diversity is determined by a latent variable which is randomly sampled from a normal distribution. The scalability is obtained by conditioning the network on the domain attributes. Additionally, we also exploit an attention mechanism that permits the generator to focus on the domain-specific attribute. We empirically demonstrate the performance of the proposed method on face mapping and other datasets beyond faces.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据