Zero-Pair Image To Image Translation Using Domain Conditional Normalization
2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION WACV 2021(2021)
摘要
In this paper, we propose an approach based on domain conditional normalization (DCN) for zero-pair image-to-image translation, i.e., translating between two domains which have no paired training data available but each have paired training data with a third domain. We employ a single generator which has an encoder-decoder structure and analyze different implementations of domain conditional normalization to obtain the desired target domain output. The validation benchmark uses RGB-depth pairs and RGB-semantic pairs for training and compares performance for the depth-semantic translation task. The proposed approaches improve in qualitative and quantitative terms over the compared methods, while using much fewer parameters. Code available at: https://github.com/samarthshukla/dcn
更多查看译文
关键词
paired training data,domain conditional normalization,RGB-depth pairs,RGB-semantic pairs,depth-semantic translation task,zero-pair image-to-image translation,target domain output,DCN,single generator,encoder-decoder structure
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络