arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1806.10050cs.CV
收藏

基于中心偏置归一化的多映射图像间平移

Multi-Mapping Image-to-Image Translation with Central Biasing Normalization

Peking University(北京大学);Tencent(腾讯)

Xiaoming Yu, Zhenqiang Ying, Thomas Li, Shan Liu, Ge Li

摘要:

图像到图像翻译的最新进展已经看到了通过单个网络生成不同图像的方法的兴起。为了指示一对多映射的目标域,将潜在代码注入生成器网络。然而,我们发现,注入方法会导致模式坍塌,因为归一化策略。现有的规范化策略可能会导致特征分布的不一致性或消除潜在代码的影响。为了解决这些问题,我们提出了多样性内一致性准则来设计多映射模型。基于该准则,我们提出了中心偏置归一化来注入潜在代码信息。实验表明,我们的方法可以提高现有图像到图像翻译模型的质量和多样性,如StarGAN,BicycleGAN和pix2pix。

英文摘要:

Recent advances in image-to-image translation have seen a rise in approaches generating diverse images through a single network. To indicate the target domain for a one-to-many mapping, the latent code is injected into the generator network. However, we found that the injection method leads to mode collapse because of normalization strategies. Existing normalization strategies might either cause the inconsistency of feature distribution or eliminate the effect of the latent code. To solve these problems, we propose the consistency within diversity criteria for designing the multi-mapping model. Based on the criteria, we propose central biasing normalization to inject the latent code information. Experiments show that our method can improve the quality and diversity of existing image-to-image translation models, such as StarGAN, BicycleGAN, and pix2pix.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑