Generating Furry Cars: Disentangling Object Shape and Appearance across Multiple Domains

Utkarsh Ojha; Krishna Kumar Singh; Yong Jae Lee

ICLR2021顶会

Generating Furry Cars: Disentangling Object Shape and Appearance across Multiple Domains

Utkarsh Ojha, Krishna Kumar Singh, Yong Jae Lee

arXiv 出版方

2021年份

2被引次数

1顶会引用

摘要

utkarshojha.github.io/inter-domain-gan/ Figure 1: Each block above follows [Appearance, Shape → Output]. We propose a generative model that disentangles and combines shape and appearance factors across multiple domains, to create hybrid images which do not exist in any single domain.