Skip to content

InsetGAN for Full-Body Image Generation #361

Description

@joyhuang9473

InsetGAN for Full-Body Image Generation

we propose a novel method to combine multiple pretrained GANs where one GAN generates a global canvas (e.g., human body) and a set of specialized GANs, or insets, focus on different parts (e.g., faces, hands) that can be seamlessly inserted onto the global canvas.

We model the problem as jointly exploring the respective latent spaces such that the generated images can be combined, by inserting the parts from the specialized generators onto the global canvas, without introducing seams.

Metadata

Metadata

Assignees

No one assigned

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions