FBC-GAN: Diverse and Flexible Image Synthesis via Foreground-Background Composition

TL;DR

FBC-GAN introduces a novel image synthesis approach that independently generates foregrounds and backgrounds, enabling higher diversity and flexibility in generated images while maintaining visual realism.

Contribution

The paper proposes FBC-GAN, a new GAN architecture that explicitly models foreground and background separately for more diverse and flexible image synthesis.

Findings

Achieves higher diversity in generated images.

Maintains competitive visual realism.

Allows flexible composition of foregrounds and backgrounds.

Abstract

Generative Adversarial Networks (GANs) have become the de-facto standard in image synthesis. However, without considering the foreground-background decomposition, existing GANs tend to capture excessive content correlation between foreground and background, thus constraining the diversity in image generation. This paper presents a novel Foreground-Background Composition GAN (FBC-GAN) that performs image generation by generating foreground objects and background scenes concurrently and independently, followed by composing them with style and geometrical consistency. With this explicit design, FBC-GAN can generate images with foregrounds and backgrounds that are mutually independent in contents, thus lifting the undesirably learned content correlation constraint and achieving superior diversity. It also provides excellent flexibility by allowing the same foreground object with different background scenes, the same background scene with varying foreground objects, or the same foreground object and background scene with different object positions, sizes and poses. It can compose foreground objects and background scenes sampled from different datasets as well. Extensive experiments over multiple datasets show that FBC-GAN achieves competitive visual realism and superior diversity as compared with state-of-the-art methods.