Compositing Foreground and Background Using Variational Autoencoders.

We consider the problem of composing images by combining an arbitrary foreground object to some background. To achieve this we use a factorized latent space. Thus we introduce a model called the “Background and Foreground VAE” (BFVAE) that can combine arbitrary foreground and background from an image dataset to generate unseen images. To enhance the quality of the generated images we also propose a VAE-GAN mixed model called “Latent Space Renderer-GAN” (LSR-GAN). This substantially reduces the blurriness of BFVAE images.