Unconditional Synthesis of Complex Scenes Using a Semantic Bottleneck
Coupling the high-fidelity generation capabilities of label-conditional image synthesis methods with the flexibility of unconditional generative models, we propose a semantic bottleneck GAN model for unconditional synthesis of complex scenes. We assume pixel-wise segmentation labels are available during training and use them to learn the scene structure through an unconditional progressive segmentation generation network. During inference, our model first synthesizes a realistic segmentation layout from scratch, then synthesizes a realistic scene conditioned on that layout through a conditional segmentation-to-image synthesis network. When trained end-to-end, the resulting model outperforms state-of-the-art generative models in unsupervised image synthesis on two challenging domains in terms of the Frechet Inception Distance and perceptual evaluations. Moreover, we demonstrate that the end-to-end training significantly improves the segmentation-to-image synthesis sub-network, which results in superior performance over the state-of-the-art when conditioning on real segmentation layouts.
PDF Abstract
Cityscapes
