Semantic Bottleneck Scene Generation
This addresses the challenge of high-fidelity scene generation for applications like computer vision and graphics, though it is incremental as it builds on existing label-conditional and unconditional methods.
The paper tackles the problem of generating complex scenes without labels by proposing a semantic bottleneck GAN that first synthesizes segmentation layouts and then images, achieving state-of-the-art results in unsupervised image synthesis with improvements in Frechet Inception Distance and user studies.
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. During inference, our model first synthesizes a realistic segmentation layout from scratch, then synthesizes a realistic scene conditioned on that layout. For the former, we use an unconditional progressive segmentation generation network that captures the distribution of realistic semantic scene layouts. For the latter, we use a conditional segmentation-to-image synthesis network that captures the distribution of photo-realistic images conditioned on the semantic layout. 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 user-study evaluations. Moreover, we demonstrate the generated segmentation maps can be used as additional training data to strongly improve recent segmentation-to-image synthesis networks.