image

Unconditional Synthesis of Complex Scenes Using a Semantic Bottleneck

Publication Date:

Abstract

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... (read more)

Authors

Topics

https://openreview.net/pdf?id=3YdNZD5dMxI

0001-01-01 -