Semantic Bottleneck Scene Generation

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... (read more)

PDF Abstract

Datasets


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Image Generation ADE-Indoor SB-GAN FID 85.27 # 1
Image-to-Image Translation ADE-Indoor Labels-to-Photo SB-GAN FID 48.15 # 1
Image Generation Cityscapes-25K 256x512 SB-GAN FID 62.97 # 1
Image Generation Cityscapes-5K 256x512 SB-GAN FID 65.49 # 1
Image-to-Image Translation Cityscapes Labels-to-Photo SB-GAN FID 60.39 # 7

Methods used in the Paper


METHOD TYPE
Convolution
Convolutions
GAN
Generative Models