SOTAVerified

Semantic Image Synthesis with Spatially-Adaptive Normalization

2019-03-18CVPR 2019Code Available1· sign in to hype

Taesung Park, Ming-Yu Liu, Ting-Chun Wang, Jun-Yan Zhu

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

We propose spatially-adaptive normalization, a simple but effective layer for synthesizing photorealistic images given an input semantic layout. Previous methods directly feed the semantic layout as input to the deep network, which is then processed through stacks of convolution, normalization, and nonlinearity layers. We show that this is suboptimal as the normalization layers tend to ``wash away'' semantic information. To address the issue, we propose using the input layout for modulating the activations in normalization layers through a spatially-adaptive, learned transformation. Experiments on several challenging datasets demonstrate the advantage of the proposed method over existing approaches, regarding both visual fidelity and alignment with input layouts. Finally, our model allows user control over both semantic and style. Code is available at https://github.com/NVlabs/SPADE .

Tasks

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
ADE20K Labels-to-PhotosSPADEmIoU38.5Unverified
ADE20K-Outdoor Labels-to-PhotosSPADEmIoU30.8Unverified
Cityscapes Labels-to-PhotoSPADEmIoU62.3Unverified
COCO-Stuff Labels-to-PhotosSPADEFID22.6Unverified

Reproductions