ML Anthology

Semantic Image Synthesis with Spatially-Adaptive Normalization

Taesung Park, Ming-Yu Liu, Ting-Chun Wang, Jun-Yan Zhu
CVPR 2019
doi:10.1109/CVPR.2019.00244 /cvpr/2019/park2019cvpr-semantic/

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 network, forcing the network to memorize the information throughout all the layers. Instead, we propose using the input layout for modulating the activations in normalization layers through a spatially-adaptive, learned affine transformation. Experiments on several challenging datasets demonstrate the superiority of our method compared to existing approaches, regarding both visual fidelity and alignment with input layouts. Finally, our model allows users to easily control the style and content of image synthesis results as well as create multi-modal results. Code is available upon publication.

PDF CVPR Semantic Scholar

Cite

Text

Park et al. "Semantic Image Synthesis with Spatially-Adaptive Normalization." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019. doi:10.1109/CVPR.2019.00244

Markdown

[Park et al. "Semantic Image Synthesis with Spatially-Adaptive Normalization." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019.](https://mlanthology.org/cvpr/2019/park2019cvpr-semantic/) doi:10.1109/CVPR.2019.00244

BibTeX

@inproceedings{park2019cvpr-semantic,
  title     = {{Semantic Image Synthesis with Spatially-Adaptive Normalization}},
  author    = {Park, Taesung and Liu, Ming-Yu and Wang, Ting-Chun and Zhu, Jun-Yan},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2019},
  doi       = {10.1109/CVPR.2019.00244},
  url       = {https://mlanthology.org/cvpr/2019/park2019cvpr-semantic/}
}