ML Anthology

Semi-Parametric Image Synthesis

Xiaojuan Qi, Qifeng Chen, Jiaya Jia, Vladlen Koltun
CVPR 2018
doi:10.1109/CVPR.2018.00918 /cvpr/2018/qi2018cvpr-semiparametric/

Abstract

We present a semi-parametric approach to photographic image synthesis from semantic layouts. The approach combines the complementary strengths of parametric and nonparametric techniques. The nonparametric component is a memory bank of image segments constructed from a training set of images. Given a novel semantic layout at test time, the memory bank is used to retrieve photographic references that are provided as source material to a deep network. The synthesis is performed by a deep network that draws on the provided photographic material. Experiments on multiple semantic segmentation datasets show that the presented approach yields considerably more realistic images than recent purely parametric techniques.

PDF CVPR Semantic Scholar

Cite

Text

Qi et al. "Semi-Parametric Image Synthesis." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018. doi:10.1109/CVPR.2018.00918

Markdown

[Qi et al. "Semi-Parametric Image Synthesis." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018.](https://mlanthology.org/cvpr/2018/qi2018cvpr-semiparametric/) doi:10.1109/CVPR.2018.00918

BibTeX

@inproceedings{qi2018cvpr-semiparametric,
  title     = {{Semi-Parametric Image Synthesis}},
  author    = {Qi, Xiaojuan and Chen, Qifeng and Jia, Jiaya and Koltun, Vladlen},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2018},
  doi       = {10.1109/CVPR.2018.00918},
  url       = {https://mlanthology.org/cvpr/2018/qi2018cvpr-semiparametric/}
}