/ Machine Learning

High-Resolution Image Synthesis from Salient Object Layout

High-Resolution Image Synthesis from Salient Object Layout

BachGAN

BachGAN: High-Resolution Image Synthesis from Salient Object Layout
Yandong Li, Yu Cheng, Zhe Gan, Licheng Yu, Liqiang Wang, and Jingjing Liu
In CVPR 2020.

Qualitive Results

Examples of image synthesis results from different models on the Cityscapes dataset

example_1

Examples of image synthesis results from different models on the ADE20K dataset

example_2

Examples of generated images by adding bounding boxes sequentially on Cityscapes.

seq_city

Examples of generated images by adding bounding boxes sequentially on ADE20K.

seq_ade20k

Usage

  • Code and scripts will be released soon.

Citation

If you use this code for your research, please cite our papers.

@inproceedings{li2020BachGAN,
  title={BachGAN: High-Resolution Image Synthesis from Salient Object Layout},
  author={Li, Yandong and Cheng, Yu and Gan, Zhe and Yu, Licheng and Wang, Liqiang and Liu, Jingjing},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  year={2020}
}

Acknowledgments

Pytorh-fid is from @mseitzer's implementation.

This code borrows heavily from pix2pixHD and SPADE. We thank Jiayuan Mao for his Synchronized Batch Normalization code.

GitHub

Comments