Toward Realistic Image Compositing with Adversarial Learning

Abstract

Compositing a realistic image is a challenging task and usually requires considerable human supervision using professional image editing software. In this work we propose a generative adversarial network (GAN) architecture for automatic image compositing. The proposed model consists of four sub-networks: a transformation network that improves the geometric and color consistency of the composite image, a refinement network that polishes the boundary of the composite image, and a pair of discriminator network and a segmentation network for adversarial learning. Experimental results on both synthesized images and real images show that our model, Geometrically and Color Consistent GANs (GCC-GANs), can automatically generate realistic composite images compared to several state-of-the-art methods, and does not require any manual effort.

Cite

Text

Chen and Kae. "Toward Realistic Image Compositing with Adversarial Learning." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019. doi:10.1109/CVPR.2019.00861

Markdown

[Chen and Kae. "Toward Realistic Image Compositing with Adversarial Learning." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019.](https://mlanthology.org/cvpr/2019/chen2019cvpr-realistic/) doi:10.1109/CVPR.2019.00861

BibTeX

@inproceedings{chen2019cvpr-realistic,
  title     = {{Toward Realistic Image Compositing with Adversarial Learning}},
  author    = {Chen, Bor-Chun and Kae, Andrew},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2019},
  doi       = {10.1109/CVPR.2019.00861},
  url       = {https://mlanthology.org/cvpr/2019/chen2019cvpr-realistic/}
}