SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis
Abstract
Synthesizing realistic images from human drawn sketches is a challenging problem in computer graphics and vision. Existing approaches either need exact edge maps, or rely on retrieval of existing photographs. In this work, we propose a novel Generative Adversarial Network (GAN) approach that synthesizes plausible images from 50 categories including motorcycles, horses and couches. We demonstrate a data augmentation technique for sketches which is fully automatic, and we show that the augmented data is helpful to our task. We introduce a new network building block suitable for both the generator and discriminator which improves the information flow by injecting the input image at multiple scales. Compared to state-of-the-art image translation methods, our approach generates more realistic images and achieves significantly higher Inception Scores.
Cite
Text
Chen and Hays. "SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018. doi:10.1109/CVPR.2018.00981Markdown
[Chen and Hays. "SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018.](https://mlanthology.org/cvpr/2018/chen2018cvpr-sketchygan/) doi:10.1109/CVPR.2018.00981BibTeX
@inproceedings{chen2018cvpr-sketchygan,
title = {{SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis}},
author = {Chen, Wengling and Hays, James},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2018},
doi = {10.1109/CVPR.2018.00981},
url = {https://mlanthology.org/cvpr/2018/chen2018cvpr-sketchygan/}
}