SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis

Wengling Chen, James Hays; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 9416-9425

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.

Related Material


[pdf] [Supp] [arXiv]
[bibtex]
@InProceedings{Chen_2018_CVPR,
author = {Chen, Wengling and Hays, James},
title = {SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}
}