Example-guided image synthesis aims to synthesize an image from a semantic label map and an exemplary image indicating style. We use the term "style" in this problem to refer to implicit characteristics of images, for example: in portraits "style" includes gender, racial identity, age, hairstyle; in full body pictures it includes clothing; in street scenes, it refers to weather and time of day and such like. A semantic label map in these cases indicates facial expression, full body pose, or scene segmentation. We propose a solution to the example-guided image synthesis problem using conditional generative adversarial networks with style consistency. Our key contributions are (i) a novel style consistency discriminator to determine whether a pair of images are consistent in style; (ii) an adaptive semantic consistency loss; and (iii) a training data sampling strategy, for synthesizing style-consistent results to the exemplar.
@article{arxiv.1906.01314,
title = {Example-Guided Style Consistent Image Synthesis from Semantic Labeling},
author = {Miao Wang and Guo-Ye Yang and Ruilong Li and Run-Ze Liang and Song-Hai Zhang and Peter. M. Hall and Shi-Min Hu},
journal= {arXiv preprint arXiv:1906.01314},
year = {2019}
}
Comments
CVPR 2019 - Code and data - https://github.com/cxjyxxme/pix2pixSC