Example-Guided Style-Consistent Image Synthesis from Semantic Labeling

Peter Hall, Miao Wang, Ruilong Li, Run-Ze Liang, Song-Hai Zhang, Shi-Min Hi

Research output: Chapter or section in a book/report/conference proceedingChapter in a published conference proceeding

67 Citations (SciVal)
32 Downloads (Pure)


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 expres- sion, full body pose, or scene segmentation. We propose a solution to the example-guided image synthesis problem us- ing conditional generative adversarial networks with style consistency. Our key contributions are (i) a novel style consistency discriminator to determine whether a pair of im- ages are consistent in style; (ii) an adaptive semantic con- sistency loss; and (iii) a training data sampling strategy, for synthesizing style-consistent results to the exemplar. We demonstrate the efficiency of our method on face, dance and street view synthesis tasks.
Original languageEnglish
Title of host publicationComputer Vision and Pattern Recognition, CVPR 2019
Number of pages10
ISBN (Electronic)9781728132938
ISBN (Print)9781728132945
Publication statusPublished - 9 Jan 2020
Event2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) - Long Beach, USA United States
Duration: 16 Jun 201920 Jun 2019

Publication series

Name2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
ISSN (Print)1063-6919
ISSN (Electronic)2575-7075


Conference2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Country/TerritoryUSA United States
CityLong Beach


Dive into the research topics of 'Example-Guided Style-Consistent Image Synthesis from Semantic Labeling'. Together they form a unique fingerprint.

Cite this