Learning from Multi-domain Artistic Images for Arbitrary Style Transfer

Simple item page
dc.contributor.authorXu, Zhengen_US
dc.contributor.authorWilber, Michaelen_US
dc.contributor.authorFang, Chenen_US
dc.contributor.authorHertzmann, Aaronen_US
dc.contributor.authorJin, Hailinen_US
dc.contributor.editorKaplan, Craig S. and Forbes, Angus and DiVerdi, Stephenen_US
dc.date.accessioned2019-05-20T09:49:44Z
dc.date.available2019-05-20T09:49:44Z
dc.date.issued2019
dc.description.abstractWe propose a fast feed-forward network for arbitrary style transfer, which can generate stylized image for previously unseen content and style image pairs. Besides the traditional content and style representation based on deep features and statistics for textures, we use adversarial networks to regularize the generation of stylized images. Our adversarial network learns the intrinsic property of image styles from large-scale multi-domain artistic images. The adversarial training is challenging because both the input and output of our generator are diverse multi-domain images.We use a conditional generator that stylized content by shifting the statistics of deep features, and a conditional discriminator based on the coarse category of styles. Moreover, we propose a mask module to spatially decide the stylization level and stabilize adversarial training by avoiding mode collapse. As a side effect, our trained discriminator can be applied to rank and select representative stylized images. We qualitatively and quantitatively evaluate the proposed method, and compare with recent style transfer methods. We release our code and model at https://github.com/nightldj/behance_release.en_US
dc.description.sectionheadersLearned Styles
dc.description.seriesinformationACM/EG Expressive Symposium
dc.identifier.doi10.2312/exp.20191073
dc.identifier.isbn978-3-03868-078-9
dc.identifier.pages21-31
dc.identifier.urihttps://doi.org/10.2312/exp.20191073
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/exp20191073
dc.publisherThe Eurographics Associationen_US
dc.subjectComputing methodologies
dc.subjectImage manipulation
dc.subjectNon
dc.subjectphotorealistic rendering
dc.titleLearning from Multi-domain Artistic Images for Arbitrary Style Transferen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
021-031.pdf
Size:
2.37 MB
Format:
Adobe Portable Document Format
Download
Collections
Expressive 2019