Learning from Multi-domain Artistic Images for Arbitrary Style Transfer (Unknown language)

In: ACM/EG Expressive Symposium   ;  21-31  ;  2019

How to get this document?

Download
Commercial Copyright fee: €14.50 Basic fee: €4.00 Total price: €18.50
Academic Copyright fee: €4.50 Basic fee: €2.00 Total price: €6.50

We 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.

Table of contents conference proceedings

The tables of contents are generated automatically and are based on the data records of the individual contributions available in the index of the TIB portal. The display of the Tables of Contents may therefore be incomplete.

1
Non-Photorealistic Animation for Immersive Storytelling
Curtis, Cassidy J. / Dart, Kevin / Latzko, Theresa / Kahrs, John | 2019
11
Video Motion Stylization by 2D Rigidification
Delanoy, Johanna / Bousseau, Adrien / Hertzmann, Aaron | 2019
21
Learning from Multi-domain Artistic Images for Arbitrary Style Transfer
Xu, Zheng / Wilber, Michael / Fang, Chen / Hertzmann, Aaron / Jin, Hailin | 2019
33
Real-Time Patch-Based Stylization of Portraits Using Generative Adversarial Network
Futschik, David / Chai, Menglei / Cao, Chen / Ma, Chongyang / Stoliar, Aleksei / Korolev, Sergey / Tulyakov, Sergey / Kučera, Michal / Sýkora, Daniel | 2019
43
Enhancing Neural Style Transfer using Patch-Based Synthesis
Texler, Ondřej / Fišer, Jakub / Lukáč, Mike / Lu, Jingwan / Shechtman, Eli / Sýkora, Daniel | 2019
51
Sketching and Layering Graffiti Primitives
Berio, Daniel / Asente, Paul / Echevarria, Jose / Leymarie, Frederic Fol | 2019
61
Single Stroke Aerial Robot Light Painting
Ren, Kejia / Kry, Paul G. | 2019
69
Generating Playful Palettes from Images
DiVerdi, Stephen / Lu, Jingwan / Echevarria, Jose / Shugrina, Maria | 2019
79
Aesthetically-Oriented Atmospheric Scattering
Shen, Yang / Mallett, Ian / Shkurko, Konstantin | 2019
87
Abstract Shape Synthesis From Linear Combinations of Clelia Curves
Putnam, Lance / Todd, Stephen / Latham, William | 2019
101
Aesthetics of Curvature Bases for Sketches
Lippincott, Keith / Hatton, Ross L. / Grimm, Cindy | 2019
111
Defining Hatching in Art
Philbrick, Greg / Kaplan, Craig S. | 2019
123
Stipple Removal in Extreme-tone Regions
Azami, Rosa / Doyle, Lars / Mould, David | 2019
133
Irregular Pebble Mosaics with Sub-Pebble Detail
Javid, Ali Sattari / Doyle, Lars / Mould, David | 2019
Feedback