Sym-parameterized Dynamic Inference for Mixed-Domain Image Translation
Abstract
Recent advances in image-to-image translation have led to some ways to generate multiple domain images through a single network. However, there is still a limit in creating an image of a target domain without a dataset on it. We propose a method that expands the concept of `multi-domain' from data to the loss area and learns the combined characteristics of each domain to dynamically infer translations of images in mixed domains. First, we introduce Sym-parameter and its learning method for variously mixed losses while synchronizing them with input conditions. Then, we propose Sym-parameterized Generative Network (SGN) which is empirically confirmed of learning mixed characteristics of various data and losses, and translating images to any mixed-domain without ground truths, such as 30% Van Gogh and 20% Monet and 40% snowy.
Cite
@article{arxiv.1811.12362,
title = {Sym-parameterized Dynamic Inference for Mixed-Domain Image Translation},
author = {Simyung Chang and SeongUk Park and John Yang and Nojun Kwak},
journal= {arXiv preprint arXiv:1811.12362},
year = {2019}
}
Comments
16pages, This paper is accepted at ICCV 2019