Unpaired Image Translation via Adaptive Convolution-based Normalization

Disentangling content and style information of an image has played an important role in recent success in image translation. In this setting, how to inject given style into an input image containing its own content is an important issue, but existing methods followed relatively simple approaches, le...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Cho, Wonwoong, Kim, Kangyeol, Kim, Eungyeup, Kim, Hyunwoo J, Choo, Jaegul
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 29.11.2019
Subjects
Adaptive filters
Convolution
Representations
Online AccessGet full text

Cover

More Information
Summary:Disentangling content and style information of an image has played an important role in recent success in image translation. In this setting, how to inject given style into an input image containing its own content is an important issue, but existing methods followed relatively simple approaches, leaving room for improvement especially when incorporating significant style changes. In response, we propose an advanced normalization technique based on adaptive convolution (AdaCoN), in order to properly impose style information into the content of an input image. In detail, after locally standardizing the content representation in a channel-wise manner, AdaCoN performs adaptive convolution where the convolution filter weights are dynamically estimated using the encoded style representation. The flexibility of AdaCoN can handle complicated image translation tasks involving significant style changes. Our qualitative and quantitative experiments demonstrate the superiority of our proposed method against various existing approaches that inject the style into the content.
ISSN:2331-8422