Depth-aware Neural Style Transfer using Instance Normalization

Ioannou, Eleftherios; Maddock, Steve

Depth-aware Neural Style Transfer using Instance Normalization

Files

001-008.pdf (15.82 MB)

Date

2022

Authors

Ioannou, Eleftherios
Maddock, Steve

Publisher

The Eurographics Association

Abstract

Neural Style Transfer (NST) is concerned with the artistic stylization of visual media. It can be described as the process of transferring the style of an artistic image onto an ordinary photograph. Recently, a number of studies have considered the enhancement of the depth-preserving capabilities of the NST algorithms to address the undesired effects that occur when the input content images include numerous objects at various depths. Our approach uses a deep residual convolutional network with instance normalization layers that utilizes an advanced depth prediction network to integrate depth preservation as an additional loss function to content and style. We demonstrate results that are effective in retaining the depth and global structure of content images. Three different evaluation processes show that our system is capable of preserving the structure of the stylized results while exhibiting style-capture capabilities and aesthetic qualities comparable or superior to state-of-the-art methods. Project page: https://ioannoue.github.io/depth-aware-nst-using-in.html.

CCS Concepts: Computing methodologies → Image processing; Image representations; Applied computing → Fine arts; Media arts

        @inproceedings{10.2312:cgvc.20221165
,
booktitle = {Computer Graphics and Visual Computing (CGVC)
},
editor = {Peter Vangorp and 
Martin J. Turner
},
title = {{Depth-aware Neural Style Transfer using Instance Normalization
}},
author = {Ioannou, Eleftherios and 
Maddock, Steve
},
year = {2022
},
publisher = {The Eurographics Association
},
ISBN = {978-3-03868-188-5
},
DOI = {10.2312/cgvc.20221165
}
}