Ioannou, E. and Maddock, S. orcid.org/0000-0003-3179-0263 (2022) Depth-aware neural style transfer using instance normalization. In: Turner, M. and Vangorp, P., (eds.) Computer Graphics & Visual Computing (CGVC) 2022. Computer Graphics & Visual Computing (CGVC) 2022, 15-16 Sep 2022, Virtual conference. Eurographics Digital Library
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.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Editors: |
|
Copyright, Publisher and Additional Information: | © 2022 The Author(s). Eurographics Proceedings © 2022 The Eurographics Association. Uploaded in accordance with the publisher's self-archiving policy. |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 31 Aug 2022 07:45 |
Last Modified: | 15 Sep 2022 00:15 |
Published Version: | https://diglib.eg.org/handle/10.2312/2633209 |
Status: | Published |
Publisher: | Eurographics Digital Library |
Refereed: | Yes |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:190004 |