Neural Style Transfer: A Paradigm Shift for Image-based Artistic Rendering?

Simple item page
dc.contributor.authorSemmo, Amiren_US
dc.contributor.authorIsenberg, Tobiasen_US
dc.contributor.authorDöllner, Jürgenen_US
dc.contributor.editorHolger Winnemoeller and Lyn Bartramen_US
dc.date.accessioned2017-10-18T08:42:17Z
dc.date.available2017-10-18T08:42:17Z
dc.date.issued2017
dc.description.abstractIn this meta paper we discussimage-based artistic rendering (IB-AR)based onneural style transfer(NST) and argue, while NST may represent a paradigm shift for IB-AR, that it also has to evolve as an interactive tool that considers the design aspects and mecha- nisms of artwork production. IB-AR received signifficant attention in the past decades for visual communication, covering a plethora of techniques to mimic the appeal of artistic media. Example-based renderingrepresents one the most promising paradigms in IB-AR to (semi-)automatically simulate artistic media with high fidelity, but so far has been limited because it relies on pre-defined image pairs for training or informs only low-level image features for texture transfers. Advancements in deep learning showed to alleviate these limitations by matching content and style statistics via activations of neural network layers, thus making a generalized style trans- fer practicable. We categorize style transfers within the taxonomy of IB-AR, then propose a semiotic structure to derive a technical research agenda for NSTs with respect to the grand challenges of NPAR. We finally discuss the potentials of NSTs, thereby identifying applications such as casual creativity and art production.en_US
dc.description.sectionheadersStyle Transfer
dc.description.seriesinformationNon-Photorealistic Animation and Rendering
dc.identifier.doi10.1145/3092919.3092920
dc.identifier.isbn978-1-4503-5081-5
dc.identifier.issn-
dc.identifier.urihttps://doi.org/10.1145/3092919.3092920
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/npar2017a05
dc.publisherAssociation for Computing Machinery, Inc (ACM)en_US
dc.subjectComputing methodologies
dc.subjectNon photorealistic rendering
dc.subjectImage processing
dc.subjectstyle transfer
dc.subjectstylization
dc.subjectconvolutional neural networks
dc.subjectimage
dc.subjectbased artistic rendering
dc.subjectimage processing
dc.subjectsemiotics
dc.titleNeural Style Transfer: A Paradigm Shift for Image-based Artistic Rendering?en_US
Files
Collections
NPAR2017