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

Abstract : In this meta paper we discuss image-based artistic rendering (IB-AR) based on neural 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 mechanisms of artwork production. IB-AR received significant attention in the past decades for visual communication, covering a plethora of techniques to mimic the appeal of artistic media. Example-based rendering (EBR) represents 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. Recent advancements in deep convolutional neural networks showed to alleviate these limitations by separating image contents from style, thus making a generalized style transfer 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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [100 references]  Display  Hide  Download

https://hal.inria.fr/hal-01527495
Contributor : Isenberg Tobias <>
Submitted on : Wednesday, June 7, 2017 - 3:12:13 PM
Last modification on : Thursday, November 30, 2017 - 9:44:54 AM
Long-term archiving on : Friday, September 8, 2017 - 1:03:46 PM

File

exp-meta2017_authors_version2_...
Files produced by the author(s)

Licence


Copyright

Identifiers

Collections

Citation

Amir Semmo, Tobias Isenberg, Jürgen Döllner. Neural Style Transfer: A Paradigm Shift for Image-based Artistic Rendering?. NPAR 2017 - Proceedings of the International Symposium on Non-Photorealistic Animation and Rendering (NPAR as part of Expressive), ACM, Jul 2017, Los Angleles, United States. pp.5:1-5:13, ⟨10.1145/3092919.3092920⟩. ⟨hal-01527495v3⟩

Share

Metrics

Record views

522

Files downloads

981