Don't measure - appreciate: NPR seen through the prism of art history

P M Hall, Ann-Sophie Lehmann

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Non Photorealistic Rendering is now an established discipline, yet the question of how to evaluate NPR output is often raised. The question is most acute when the NPR algorithms are fully automatic, because then the outputs have no human involvement other than authorship of code. This paper addresses the question “how can we assess the value of automatically produced NPR”. We doubt there is any single objective answer to this important question. We argue that experiments are at best difficult to design, and even the Turing test is of limited value because we are not asking whether a piece has been produced by a human but whether it possesses artistic merit regardless of its source. We conclude by suggesting that to assess progress in NPR, one must adopt an art historical perspective and appreciate it both for itself in its own terms, and its wider cultural context
LanguageEnglish
Title of host publicationImage and Video-Based Artistic Stylisation
EditorsJohn Collomosse, Paul Rosin
Place of PublicationUK
PublisherSpringer
Pages333-351
Number of pages19
Volume42
DOIs
StatusPublished - 2014

Fingerprint

Art History
Authorship
Turing Test
Art
Cultural Context
Rendering
Experiment
Historical Perspective
Artistic Merit

Cite this

Hall, P. M., & Lehmann, A-S. (2014). Don't measure - appreciate: NPR seen through the prism of art history. In J. Collomosse, & P. Rosin (Eds.), Image and Video-Based Artistic Stylisation (Vol. 42, pp. 333-351). UK: Springer. DOI: 10.1007/978-1-4471-4519-6

Don't measure - appreciate : NPR seen through the prism of art history. / Hall, P M; Lehmann, Ann-Sophie.

Image and Video-Based Artistic Stylisation. ed. / John Collomosse; Paul Rosin. Vol. 42 UK : Springer, 2014. p. 333-351.

Research output: Chapter in Book/Report/Conference proceedingChapter

Hall, PM & Lehmann, A-S 2014, Don't measure - appreciate: NPR seen through the prism of art history. in J Collomosse & P Rosin (eds), Image and Video-Based Artistic Stylisation. vol. 42, Springer, UK, pp. 333-351. DOI: 10.1007/978-1-4471-4519-6
Hall PM, Lehmann A-S. Don't measure - appreciate: NPR seen through the prism of art history. In Collomosse J, Rosin P, editors, Image and Video-Based Artistic Stylisation. Vol. 42. UK: Springer. 2014. p. 333-351. Available from, DOI: 10.1007/978-1-4471-4519-6
Hall, P M ; Lehmann, Ann-Sophie. / Don't measure - appreciate : NPR seen through the prism of art history. Image and Video-Based Artistic Stylisation. editor / John Collomosse ; Paul Rosin. Vol. 42 UK : Springer, 2014. pp. 333-351
@inbook{98a1542f595c4eeb8f697fcdaec42d5b,
title = "Don't measure - appreciate: NPR seen through the prism of art history",
abstract = "Non Photorealistic Rendering is now an established discipline, yet the question of how to evaluate NPR output is often raised. The question is most acute when the NPR algorithms are fully automatic, because then the outputs have no human involvement other than authorship of code. This paper addresses the question “how can we assess the value of automatically produced NPR”. We doubt there is any single objective answer to this important question. We argue that experiments are at best difficult to design, and even the Turing test is of limited value because we are not asking whether a piece has been produced by a human but whether it possesses artistic merit regardless of its source. We conclude by suggesting that to assess progress in NPR, one must adopt an art historical perspective and appreciate it both for itself in its own terms, and its wider cultural context",
author = "Hall, {P M} and Ann-Sophie Lehmann",
year = "2014",
doi = "10.1007/978-1-4471-4519-6",
language = "English",
volume = "42",
pages = "333--351",
editor = "John Collomosse and Paul Rosin",
booktitle = "Image and Video-Based Artistic Stylisation",
publisher = "Springer",

}

TY - CHAP

T1 - Don't measure - appreciate

T2 - NPR seen through the prism of art history

AU - Hall,P M

AU - Lehmann,Ann-Sophie

PY - 2014

Y1 - 2014

N2 - Non Photorealistic Rendering is now an established discipline, yet the question of how to evaluate NPR output is often raised. The question is most acute when the NPR algorithms are fully automatic, because then the outputs have no human involvement other than authorship of code. This paper addresses the question “how can we assess the value of automatically produced NPR”. We doubt there is any single objective answer to this important question. We argue that experiments are at best difficult to design, and even the Turing test is of limited value because we are not asking whether a piece has been produced by a human but whether it possesses artistic merit regardless of its source. We conclude by suggesting that to assess progress in NPR, one must adopt an art historical perspective and appreciate it both for itself in its own terms, and its wider cultural context

AB - Non Photorealistic Rendering is now an established discipline, yet the question of how to evaluate NPR output is often raised. The question is most acute when the NPR algorithms are fully automatic, because then the outputs have no human involvement other than authorship of code. This paper addresses the question “how can we assess the value of automatically produced NPR”. We doubt there is any single objective answer to this important question. We argue that experiments are at best difficult to design, and even the Turing test is of limited value because we are not asking whether a piece has been produced by a human but whether it possesses artistic merit regardless of its source. We conclude by suggesting that to assess progress in NPR, one must adopt an art historical perspective and appreciate it both for itself in its own terms, and its wider cultural context

UR - http://dx.doi.org/ 10.1007/978-1-4471-4519-6

U2 - 10.1007/978-1-4471-4519-6

DO - 10.1007/978-1-4471-4519-6

M3 - Chapter

VL - 42

SP - 333

EP - 351

BT - Image and Video-Based Artistic Stylisation

PB - Springer

CY - UK

ER -