Comparing Neural Style Transfer and Gradient-Based Algorithms in Brushstroke Rendering Tasks

Non-photorealistic rendering (NPR) with explicit brushstroke representation is essential for both high-grade imitating of artistic paintings and generating commands for artistically skilled robots. Some algorithms for this purpose have been recently developed based on simple heuristics, e.g., using...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Mathematics (Basel) Ročník 11; číslo 10; s. 2255
Hlavní autoři: Karimov, Artur, Kopets, Ekaterina, Shpilevaya, Tatiana, Katser, Evgenii, Leonov, Sergey, Butusov, Denis
Médium: Journal Article
Jazyk:angličtina
Vydáno: Basel MDPI AG 01.05.2023
Témata:
Algorithms
Analysis
Artists
brushstroke rendering
Correlation analysis
Heuristic
Heuristic methods
Histograms
Machine learning
Methods
Neural networks
neural style transfer
non-photorealistic rendering
oil paintings
Orientation
Parameters
postimpressionism
Public radio
Questions
realism
Rendering
Robots
ISSN:2227-7390, 2227-7390
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Non-photorealistic rendering (NPR) with explicit brushstroke representation is essential for both high-grade imitating of artistic paintings and generating commands for artistically skilled robots. Some algorithms for this purpose have been recently developed based on simple heuristics, e.g., using an image gradient for driving brushstroke orientation. The notable drawback of such algorithms is the impossibility of automatic learning to reproduce an individual artist’s style. In contrast, popular neural style transfer (NST) algorithms are aimed at this goal by their design. The question arises: how good is the performance of neural style transfer methods in comparison with the heuristic approaches? To answer this question, we develop a novel method for experimentally quantifying brushstroke rendering algorithms. This method is based on correlation analysis applied to histograms of six brushstroke parameters: length, orientation, straightness, number of neighboring brushstrokes (NBS-NB), number of brushstrokes with similar orientations in the neighborhood (NBS-SO), and orientation standard deviation in the neighborhood (OSD-NB). This method numerically captures similarities and differences in the distributions of brushstroke parameters and allows comparison of two NPR algorithms. We perform an investigation of the brushstrokes generated by the heuristic algorithm and the NST algorithm. The results imply that while the neural style transfer and the heuristic algorithms give rather different parameter histograms, their capabilities of mimicking individual artistic manner are limited comparably. A direct comparison of NBS-NB histograms of brushstrokes generated by these algorithms and of brushstrokes extracted from a real painting confirms this finding.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2227-7390
2227-7390
DOI:10.3390/math11102255