Stroke Based Painterly Rendering

Vanderhaeghe, David; Collomosse, John

doi:10.1007/978-1-4471-4519-6_1

Cited by 5 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These are systems that take a photograph as input, and output an image that simulates the same image as generated by a particular artistic technique. Some of these systems are based on a searchbased technique (Vanderhaeghe and Collomosse, 2012), though they apply this to the overall image, rather than to detailed mark making. In music, this might be seen in systems such as that described by Ramirez et al (2006), which take a piece of music at attempt to adjust the details of timing, volume, etc.…”

Section: Skill and Expertisementioning

confidence: 99%

Aesthetics, Artificial Intelligence, and Search-Based Art

Johnson

2021

Artificial Intelligence and the Arts

View full text Add to dashboard Cite

Why do people exhibit particular behaviour towards a class of objects called artworks? That is the topic of study in aesthetics. This paper explores how various theories of aesthetics can be interpreted in the context of artworks generated by artificial intelligence systems, in particular those that are grounded in the idea of search as a means of implementing intelligence computationally. A number of aesthetic theories are explored, including ideas of imitation, skill, form, expression, imagination, and focus. The paper concludes by highlighting a number of areas that, in light of these considerations, have been neglected by the makers of computer art systems and which provide future opportunities in this area.

show abstract

Section: Skill and Expertisementioning

confidence: 99%

Aesthetics, Artificial Intelligence, and Search-Based Art

Johnson

2021

Artificial Intelligence and the Arts

View full text Add to dashboard Cite

show abstract

“…Stroke-based rendering (SBR) is another approach to mimicking artistic paintings. The paper [21] defines SBR as a process of generating a digital artwork using special rendering marks , for example, hatches, brushstrokes, or other primitives. For convenience, we will further consider only brushstrokes as rendering marks.…”

Section: Introductionmentioning

confidence: 99%

“…For convenience, we will further consider only brushstrokes as rendering marks. Such algorithms do not necessarily require machine learning and sometimes can synthesize brushstrokes using simple heuristics, for example, determine brushstrokes randomly, or apply them in accordance with image edges or image gradient, or using any other local image features [21][22][23]. This determined the relative popularity of such algorithms before the mid-2010s when the machine learning boom had begun.…”

Section: Introductionmentioning

confidence: 99%

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

Karimov,

Kopets,

Shpilevaya

et al. 2023

Mathematics

View full text Add to dashboard Cite

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.

show abstract