Adapting and Enhancing Evolutionary Art for Casual Creation

Colton, Simon; McCormack, Jon; Berns, Sebastian; Petrovskaya, Elena; Cook, Michael

doi:10.1007/978-3-030-43859-3_2

Cited by 5 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The rise of generative AI systems have moreover sparked debate about the nature of creativity itself, some argue that AI-generated art lacks the depth of human emotion and lived experience [47], while others contend that creativity is not solely reserved to human actors [12]. The emergence of AI-generated artworks that evoke strong emotional responses challenges the notion that creativity is an exclusively human domain.…”

Section: Background and Related Work 21 Ai And Creativitymentioning

confidence: 99%

Practice-based research at SensiLab

McCormack¹,

Ilsar²,

Chandler³

et al. 2021

The Routledge International Handbook of Practice-Based Research

Self Cite

View full text Add to dashboard Cite

Recent developments in prompt-based generative AI has given rise to discourse surrounding the perceived ethical concerns, economic implications, and consequences for the future of cultural production. As generative imagery becomes pervasive in mainstream society, dominated primarily by emerging industry leaders, we encourage that the role of the CHI community be one of inquiry; to investigate the numerous ways in which generative AI has the potential to, and already is, augmenting human creativity. In this paper, we conducted a diffractive analysis exploring the potential role of prompt-based interfaces in artists' creative practice. Over a two week period, seven visual artists were given access to a personalised instance of Stable Diffusion, fine-tuned on a dataset of their work. In the following diffractive analysis, we identified two

show abstract

Section: Background and Related Work 21 Ai And Creativitymentioning

confidence: 99%

Practice-based research at SensiLab

McCormack¹,

Ilsar²,

Chandler³

et al. 2021

The Routledge International Handbook of Practice-Based Research

Self Cite

View full text Add to dashboard Cite

show abstract

“…Work by Colton et al [9] experimented with a number of image classification networks (ResNet, MobileNet and SqueezeNet) to drive an evolutionary art system for causal creation towards categories that were classified with high confidence by the network. As these classification networks were trained on the ImageNet database of real images [11], the abstract images generated by this system required active and considered viewing to find the connection between their visual appearance and the neural network's classification.…”

Section: Related Workmentioning

confidence: 99%

Deep learning of individual aesthetics

McCormack

Lomas

2020

Neural Comput & Applic

Self Cite

View full text Add to dashboard Cite

Accurate evaluation of human aesthetic preferences represents a major challenge for creative evolutionary and generative systems research. Prior work has tended to focus on feature measures of the artefact, such as symmetry, complexity and coherence. However, research models from Psychology suggest that human aesthetic experiences encapsulate factors beyond the artefact, making accurate computational models very difficult to design. The interactive genetic algorithm (IGA) circumvents the problem through human-in-the-loop, subjective evaluation of aesthetics, but is limited due to user fatigue and small population sizes. In this paper we look at how recent advances in deep learning can assist in automating personal aesthetic judgement. Using a leading artist's computer art dataset, we investigate the relationship between image measures, such as complexity, and human aesthetic evaluation. We use dimension reduction methods to visualise both genotype and phenotype space in order to support the exploration of new territory in a generative system. Convolutional Neural Networks trained on the artist's prior aesthetic evaluations are used to suggest new possibilities similar or between known high quality genotype-phenotype mappings. We integrate this classification and discovery system into a software tool for evolving complex generative art and design.

show abstract

Evolving Neural Style Transfer Blends

Colton

2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Adapting and Enhancing Evolutionary Art for Casual Creation

Cited by 5 publications

References 16 publications

Practice-based research at SensiLab

Practice-based research at SensiLab

Deep learning of individual aesthetics

Evolving Neural Style Transfer Blends

Contact Info

Product

Resources

About