Deep learning of individual aesthetics

  title={Deep learning of individual aesthetics},
  author={Jon Mccormack and Andy Lomas},
  journal={Neural Computing and Applications},
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 circumvents the problem… 
Quality-diversity for aesthetic evolution
This paper performs a random sampling of genotype space and uses individual artist-assigned evaluations of aesthetic quality to formulate a computable fitness measure specific to the artist and this system, and shows that the quality-diversity search is able to find multiple phenotypes of high aesthetic value.
A Survey of Hand Crafted and Deep Learning Methods for Image Aesthetic Assessment
A large number of traditional hand crafted and deep learning based approaches are reviewed and why some features or models perform better than others and what are the limitations are discussed.
Interpretable Aesthetic Analysis Model for Intelligent Photography Guidance Systems
This work uses a hyper-network to learn the overall aesthetic rating as a combination of individual aesthetic attribute scores, and introduces a specially designed attentional mechanism in attribute score estimators to enable the users to know exactly which parts/elements of visual inputs lead to the estimated score.
A Compositional Exploration of Computational Aesthetic Evaluation and AI Bias.
A subversive compositional approach to machine learning, focused on the exploration of AI bias and computational aesthetic evaluation, is described with respect to the objective of balancing the trade-off between musical authorship and interpretative freedom in interactive musical works.
A Survey on Image Aesthetic Assessment
Automatic image aesthetics assessment is a computer vision problem dealing with categorizing images into different aesthetic levels. The categorization is usually done by analyzing an input image and
Complexity and Aesthetics in Generative and Evolutionary Art
The value of direct measures in generative and evolutionary art is discussed, reinforcing recent findings from neuroimaging and psychology which suggest human aesthetic judgement is informed by many extrinsic factors beyond the measurable properties of the object being judged.
Validation of an Aesthetic Assessment System for Commercial Tasks
A statistical analysis prove that there is a significant difference in the number of clicks after selecting the images with the AI system, in the experiment with Real Estate portals.
Opleiding Informatica Automating the process of defining the aesthetic quality of an image in a numerical way
The goal of this research is to automate the process of determining the aesthetic quality of an image numerically. Subsequently, this numerical value will be used in an unsupervised evolutionary
The Enigma of Complexity
The value of direct measures in generative and evolutionary art is discussed, reinforcing recent findings from neuroimaging and psychology which suggest human aesthetic judgement is informed by many extrinsic factors beyond the measurable properties of the object being judged.
Growing and Evolving 3-D Prints
This article describes a biologically inspired developmental model as the basis of a generative form-finding system and finds that by evolving first for aesthetic complexity, then evolving for structural consistency until the form is “just printable,” gives the best results.


Understanding Aesthetics and Fitness Measures in Evolutionary Art Systems
The recent research on fitness for evolutionary art related to aesthetics and research in the psychology of aesthetics are surveyed, including relation between complexity and aesthetics, measures of complexity, and complexity predictors are covered.
Adversarial Evolution and Deep Learning - How Does an Artist Play with Our Visual System?
The resulting artificially intelligent artist, whimsically named Hercule LeNet, aims to produce images of low algorithmic complexity which nevertheless resemble a set of real photographs well enough to fool an adversarially trained deep learning critic modeled on the human visual system.
Ten years of a model of aesthetic appreciation and aesthetic judgments : The aesthetic episode - Developments and challenges in empirical aesthetics.
The current state of the descriptive information-processing model, and its relation to the major topics in empirical aesthetics today, including the nature of aesthetic emotions, the role of context, and the neural and evolutionary foundations of art and aesthetics are reviewed.
A model of aesthetic appreciation and aesthetic judgments.
It is explained why modern art's large number of individualized styles, innovativeness and conceptuality offer positive aesthetic experiences and why the challenge of art is mainly driven by a need for understanding.
Deep Interactive Evolution
The main insight in this paper is that a GAN trained on a specific target domain can act as a compact and robust genotype-to-phenotype mapping, allowing controllable and high-quality image generation.
On Hybrid Creativity
This article argues for a collaborative relationship with the computer that can free the artist to more fearlessly engage with the challenges of working with emergent systems that exhibit complex unpredictable behavior.
CAN: Creative Adversarial Networks, Generating "Art" by Learning About Styles and Deviating from Style Norms
The results show that human subjects could not distinguish artgenerated by the proposed system from art generated by contemporary artists and shown in top art fairs.
Camera Obscurer: Generative Art for Design Inspiration
We investigate using generated decorative art as a source of inspiration for design tasks. Using a visual similarity search for image retrieval, the Camera Obscurer app enables rapid searching of
Adapting and Enhancing Evolutionary Art for Casual Creation
Employing a fun-first methodology for the app design, an evolutionary art approach for casual creation was adapted and enhanced, and image production speed and the quality of randomly generated images were improved.
Adversarial Autoencoders
This paper shows how the adversarial autoencoder can be used in applications such as semi-supervised classification, disentangling style and content of images, unsupervised clustering, dimensionality reduction and data visualization, and performed experiments on MNIST, Street View House Numbers and Toronto Face datasets.