AffectGAN: Affect-Based Generative Art Driven by Semantics
This work addresses the problem of creating emotionally intentional generative art for researchers in affective computing and computational creativity, but it is incremental as it builds on existing methods with a small-scale validation.
The paper tackled generating artistic images that express specific affective states by developing AffectGAN, which uses generative adversarial networks, semantic models, and WikiArt data; results from a small study with 32 images and 50 participants showed that the intended emotions matched participants' responses in most cases.
This paper introduces a novel method for generating artistic images that express particular affective states. Leveraging state-of-the-art deep learning methods for visual generation (through generative adversarial networks), semantic models from OpenAI, and the annotated dataset of the visual art encyclopedia WikiArt, our AffectGAN model is able to generate images based on specific or broad semantic prompts and intended affective outcomes. A small dataset of 32 images generated by AffectGAN is annotated by 50 participants in terms of the particular emotion they elicit, as well as their quality and novelty. Results show that for most instances the intended emotion used as a prompt for image generation matches the participants' responses. This small-scale study brings forth a new vision towards blending affective computing with computational creativity, enabling generative systems with intentionality in terms of the emotions they wish their output to elicit.