# Toward Quantifying Ambiguities in Artistic Images

arXiv: https://arxiv.org/abs/2008.09688 · HTML: https://mlsanity.com/paper/2008.09688/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Aug 2020.

## Built on by (most cited first, 8 of 8)

- [Visual Anagrams: Generating Multi-View Optical Illusions with Diffusion Models](https://mlsanity.com/paper/2311.17919/) (2023)
- [Active Divergence with Generative Deep Learning -- A Survey and Taxonomy](https://mlsanity.com/paper/2107.05599/) (2021)
- [Diffusion-based Visual Anagram as Multi-task Learning](https://mlsanity.com/paper/2412.02693/) (2024)
- [Illusion3D: 3D Multiview Illusion with 2D Diffusion Priors](https://mlsanity.com/paper/2412.09625/) (2024)
- [Continuation of Famous Art with AI: A Conditional Adversarial Network Inpainting Approach](https://mlsanity.com/paper/2110.09170/) (2021)
- [An Image-based Typology for Visualization](https://mlsanity.com/paper/2403.05594/) (2024)
- [Meschers: Geometry Processing of Impossible Objects](https://mlsanity.com/paper/2605.14960/) (2026)
- [Exploring Latent Dimensions of Crowd-sourced Creativity](https://mlsanity.com/paper/2112.06978/) (2021)

## Abstract (arXiv)

It has long been hypothesized that perceptual ambiguities play an important role in aesthetic experience: a work with some ambiguity engages a viewer more than one that does not. However, current frameworks for testing this theory are limited by the availability of stimuli and data collection methods. This paper presents an approach to measuring the perceptual ambiguity of a collection of images. Crowdworkers are asked to describe image content, after different viewing durations. Experiments are performed using images created with Generative Adversarial Networks, using the Artbreeder website. We show that text processing of viewer responses can provide a fine-grained way to measure and describe image ambiguities.