An Automated Estimator of Image Visual Realism Based on Human Cognition
Citations Over TimeTop 18% of 2014 papers
Abstract
Assessing the visual realism of images is increasingly becoming an essential aspect of fields ranging from computer graphics (CG) rendering to photo manipulation. In this paper we systematically evaluate factors underlying human perception of visual realism and use that information to create an automated assessment of visual realism. We make the following unique contributions. First, we established a benchmark dataset of images with empirically determined visual realism scores. Second, we identified attributes potentially related to image realism, and used correlational techniques to determine that realism was most related to image naturalness, familiarity, aesthetics, and semantics. Third, we created an attributes-motivated, automated computational model that estimated image visual realism quantitatively. Using human assessment as a benchmark, the model was below human performance, but outperformed other state-of-the-art algorithms.
Related Papers
- → How should importance of naturalness be measured? A comparison of different scales(2019)47 cited
- → The effect of naturalness claims on perceptions of food product naturalness in the point of purchase(2013)40 cited
- → Predicting how consumers perceive the naturalness of snacks: The usefulness of a simple index(2021)18 cited
- Towards Improving the Naturalness of Social Conversations with Dialogue Systems(2010)
- → Naturalness and Naturalness Criteria(2005)