Abstract
Visual realism is defined as the extent to which an image appears to people as a photo rather than computer generated. Assessing visual realism is important in applications like computer graphics rendering and photo retouching. However, current realism evaluation approaches use either labor-intensive human judgments or automated algorithms largely dependent on comparing renderings to reference images. We develop a reference-free computational framework for visual realism prediction to overcome these constraints. First, we construct a benchmark dataset of 2,520 images with comprehensive human annotated attributes. From statistical modeling on this data, we identify image attributes most relevant for visual realism. We propose both empirically-based (guided by our statistical modeling of human data) and deep convolutional neural network models to predict visual realism of images. Our framework has the following advantages: (1) it creates an interpretable and concise empirical model that characterizes human perception of visual realism; (2) it links computational features to latent factors of human image perception.
Original language | English (US) |
---|---|
Article number | 8022957 |
Pages (from-to) | 2180-2193 |
Number of pages | 14 |
Journal | IEEE Transactions on Pattern Analysis and Machine Intelligence |
Volume | 40 |
Issue number | 9 |
DOIs | |
State | Published - Sep 1 2018 |
Bibliographical note
Publisher Copyright:© 1979-2012 IEEE.
Keywords
- Visual realism
- convolutional neural network
- human psychophysics
- statistical modeling