Image Visual Realism: From Human Perception to Machine Computation

Shaojing Fan, Tian Tsong Ng, Bryan L. Koenig, Jonathan S. Herberg, Ming Jiang, Zhiqi Shen, Qi Zhao

Research output: Contribution to journalArticlepeer-review

7 Scopus citations

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 languageEnglish (US)
Article number8022957
Pages (from-to)2180-2193
Number of pages14
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume40
Issue number9
DOIs
StatePublished - Sep 1 2018

Keywords

  • Visual realism
  • convolutional neural network
  • human psychophysics
  • statistical modeling

Fingerprint Dive into the research topics of 'Image Visual Realism: From Human Perception to Machine Computation'. Together they form a unique fingerprint.

Cite this