Image Visual Realism: From Human Perception to Machine Computation
| Autor: | Zhiqi Shen, Jonathan S. Herberg, Shaojing Fan, Tian-Tsong Ng, Ming Jiang, Qi Zhao, Bryan L. Koenig |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Male
Visual perception Computer science media_common.quotation_subject Image processing 02 engineering and technology Virtual reality Machine learning computer.software_genre Convolutional neural network 050105 experimental psychology Rendering (computer graphics) Machine Learning Computer graphics Artificial Intelligence Perception Computer Graphics Psychophysics 0202 electrical engineering electronic engineering information engineering Humans 0501 psychology and cognitive sciences Computer vision ComputingMethodologies_COMPUTERGRAPHICS media_common Models Statistical business.industry Applied Mathematics 05 social sciences Virtual Reality Visualization Computational Theory and Mathematics Visual Perception Female 020201 artificial intelligence & image processing Neural Networks Computer Computer Vision and Pattern Recognition Artificial intelligence business computer Software Realism |
| Zdroj: | IEEE Transactions on Pattern Analysis and Machine Intelligence. 40:2180-2193 |
| ISSN: | 1939-3539 0162-8828 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|