Work

Learning a Discriminative Model for the Perception of Realism in Composite Images

Year: 2015
Type: conference-paper
Abstract: What makes an image appear realistic? In this work, we are answering this question from a data-driven perspective by learning the perception of visual realism directly from large amounts of data. In particular, we train a Convolutional Neural Network (CNN) model that distinguishes natural photographs from automatically generated composite images. The model learns to predict visual realism of a scene in terms of color, lighting and texture compatibility, without any human annotations pertaining to it. Our model outperforms previous works that rely on hand-crafted heuristics, for the task of classifying realistic vs. unrealistic photos. Furthermore, we apply our learned model to compute optimal parameters of a compositing method, to maximize the visual realism score predicted by our CNN model. We demonstrate its advantage against existing methods via a human perception study.
Language: English
Open Access status: green
OpenAlex ID: W2190424233
FWCI: 3.226
Cites: 44
Cited by: 151
Related to: 10