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

Jun-Yan Zhu, Philipp Krahenbuhl, Eli Shechtman, Alexei A. Efros; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2015, pp. 3943-3951

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.

Related Material


[pdf]
[bibtex]
@InProceedings{Zhu_2015_ICCV,
author = {Zhu, Jun-Yan and Krahenbuhl, Philipp and Shechtman, Eli and Efros, Alexei A.},
title = {Learning a Discriminative Model for the Perception of Realism in Composite Images},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
month = {December},
year = {2015}
}