Using Color Compatibility for Assessing Image Realism

By Jean-François Lalonde, Alexei A. Efros. 2007

171 citations recorded by the source corpus.

Why does placing an object from one photograph into another often make the colors of that object suddenly look wrong? One possibility is that humans prefer distributions of colors that are often found in nature; that is, we find pleasing these color combinations that we see often. Another possibility is that humans simply prefer colors to be consistent within an image, regardless of what they are. In this paper, we explore some of these issues by studying the color statistics of a large dataset of natural images, and by looking at differences in color distribution in realistic and unrealistic images. We apply our findings to two problems: 1) classifying composite images into realistic vs. non- realistic, and 2) recoloring image regions for realistic compositing.

Subfields: Atomic and Molecular Physics, and Optics, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atomic and Molecular Physics, and Optics

In Computer Vision and Pattern Recognition

Citations in the corpus

DoveNet: Deep Image Harmonization via Domain Verification (2019, methodology): “We compare with both traditional methods [20, 47] and deep learning based methods [54, 43, 45].”
CG2Real: Improving the Realism of Computer Generated Images Using a Large Collection of Photographs (2011, background): “Bae et al. [12] used a two-scale nonlinear decomposition of an image to transfer style between images.”
Semi-Parametric Image Synthesis (2018, unknown): “Hays and Efros [7] used a collection of images as source material for image completion.”
Deep Image Harmonization (2017, methodology): “Ground truth Input Lalonde [13] Xue [28] Zhu [32] Ours”
Rendering synthetic objects into legacy photographs (2011, unknown): “Like us, Lalonde et al. [2007] aim to allow a non-expert user populate an image with objects.”
Fighting Fake News: Image Splice Detection via Learned Self-Consistency (2018, methodology): “We do this mode-seeking using Mean Shift [39].”
Learning a Discriminative Model for the Perception of Realism in Composite Images (2015, methodology): “Table 1: Area under ROC curve comparing our method against previous methods [15, 23].”
Detection of GAN-Generated Fake Images over Social Networks (2018, background): “Differences in color distribution are explored in [10], while in [11] the statistical properties of local edge patches are used for discrimination.”