Automatic color realism enhancement for computer generated images

Hyunjung Shim, Seungkyu Lee

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Photorealism has been one of the essential elements in producing computer generated imagery. The state-of-the-art techniques employ various rendering algorithms to simulate physically accurate light transport for generating a photorealistic appearance of scene. However, they require a labor-intensive tone mapping and color tunes by an experienced artist. In this paper, we propose an automatic photorealism enhancement algorithm by manipulating the color distribution of graphics so to match with that of real photographs. Our hypothesis is that photorealism is highly correlated with the frequency of color occurrence in real photographs; more often we observe more realistic we believe. Based on this hypothesis, we find principal color components by following two steps. First, we extract the most representative features from the color distribution of photographs. Then, we obtain the coefficients of the most distinguishable principal axis to separate the features of photographs and those of graphics. The distribution of these coefficients constructs the color distribution of graphics and real photographs, respectively. Then, we modify the statistical characteristics (orientation, variation and the mean of color distribution) of graphics according to that of photographs. Experiments and user study have confirmed the effectiveness of proposed method.

Original languageEnglish
Pages (from-to)966-973
Number of pages8
JournalComputers and Graphics (Pergamon)
Volume36
Issue number8
DOIs
Publication statusPublished - 2012 Dec

Fingerprint

Color
Personnel
Experiments

All Science Journal Classification (ASJC) codes

  • Engineering(all)
  • Human-Computer Interaction
  • Computer Graphics and Computer-Aided Design

Cite this

@article{6316b0c23ab146a09e5f7f49c7472fe6,
title = "Automatic color realism enhancement for computer generated images",
abstract = "Photorealism has been one of the essential elements in producing computer generated imagery. The state-of-the-art techniques employ various rendering algorithms to simulate physically accurate light transport for generating a photorealistic appearance of scene. However, they require a labor-intensive tone mapping and color tunes by an experienced artist. In this paper, we propose an automatic photorealism enhancement algorithm by manipulating the color distribution of graphics so to match with that of real photographs. Our hypothesis is that photorealism is highly correlated with the frequency of color occurrence in real photographs; more often we observe more realistic we believe. Based on this hypothesis, we find principal color components by following two steps. First, we extract the most representative features from the color distribution of photographs. Then, we obtain the coefficients of the most distinguishable principal axis to separate the features of photographs and those of graphics. The distribution of these coefficients constructs the color distribution of graphics and real photographs, respectively. Then, we modify the statistical characteristics (orientation, variation and the mean of color distribution) of graphics according to that of photographs. Experiments and user study have confirmed the effectiveness of proposed method.",
author = "Hyunjung Shim and Seungkyu Lee",
year = "2012",
month = "12",
doi = "10.1016/j.cag.2012.09.001",
language = "English",
volume = "36",
pages = "966--973",
journal = "Computers and Graphics",
issn = "0097-8493",
publisher = "Elsevier Limited",
number = "8",

}

Automatic color realism enhancement for computer generated images. / Shim, Hyunjung; Lee, Seungkyu.

In: Computers and Graphics (Pergamon), Vol. 36, No. 8, 12.2012, p. 966-973.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automatic color realism enhancement for computer generated images

AU - Shim, Hyunjung

AU - Lee, Seungkyu

PY - 2012/12

Y1 - 2012/12

N2 - Photorealism has been one of the essential elements in producing computer generated imagery. The state-of-the-art techniques employ various rendering algorithms to simulate physically accurate light transport for generating a photorealistic appearance of scene. However, they require a labor-intensive tone mapping and color tunes by an experienced artist. In this paper, we propose an automatic photorealism enhancement algorithm by manipulating the color distribution of graphics so to match with that of real photographs. Our hypothesis is that photorealism is highly correlated with the frequency of color occurrence in real photographs; more often we observe more realistic we believe. Based on this hypothesis, we find principal color components by following two steps. First, we extract the most representative features from the color distribution of photographs. Then, we obtain the coefficients of the most distinguishable principal axis to separate the features of photographs and those of graphics. The distribution of these coefficients constructs the color distribution of graphics and real photographs, respectively. Then, we modify the statistical characteristics (orientation, variation and the mean of color distribution) of graphics according to that of photographs. Experiments and user study have confirmed the effectiveness of proposed method.

AB - Photorealism has been one of the essential elements in producing computer generated imagery. The state-of-the-art techniques employ various rendering algorithms to simulate physically accurate light transport for generating a photorealistic appearance of scene. However, they require a labor-intensive tone mapping and color tunes by an experienced artist. In this paper, we propose an automatic photorealism enhancement algorithm by manipulating the color distribution of graphics so to match with that of real photographs. Our hypothesis is that photorealism is highly correlated with the frequency of color occurrence in real photographs; more often we observe more realistic we believe. Based on this hypothesis, we find principal color components by following two steps. First, we extract the most representative features from the color distribution of photographs. Then, we obtain the coefficients of the most distinguishable principal axis to separate the features of photographs and those of graphics. The distribution of these coefficients constructs the color distribution of graphics and real photographs, respectively. Then, we modify the statistical characteristics (orientation, variation and the mean of color distribution) of graphics according to that of photographs. Experiments and user study have confirmed the effectiveness of proposed method.

UR - http://www.scopus.com/inward/record.url?scp=84867421589&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84867421589&partnerID=8YFLogxK

U2 - 10.1016/j.cag.2012.09.001

DO - 10.1016/j.cag.2012.09.001

M3 - Article

AN - SCOPUS:84867421589

VL - 36

SP - 966

EP - 973

JO - Computers and Graphics

JF - Computers and Graphics

SN - 0097-8493

IS - 8

ER -