Art-Photographic Detail Enhancement

Minjung Son
POSTECH

Yunjin Lee
Ajou University

Henry Kang
UMSL

Seungyong Lee
POSTECH

Computer Graphics Forum (Special Issue on Eurographics 2014), vol 33, no 2, April 2014


(a) Input Image

(b) Our Result [see original size]


Abstract

We present a novel method for enhancing details in a digital photograph, inspired by the principle of art photography. In contrast to the previous methods that primarily rely on tone scaling, our technique provides a flexible tone transform model that consists of two operators: shifting and scaling. This model permits shifting of the tonal range in each image region to enable significant detail boosting regardless of the original tone. We optimize these shift and scale factors in our constrained optimization framework to achieve extreme detail enhancement across the image in a piecewise smooth fashion, as in art photography. The experimental results show that the proposed method brings out a significantly large amount of details even from an ordinary low-dynamic range image.


Paper
PDF, 47.5MB
More Results
LINK

Talk
PDF, 25.5MB

BibTex

@article{Son-2014-art-photograph,
author = {Minjung Son and Yunjin Lee and Henry Kang and Seungyong Lee},
title = {Art-Photographic Detail Enhancement},
journal = {Computer Graphics Forum},
year = {2014},
volume = {33},
number = {2},
pages = {391-400},
}


Coupe: Open Source Photo Enhancement Library