Correcting Over-Exposure in Photographs
Dong Guo, Yuan Cheng, Shaojie Zhuo and Terence Sim
School of Computing
National University of Singapore
splash:input splash:detection splash:output
Input Photo Over-Exposed Regions Over-Exposure Corrected
Abstract
This paper introduces a method to correct over-exposure in an existing photograph by recovering the color and lightness separately. First, the dynamic range of well exposed region is slightly compressed to make room for the recovered lightness of the over-exposed region. Then the lightness is recovered based on an over-exposure likelihood. The color of each pixel is corrected via neighborhood propagation and also based on the confidence of the original color. Previous methods make use of ratios between different color channels to recover the over-exposed ones, and thus can not handle regions where all three channels are over-exposed. In contrast, our method does not have this limitation. Our method is fully automatic and requires only one single input photo. We also provide users with the flexibility to control the amount of over-exposure correction. Experiment results demonstrate the effectiveness of the proposed method in correcting over-exposure.
Workflow
workflow
Workflow of Correcting Over-Exposure.

Two aspects are included, lightness recovery (orange line) and color correction (green and blue lines). Lightness recovery is through L* channel using over-exposure likelihood P. Color correction is through a*, b* channels using color confidence C. Both P and C are derived from an over-exposure map M, which is generated from the input.

Downloads

Paper: Low Res PDF (3.9M)       High Res PDF (16.9M)       Poster: coming soon      

Bibtex:
@INPROCEEDINGS{Guo2010overexposure,
  title = {Correcting Over-Exposure in Photographs},
  author = {Dong Guo and Yuan Cheng and Shaojie Zhuo and Terence Sim},
  booktitle = {Proc. CVPR},
  year = {2010}
}
Comparison with Masood et al.*
compare:input
Input
compare:masood's
Result of Masood et al.
compare:our
Our Result
(photo courtesy of Han Lu)
* The result image by Masood et al. was generated by the code provided on the authors' website. More comparison results can be found here.
Reference: S. Z. Masood, J. Zhu, and M. F. Tappen. Automatic correction of saturated regions in photographs using cross-channel correlation. In Proc. PG, 2009.
More examples
input
Input
output
Output
input
Input
output
Output
input
Input
output
Output
input
Input
output
Output
input
Input
output
Output
input
Input
output
Output
input
Input
output
Output
First three photos courtesy of Xianjun Wang, Han Lu, Jing Sun, respectively. For the rest, sorry, I couldn't find the photographers' names.