Probability Models for High Dynamic Range Imaging
Abstract
Methods for expanding the dynamic range of digital photographs by combining images taken at different exposures have recently received a lot of attention. Current techniques assume that the photometric transfer function of a given camera is the same (modulo an overall exposure change) for all the input images. Unfortunately, this is rarely the case with today's camera, which may perform complex nonlinear color and intensity transforms on each picture. In this paper, we show how the use of probability models for the imaging system and weak prior models for the response functions enable us to estimate a different function for each image using only pixel intensity values. Our approach also allows us to characterize the uncertainty inherent in each pixel measurement. We can therefore produce statistically optimal estimates for the hidden variables in our model representing scene irradiance. We present results using this method to statistically characterize camera imaging functions and construct high-quality high dynamic range (HDR) images using only image pixel information.
Cite
Text
Pal et al. "Probability Models for High Dynamic Range Imaging." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2004. doi:10.1109/CVPR.2004.192Markdown
[Pal et al. "Probability Models for High Dynamic Range Imaging." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2004.](https://mlanthology.org/cvpr/2004/pal2004cvpr-probability/) doi:10.1109/CVPR.2004.192BibTeX
@inproceedings{pal2004cvpr-probability,
title = {{Probability Models for High Dynamic Range Imaging}},
author = {Pal, Chris and Szeliski, Richard and Uyttendaele, Matthew and Jojic, Nebojsa},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2004},
pages = {173-180},
doi = {10.1109/CVPR.2004.192},
url = {https://mlanthology.org/cvpr/2004/pal2004cvpr-probability/}
}