Example of reverse tone mapping using our technique for computing brightness enhancement functions.
(left) Input LDR image. (center) Brightness enhancement function produced by our technique. Note that
even the boundaries of the tiniest structures have been preserved. Also note the various shades associated
to the layers of clouds. (right) Split rendition of the resulting HDR image (white point scaled to 4,800 cd/m2 ).
Its darker (left) portion was processed using Reinhard et al.’s [18] photographic local tone mapping operator.
The brighter portion was visualized using the HDRShop software (with minus 8 stops).
High-Quality Brightness Enhancement Functions for Real-Time Reverse Tone Mapping
Rafael Pacheco Kovaleski
rpkovaleski@inf.ufrgs.br

Manuel M. Oliveira
oliveira@inf.ufrgs.br

Instituto de Informática, UFRGS

Logo INFLogo UFRGS

The Visual Computer.
Volume 25, Numbers 5-7, May 2009. pp. 539-547. [DOI]


Contents

Abstract Downloads Reference Acknowledgments

Abstract

This paper presents an automatic technique for producing high-quality brightness-enhancement functions for real-time reverse tone mapping of images and videos. Our approach uses a bilateral filter to obtain smooth results while preserving sharp luminance discontinuities, and can be efficiently implemented on GPUs. We demonstrate the effectiveness of our approach by reverse tone mapping several images and videos. Experiments based on HDR visible difference predicator and on an image distortion metric indicate that the results produced by our method are less prone to visible artifacts than the ones obtained with the state-of-the- art technique for real-time automatic computation of brightness enhancement functions.

Downloads

Paper


Full Paper (pre-print)

The final publication is available at Springer

Video

Reference

Citation

Kovaleski, Rafael and Manuel M. Oliveira "High-quality brightness enhancement functions for real-time reverse tone mapping"The Visual Computer. Volume 25 (2009), Numbers 5-7,  pp. 539-547.

BibTeX

   @article {springerlink:10.1007/s00371-009-0327-3,
   author = {Rafael Kovaleski and Manuel M. Oliveira},
   title = {High-quality brightness enhancement functions for real-time reverse tone mapping},
   journal = {The Visual Computer},
   keyword = {Computer Science},
   pages = {539-547},
   volume = {25},
   issue = {5},
   year = {2009}
}

Keywords

Brightness enhancement functions, Reverse tone mapping, Bilateral filtering.

Acknowledgments

CNPq-Brazil fellowships and grants #305613/2007-3 and 476954/2008-8.