Adversarial and Adaptive Tone Mapping Operator for High Dynamic Range Images
Authors:
- 1 December 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1814-1821
Abstract
This work addresses tone mapping, a common approach to convert high dynamic range (HDR) images into low dynamic range (LDR) images. We approach this problem by using adaptive tone mapping. We propose to deploy a conditional generative adversarial networks to build an adversarial and adaptive tone mapping operator (adTMO) that converts HDR into LDR images. We use an objective quality metric called the Tone Mapped Image Quality Index (TMQI) to evaluate our adTMO. Trained with 256*256 images, adTMO is able to generate 256*256 and high-resolution 1024*2048 LDR images. Given 1024*2048 HDR images, TMQI of the generated LDR images reaches the value of 0.90, which outperforms all other contemporary tone mapping operators.Keywords
Funding Information
- Natural Sciences and Engineering Research Council of Canada
- Biomet
- Mitacs
This publication has 14 references indexed in Scilit:
- Application‐Specific Tone Mapping Via Genetic ProgrammingComputer Graphics Forum, 2017
- Advanced High Dynamic Range Imaging2017
- Deep high dynamic range imaging of dynamic scenesACM Transactions on Graphics, 2017
- The Southampton-York Natural Scenes (SYNS) dataset: Statistics of surface attitudeScientific Reports, 2016
- High Dynamic Range Image Compression by Optimizing Tone Mapped Image Quality IndexIEEE Transactions on Image Processing, 2015
- Objective Quality Assessment of Tone-Mapped ImagesIEEE Transactions on Image Processing, 2012
- Evaluation of tone mapping operators using a High Dynamic Range displayACM Transactions on Graphics, 2005
- Adaptive Logarithmic Mapping For Displaying High Contrast ScenesComputer Graphics Forum, 2003
- Two methods for display of high contrast imagesACM Transactions on Graphics, 1999
- A visibility matching tone reproduction operator for high dynamic range scenesIEEE Transactions on Visualization and Computer Graphics, 1997