We describe a deep high-dynamic-range (HDR) image tone mapping operator that is computationally efficient and perceptually optimized. We first decompose an HDR image into a normalized Laplacian pyramid, and use two deep neural networks (DNNs) to estimate the Laplacian pyramid of the desired tone-mapped image from the normalized representation. We then end-to-end optimize the entire method over a database of HDR images by minimizing the normalized Laplacian pyramid distance (NLPD), a recently proposed perceptual metric. Qualitative and quantitative experiments demonstrate that our method produces images with better visual quality, and runs the fastest among existing local tone mapping algorithms.
@article{arxiv.2109.00180,
title = {Perceptually Optimized Deep High-Dynamic-Range Image Tone Mapping},
author = {Chenyang Le and Jiebin Yan and Yuming Fang and Kede Ma},
journal= {arXiv preprint arXiv:2109.00180},
year = {2021}
}