Perceptually Optimized Deep High-Dynamic-Range Image Tone Mapping
This work addresses the need for efficient and high-quality tone mapping in image processing, though it appears incremental as it builds on existing perceptual metrics and deep learning techniques.
The paper tackled the problem of tone mapping high-dynamic-range (HDR) images by developing a deep learning method that uses Laplacian pyramid decomposition and neural networks, resulting in images with better visual quality and the fastest runtime among local tone mapping algorithms.
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.