Open AccessMethod for reconstructing a high dynamic range image based on a single-shot filtered low dynamic range image
Author(s) -
Bin Liang,
Dongdong Weng,
Yihua Bao,
Ziqi Tu,
Le Luo
Publication year - 2020
Publication title -
optics express
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.394
H-Index - 271
ISSN - 1094-4087
DOI - 10.1364/oe.400820
Subject(s) - high dynamic range , tone mapping , artificial intelligence , computer vision , dynamic range , computer science , high dynamic range imaging , rgb color model , luminance , image processing , optics , filter (signal processing) , inverse filter , single shot , range (aeronautics) , lens (geology) , image restoration , image (mathematics) , inverse , mathematics , physics , materials science , geometry , composite material
Traditional cameras are limited by sensors and cannot directly capture single-shot high dynamic range (HDR) images. We propose an improved single-shot HDR image reconstruction method that uses a single-exposure filtered low dynamic range (FLDR) image. First, by adding an optical filter in front of the camera lens, a FLDR image with different RGB channel exposure states and luminance ranges can be captured in a single-shot, unlike the traditional LDR image. Second, a deep inverse tone mapping network (DITMnet) with multibranch features extraction and multioutput images synthesis is designed to reconstruct an HDR image from a single FLDR image. Experimentally, under different exposure states and color spaces, our method outperforms similar algorithms.