Share Email Print

Proceedings Paper

A NR-IQA based deep neural network for tone mapping HDR images
Author(s): Minseok Choi; Pilkyu Park; Kwang Pyo Choi; Tejas Nair
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The most recent High Dynamic Range (HDR) standard, HDR10+, achieves good picture quality by incorporating dynamic metadata that carry frame-by-frame information for tone mapping while most HDR standards use static tone mapping curves that apply across the entire video. Since it is laborious to acquire hand-crafted best-fitting tone mapping curve for each frame, there have been attempts to derive the curves from input images. This paper proposes the neural network framework that generates tone mapping on a frame-by-frame basis. Although a number of successful tone mapping operators (TMOs) have been proposed over the years, evaluation of tone mapped images still remains a challenging topic. We define an objective measure to evaluate tone mapping based on Non-Reference Image Quality Assessment (NR-IQA). Experiments show that the framework produces good tone mapping curves and makes the video more vivid and colorful.

Paper Details

Date Published: 6 September 2019
PDF: 8 pages
Proc. SPIE 11137, Applications of Digital Image Processing XLII, 111370S (6 September 2019); doi: 10.1117/12.2528617
Show Author Affiliations
Minseok Choi, SAMSUNG Research (Korea, Republic of)
Pilkyu Park, SAMSUNG Research (Korea, Republic of)
Kwang Pyo Choi, SAMSUNG Research (Korea, Republic of)
Tejas Nair, SAMSUNG Research (Korea, Republic of)

Published in SPIE Proceedings Vol. 11137:
Applications of Digital Image Processing XLII
Andrew G. Tescher; Touradj Ebrahimi, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?