An optimization framework for inverse tone mapping using a single low dynamic range image

Ming Fan, Dae Hong Lee, Seung Wook Kim, Sung-Jea Ko

Research output: Contribution to journalArticle

Abstract

Conventional inverse tone-mapping (ITM) methods tend to produce contrast distortions such as contrast loss and contrast reversal in reconstructed high dynamic range (HDR) images. This paper proposes a novel ITM optimization framework based on the assumption that the input low dynamic range (LDR) image is similar to the LDR image obtained by tone mapping a true HDR image. In the proposed framework, an HDR image is initially reconstructed by applying a conventional tone-mapping function in a reverse manner, and then the reconstructed HDR image is iteratively modified toward the optimum HDR image by minimizing the difference between the input LDR image and a tone-mapped LDR image obtained from the reconstructed HDR image. The experimental results demonstrate that the proposed framework effectively reconstructs a high-quality HDR image and outperforms other conventional methods in terms of objective quality.

Original languageEnglish
Pages (from-to)274-283
Number of pages10
JournalSignal Processing: Image Communication
Volume78
DOIs
Publication statusPublished - 2019 Oct 1

Keywords

  • Brightness enhancement function
  • Inverse tone mapping
  • Newton–Raphson

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

An optimization framework for inverse tone mapping using a single low dynamic range image. / Fan, Ming; Lee, Dae Hong; Kim, Seung Wook; Ko, Sung-Jea.

In: Signal Processing: Image Communication, Vol. 78, 01.10.2019, p. 274-283.

Research output: Contribution to journalArticle

@article{19fb57cda69d4f7798faaf9d4f674985,
title = "An optimization framework for inverse tone mapping using a single low dynamic range image",
abstract = "Conventional inverse tone-mapping (ITM) methods tend to produce contrast distortions such as contrast loss and contrast reversal in reconstructed high dynamic range (HDR) images. This paper proposes a novel ITM optimization framework based on the assumption that the input low dynamic range (LDR) image is similar to the LDR image obtained by tone mapping a true HDR image. In the proposed framework, an HDR image is initially reconstructed by applying a conventional tone-mapping function in a reverse manner, and then the reconstructed HDR image is iteratively modified toward the optimum HDR image by minimizing the difference between the input LDR image and a tone-mapped LDR image obtained from the reconstructed HDR image. The experimental results demonstrate that the proposed framework effectively reconstructs a high-quality HDR image and outperforms other conventional methods in terms of objective quality.",
keywords = "Brightness enhancement function, Inverse tone mapping, Newton–Raphson",
author = "Ming Fan and Lee, {Dae Hong} and Kim, {Seung Wook} and Sung-Jea Ko",
year = "2019",
month = "10",
day = "1",
doi = "10.1016/j.image.2019.07.009",
language = "English",
volume = "78",
pages = "274--283",
journal = "Signal Processing: Image Communication",
issn = "0923-5965",
publisher = "Elsevier",

}

TY - JOUR

T1 - An optimization framework for inverse tone mapping using a single low dynamic range image

AU - Fan, Ming

AU - Lee, Dae Hong

AU - Kim, Seung Wook

AU - Ko, Sung-Jea

PY - 2019/10/1

Y1 - 2019/10/1

N2 - Conventional inverse tone-mapping (ITM) methods tend to produce contrast distortions such as contrast loss and contrast reversal in reconstructed high dynamic range (HDR) images. This paper proposes a novel ITM optimization framework based on the assumption that the input low dynamic range (LDR) image is similar to the LDR image obtained by tone mapping a true HDR image. In the proposed framework, an HDR image is initially reconstructed by applying a conventional tone-mapping function in a reverse manner, and then the reconstructed HDR image is iteratively modified toward the optimum HDR image by minimizing the difference between the input LDR image and a tone-mapped LDR image obtained from the reconstructed HDR image. The experimental results demonstrate that the proposed framework effectively reconstructs a high-quality HDR image and outperforms other conventional methods in terms of objective quality.

AB - Conventional inverse tone-mapping (ITM) methods tend to produce contrast distortions such as contrast loss and contrast reversal in reconstructed high dynamic range (HDR) images. This paper proposes a novel ITM optimization framework based on the assumption that the input low dynamic range (LDR) image is similar to the LDR image obtained by tone mapping a true HDR image. In the proposed framework, an HDR image is initially reconstructed by applying a conventional tone-mapping function in a reverse manner, and then the reconstructed HDR image is iteratively modified toward the optimum HDR image by minimizing the difference between the input LDR image and a tone-mapped LDR image obtained from the reconstructed HDR image. The experimental results demonstrate that the proposed framework effectively reconstructs a high-quality HDR image and outperforms other conventional methods in terms of objective quality.

KW - Brightness enhancement function

KW - Inverse tone mapping

KW - Newton–Raphson

UR - http://www.scopus.com/inward/record.url?scp=85069839917&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069839917&partnerID=8YFLogxK

U2 - 10.1016/j.image.2019.07.009

DO - 10.1016/j.image.2019.07.009

M3 - Article

AN - SCOPUS:85069839917

VL - 78

SP - 274

EP - 283

JO - Signal Processing: Image Communication

JF - Signal Processing: Image Communication

SN - 0923-5965

ER -