Convolutional Neural Network based Inverse Tone Mapping for High Dynamic Range Display using LUCORE

Katsuhiko Hirao, Zhengxue Cheng, Masaru Takeuchi, Jiro Katto

研究成果: Conference contribution

1 引用 (Scopus)

抄録

The popularity of high dynamic range (HDR) makes the inverse tone mapping become an important technique for HDR display. In this paper, we propose a convolutional neural network (CNN)-based inverse tone mapping method to generate a high-quality HDR image from one single standard dynamic range (SDR) image. First, we present a CNN design with a three- channel input, which considers both luminance and chrominance. Second, we propose to use overlapped inputs to remove the boundary artifacts, caused by zero paddings in CNN. Experimental results demonstrate the high quality of our generated HDR images compared to the ground truth.

元の言語English
ホスト出版物のタイトル2019 IEEE International Conference on Consumer Electronics, ICCE 2019
出版者Institute of Electrical and Electronics Engineers Inc.
ISBN(電子版)9781538679104
DOI
出版物ステータスPublished - 2019 3 6
イベント2019 IEEE International Conference on Consumer Electronics, ICCE 2019 - Las Vegas, United States
継続期間: 2019 1 112019 1 13

出版物シリーズ

名前2019 IEEE International Conference on Consumer Electronics, ICCE 2019

Conference

Conference2019 IEEE International Conference on Consumer Electronics, ICCE 2019
United States
Las Vegas
期間19/1/1119/1/13

Fingerprint

Display devices
Neural networks
Luminance

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering
  • Media Technology
  • Electrical and Electronic Engineering

これを引用

Hirao, K., Cheng, Z., Takeuchi, M., & Katto, J. (2019). Convolutional Neural Network based Inverse Tone Mapping for High Dynamic Range Display using LUCORE. : 2019 IEEE International Conference on Consumer Electronics, ICCE 2019 [8662048] (2019 IEEE International Conference on Consumer Electronics, ICCE 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCE.2019.8662048

Convolutional Neural Network based Inverse Tone Mapping for High Dynamic Range Display using LUCORE. / Hirao, Katsuhiko; Cheng, Zhengxue; Takeuchi, Masaru; Katto, Jiro.

2019 IEEE International Conference on Consumer Electronics, ICCE 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 8662048 (2019 IEEE International Conference on Consumer Electronics, ICCE 2019).

研究成果: Conference contribution

Hirao, K, Cheng, Z, Takeuchi, M & Katto, J 2019, Convolutional Neural Network based Inverse Tone Mapping for High Dynamic Range Display using LUCORE. : 2019 IEEE International Conference on Consumer Electronics, ICCE 2019., 8662048, 2019 IEEE International Conference on Consumer Electronics, ICCE 2019, Institute of Electrical and Electronics Engineers Inc., 2019 IEEE International Conference on Consumer Electronics, ICCE 2019, Las Vegas, United States, 19/1/11. https://doi.org/10.1109/ICCE.2019.8662048
Hirao K, Cheng Z, Takeuchi M, Katto J. Convolutional Neural Network based Inverse Tone Mapping for High Dynamic Range Display using LUCORE. : 2019 IEEE International Conference on Consumer Electronics, ICCE 2019. Institute of Electrical and Electronics Engineers Inc. 2019. 8662048. (2019 IEEE International Conference on Consumer Electronics, ICCE 2019). https://doi.org/10.1109/ICCE.2019.8662048
Hirao, Katsuhiko ; Cheng, Zhengxue ; Takeuchi, Masaru ; Katto, Jiro. / Convolutional Neural Network based Inverse Tone Mapping for High Dynamic Range Display using LUCORE. 2019 IEEE International Conference on Consumer Electronics, ICCE 2019. Institute of Electrical and Electronics Engineers Inc., 2019. (2019 IEEE International Conference on Consumer Electronics, ICCE 2019).
@inproceedings{bc414d6f8f5d4d258615c47279fb55a3,
title = "Convolutional Neural Network based Inverse Tone Mapping for High Dynamic Range Display using LUCORE",
abstract = "The popularity of high dynamic range (HDR) makes the inverse tone mapping become an important technique for HDR display. In this paper, we propose a convolutional neural network (CNN)-based inverse tone mapping method to generate a high-quality HDR image from one single standard dynamic range (SDR) image. First, we present a CNN design with a three- channel input, which considers both luminance and chrominance. Second, we propose to use overlapped inputs to remove the boundary artifacts, caused by zero paddings in CNN. Experimental results demonstrate the high quality of our generated HDR images compared to the ground truth.",
author = "Katsuhiko Hirao and Zhengxue Cheng and Masaru Takeuchi and Jiro Katto",
year = "2019",
month = "3",
day = "6",
doi = "10.1109/ICCE.2019.8662048",
language = "English",
series = "2019 IEEE International Conference on Consumer Electronics, ICCE 2019",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2019 IEEE International Conference on Consumer Electronics, ICCE 2019",

}

TY - GEN

T1 - Convolutional Neural Network based Inverse Tone Mapping for High Dynamic Range Display using LUCORE

AU - Hirao, Katsuhiko

AU - Cheng, Zhengxue

AU - Takeuchi, Masaru

AU - Katto, Jiro

PY - 2019/3/6

Y1 - 2019/3/6

N2 - The popularity of high dynamic range (HDR) makes the inverse tone mapping become an important technique for HDR display. In this paper, we propose a convolutional neural network (CNN)-based inverse tone mapping method to generate a high-quality HDR image from one single standard dynamic range (SDR) image. First, we present a CNN design with a three- channel input, which considers both luminance and chrominance. Second, we propose to use overlapped inputs to remove the boundary artifacts, caused by zero paddings in CNN. Experimental results demonstrate the high quality of our generated HDR images compared to the ground truth.

AB - The popularity of high dynamic range (HDR) makes the inverse tone mapping become an important technique for HDR display. In this paper, we propose a convolutional neural network (CNN)-based inverse tone mapping method to generate a high-quality HDR image from one single standard dynamic range (SDR) image. First, we present a CNN design with a three- channel input, which considers both luminance and chrominance. Second, we propose to use overlapped inputs to remove the boundary artifacts, caused by zero paddings in CNN. Experimental results demonstrate the high quality of our generated HDR images compared to the ground truth.

UR - http://www.scopus.com/inward/record.url?scp=85063804048&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063804048&partnerID=8YFLogxK

U2 - 10.1109/ICCE.2019.8662048

DO - 10.1109/ICCE.2019.8662048

M3 - Conference contribution

AN - SCOPUS:85063804048

T3 - 2019 IEEE International Conference on Consumer Electronics, ICCE 2019

BT - 2019 IEEE International Conference on Consumer Electronics, ICCE 2019

PB - Institute of Electrical and Electronics Engineers Inc.

ER -