Low-Light Image Enhancement via Distillation of NIR-to-RGB Conversion Knowledge

Young Min Jeong; Tae Sung Park; Jeong Hyeok Park; Jong Ok Kim

doi:10.1109/APSIPAASC58517.2023.10317205

Low-Light Image Enhancement via Distillation of NIR-to-RGB Conversion Knowledge

Young Min Jeong, Tae Sung Park, Jeong Hyeok Park, Jong Ok Kim

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this paper, we propose a novel approach for low-light image enhancement via distillation of NIR-to-RGB conversion network's knowledge. NIR images contain abundant detail information that is independent of lighting conditions. We leverage the knowledge of the NIR-to-RGB conversion network, which effectively preserves detail information from NIR while generating accurate colors, as it shares similarities with low-light image enhancement. By using the rich detail information provided by the NIR-to-RGB conversion for low-light image enhancement, we are able to reduce color distortion and noise while preserving detail information. Our experimental results show the superior performance of our proposed network.

Original language	English
Title of host publication	2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	714-718
Number of pages	5
ISBN (Electronic)	9798350300673
DOIs	https://doi.org/10.1109/APSIPAASC58517.2023.10317205
Publication status	Published - 2023
Event	2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023 - Taipei, Taiwan, Province of China Duration: 2023 Oct 31 → 2023 Nov 3

Publication series

Name	2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023

Conference

Conference	2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023
Country/Territory	Taiwan, Province of China
City	Taipei
Period	23/10/31 → 23/11/3

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

ASJC Scopus subject areas

Hardware and Architecture
Signal Processing
Artificial Intelligence
Computer Science Applications

Access to Document

10.1109/APSIPAASC58517.2023.10317205

Cite this

Jeong, Y. M., Park, T. S., Park, J. H., & Kim, J. O. (2023). Low-Light Image Enhancement via Distillation of NIR-to-RGB Conversion Knowledge. In 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023 (pp. 714-718). (2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/APSIPAASC58517.2023.10317205

Low-Light Image Enhancement via Distillation of NIR-to-RGB Conversion Knowledge. / Jeong, Young Min; Park, Tae Sung; Park, Jeong Hyeok et al.
2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 714-718 (2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Jeong, YM, Park, TS, Park, JH & Kim, JO 2023, Low-Light Image Enhancement via Distillation of NIR-to-RGB Conversion Knowledge. in 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023. 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023, Institute of Electrical and Electronics Engineers Inc., pp. 714-718, 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023, Taipei, Taiwan, Province of China, 23/10/31. https://doi.org/10.1109/APSIPAASC58517.2023.10317205

Jeong YM, Park TS, Park JH, Kim JO. Low-Light Image Enhancement via Distillation of NIR-to-RGB Conversion Knowledge. In 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 714-718. (2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023). doi: 10.1109/APSIPAASC58517.2023.10317205

Jeong, Young Min ; Park, Tae Sung ; Park, Jeong Hyeok et al. / Low-Light Image Enhancement via Distillation of NIR-to-RGB Conversion Knowledge. 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 714-718 (2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023).

@inproceedings{55c73f97c2d644d6b95d96e657f712c2,

title = "Low-Light Image Enhancement via Distillation of NIR-to-RGB Conversion Knowledge",

abstract = "In this paper, we propose a novel approach for low-light image enhancement via distillation of NIR-to-RGB conversion network's knowledge. NIR images contain abundant detail information that is independent of lighting conditions. We leverage the knowledge of the NIR-to-RGB conversion network, which effectively preserves detail information from NIR while generating accurate colors, as it shares similarities with low-light image enhancement. By using the rich detail information provided by the NIR-to-RGB conversion for low-light image enhancement, we are able to reduce color distortion and noise while preserving detail information. Our experimental results show the superior performance of our proposed network.",

author = "Jeong, {Young Min} and Park, {Tae Sung} and Park, {Jeong Hyeok} and Kim, {Jong Ok}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023 ; Conference date: 31-10-2023 Through 03-11-2023",

year = "2023",

doi = "10.1109/APSIPAASC58517.2023.10317205",

language = "English",

series = "2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "714--718",

booktitle = "2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023",

}

TY - GEN

T1 - Low-Light Image Enhancement via Distillation of NIR-to-RGB Conversion Knowledge

AU - Jeong, Young Min

AU - Park, Tae Sung

AU - Park, Jeong Hyeok

AU - Kim, Jong Ok

PY - 2023

Y1 - 2023

N2 - In this paper, we propose a novel approach for low-light image enhancement via distillation of NIR-to-RGB conversion network's knowledge. NIR images contain abundant detail information that is independent of lighting conditions. We leverage the knowledge of the NIR-to-RGB conversion network, which effectively preserves detail information from NIR while generating accurate colors, as it shares similarities with low-light image enhancement. By using the rich detail information provided by the NIR-to-RGB conversion for low-light image enhancement, we are able to reduce color distortion and noise while preserving detail information. Our experimental results show the superior performance of our proposed network.

AB - In this paper, we propose a novel approach for low-light image enhancement via distillation of NIR-to-RGB conversion network's knowledge. NIR images contain abundant detail information that is independent of lighting conditions. We leverage the knowledge of the NIR-to-RGB conversion network, which effectively preserves detail information from NIR while generating accurate colors, as it shares similarities with low-light image enhancement. By using the rich detail information provided by the NIR-to-RGB conversion for low-light image enhancement, we are able to reduce color distortion and noise while preserving detail information. Our experimental results show the superior performance of our proposed network.

UR - http://www.scopus.com/inward/record.url?scp=85180009504&partnerID=8YFLogxK

U2 - 10.1109/APSIPAASC58517.2023.10317205

DO - 10.1109/APSIPAASC58517.2023.10317205

M3 - Conference contribution

AN - SCOPUS:85180009504

T3 - 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023

SP - 714

EP - 718

BT - 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023

Y2 - 31 October 2023 through 3 November 2023

ER -

Low-Light Image Enhancement via Distillation of NIR-to-RGB Conversion Knowledge

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this