MoEnlight: Energy-efficient and self-Adaptive Low-light Video Stream Enhancement on Mobile Devices

Sicong Liu; Xiaochen Li; Zimu Zhou; Bin Guo; Yuan Xu; Zhiwen Yu

doi:10.1145/3603165.3607375

MoEnlight: Energy-efficient and self-Adaptive Low-light Video Stream Enhancement on Mobile Devices

Sicong Liu^*, Xiaochen Li, Zimu Zhou, Bin Guo, Yuan Xu, Zhiwen Yu

^*Corresponding author for this work

Department of Data Science

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

Abstract

Camera-equipped devices and deep learning advancements have driven the development of intelligent mobile video apps. These apps require on-device processing of video streams for real-Time, high-quality services while addressing privacy and robustness. However, their performance is limited by low-light conditions and small-Aperture cameras in mobile platforms. Existing low-light video enhancement solutions are unsuitable due to complex models and lack of energy efficiency. We introduce MoEnlight, an energy-conscious system for enhancing low-light video on mobile devices. MoEnlight achieves real-Time enhancement with competitive quality, adapting to dynamic energy budgets. Our experiments demonstrate MoEnlight's superiority over state-of-The-Art solutions for enhancing low-light videos. © 2023 Owner/Author.

Original language	English
Title of host publication	Proceedings of ACM Turing Award Celebration Conference, CHINA 2023
Publisher	Association for Computing Machinery
Pages	19-20
ISBN (Print)	9798400702334
DOIs	https://doi.org/10.1145/3603165.3607375
Publication status	Published - Jul 2023
Event	ACM Turing Award Celebration Conference - China 2023 (ACM TURC 2023): "Artificial General Intelligence, Human-Machine Symbiosis" - Wanda Reign Wuhan, Wuhan, China Duration: 28 Jul 2023 → 30 Jul 2023 https://www.acmturc.com/2023/en/index.html

Publication series

Name	Proceedings of ACM Turing Award Celebration Conference, CHINA

Conference

Conference	ACM Turing Award Celebration Conference - China 2023 (ACM TURC 2023)
Place	China
City	Wuhan
Period	28/07/23 → 30/07/23
Internet address	https://www.acmturc.com/2023/en/index.html

Research Keywords

energy awareness
low light video enhancement
mobile devices

Access Output

10.1145/3603165.3607375

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Liu, S., Li, X., Zhou, Z., Guo, B., Xu, Y., & Yu, Z. (2023). MoEnlight: Energy-efficient and self-Adaptive Low-light Video Stream Enhancement on Mobile Devices. In Proceedings of ACM Turing Award Celebration Conference, CHINA 2023 (pp. 19-20). (Proceedings of ACM Turing Award Celebration Conference, CHINA). Association for Computing Machinery. https://doi.org/10.1145/3603165.3607375

@inproceedings{91ea717d24d9481a813dea783eb3a790,

title = "MoEnlight: Energy-efficient and self-Adaptive Low-light Video Stream Enhancement on Mobile Devices",

abstract = "Camera-equipped devices and deep learning advancements have driven the development of intelligent mobile video apps. These apps require on-device processing of video streams for real-Time, high-quality services while addressing privacy and robustness. However, their performance is limited by low-light conditions and small-Aperture cameras in mobile platforms. Existing low-light video enhancement solutions are unsuitable due to complex models and lack of energy efficiency. We introduce MoEnlight, an energy-conscious system for enhancing low-light video on mobile devices. MoEnlight achieves real-Time enhancement with competitive quality, adapting to dynamic energy budgets. Our experiments demonstrate MoEnlight's superiority over state-of-The-Art solutions for enhancing low-light videos. {\textcopyright} 2023 Owner/Author.",

keywords = "energy awareness, low light video enhancement, mobile devices",

author = "Sicong Liu and Xiaochen Li and Zimu Zhou and Bin Guo and Yuan Xu and Zhiwen Yu",

year = "2023",

month = jul,

doi = "10.1145/3603165.3607375",

language = "English",

isbn = "9798400702334",

series = "Proceedings of ACM Turing Award Celebration Conference, CHINA",

publisher = "Association for Computing Machinery",

pages = "19--20",

booktitle = "Proceedings of ACM Turing Award Celebration Conference, CHINA 2023",

address = "United States",

note = "ACM Turing Award Celebration Conference - China 2023 (ACM TURC 2023) : {"}Artificial General Intelligence, Human-Machine Symbiosis{"} ; Conference date: 28-07-2023 Through 30-07-2023",

url = "https://www.acmturc.com/2023/en/index.html",

}

Liu, S, Li, X, Zhou, Z, Guo, B, Xu, Y & Yu, Z 2023, MoEnlight: Energy-efficient and self-Adaptive Low-light Video Stream Enhancement on Mobile Devices. in Proceedings of ACM Turing Award Celebration Conference, CHINA 2023. Proceedings of ACM Turing Award Celebration Conference, CHINA, Association for Computing Machinery, pp. 19-20, ACM Turing Award Celebration Conference - China 2023 (ACM TURC 2023), Wuhan, China, 28/07/23. https://doi.org/10.1145/3603165.3607375

MoEnlight: Energy-efficient and self-Adaptive Low-light Video Stream Enhancement on Mobile Devices. / Liu, Sicong; Li, Xiaochen; Zhou, Zimu et al.
Proceedings of ACM Turing Award Celebration Conference, CHINA 2023. Association for Computing Machinery, 2023. p. 19-20 (Proceedings of ACM Turing Award Celebration Conference, CHINA).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - MoEnlight

T2 - ACM Turing Award Celebration Conference - China 2023 (ACM TURC 2023)

AU - Liu, Sicong

AU - Li, Xiaochen

AU - Zhou, Zimu

AU - Guo, Bin

AU - Xu, Yuan

AU - Yu, Zhiwen

PY - 2023/7

Y1 - 2023/7

N2 - Camera-equipped devices and deep learning advancements have driven the development of intelligent mobile video apps. These apps require on-device processing of video streams for real-Time, high-quality services while addressing privacy and robustness. However, their performance is limited by low-light conditions and small-Aperture cameras in mobile platforms. Existing low-light video enhancement solutions are unsuitable due to complex models and lack of energy efficiency. We introduce MoEnlight, an energy-conscious system for enhancing low-light video on mobile devices. MoEnlight achieves real-Time enhancement with competitive quality, adapting to dynamic energy budgets. Our experiments demonstrate MoEnlight's superiority over state-of-The-Art solutions for enhancing low-light videos. © 2023 Owner/Author.

AB - Camera-equipped devices and deep learning advancements have driven the development of intelligent mobile video apps. These apps require on-device processing of video streams for real-Time, high-quality services while addressing privacy and robustness. However, their performance is limited by low-light conditions and small-Aperture cameras in mobile platforms. Existing low-light video enhancement solutions are unsuitable due to complex models and lack of energy efficiency. We introduce MoEnlight, an energy-conscious system for enhancing low-light video on mobile devices. MoEnlight achieves real-Time enhancement with competitive quality, adapting to dynamic energy budgets. Our experiments demonstrate MoEnlight's superiority over state-of-The-Art solutions for enhancing low-light videos. © 2023 Owner/Author.

KW - energy awareness

KW - low light video enhancement

KW - mobile devices

UR - http://www.scopus.com/inward/record.url?scp=85174262591&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85174262591&origin=recordpage

U2 - 10.1145/3603165.3607375

DO - 10.1145/3603165.3607375

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9798400702334

T3 - Proceedings of ACM Turing Award Celebration Conference, CHINA

SP - 19

EP - 20

BT - Proceedings of ACM Turing Award Celebration Conference, CHINA 2023

PB - Association for Computing Machinery

Y2 - 28 July 2023 through 30 July 2023

ER -

MoEnlight: Energy-efficient and self-Adaptive Low-light Video Stream Enhancement on Mobile Devices

Abstract

Publication series

Conference

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this