Enhancing Low-light Images using Infrared Encoded Images

Shulin Tian; Yufei Wang; Renjie Wan; Wenhan Yang; Alex C. Kot; Bihan Wen

doi:10.1109/ICIP49359.2023.10222583

Enhancing Low-light Images using Infrared Encoded Images

Shulin Tian, Yufei Wang, Renjie Wan, Wenhan Yang, Alex C. Kot, Bihan Wen

Department of Computer Science

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

Abstract

Low-light image enhancement task is essential yet challenging as it is ill-posed intrinsically. Previous arts mainly focus on the low-light images captured in the visible spectrum using pixel-wise loss, which limits the capacity of recovering the brightness, contrast, and texture details due to the small number of income photons. In this work, we propose a novel approach to increase the visibility of images captured under low-light environments by removing the in-camera infrared (IR) cut-off filter, which allows for the capture of more photons and results in improved signal-to-noise ratio due to the inclusion of information from the IR spectrum. To verify the proposed strategy, we collect a paired dataset of low-light images captured without the IR cut-off filter, with corresponding long-exposure reference images with an external filter. The experimental results on the proposed dataset demonstrate the effectiveness of the proposed method, showing better performance quantitatively and qualitatively. The dataset and code are publicly available at https://wyf0912.github.io/ELIEI/

Original language	English
Title of host publication	2023 IEEE International Conference on Image Processing (ICIP)
Publisher	IEEE
Pages	465-469
Number of pages	5
ISBN (Electronic)	9781728198354
ISBN (Print)	9781728198361
DOIs	https://doi.org/10.1109/ICIP49359.2023.10222583
Publication status	Published - 8 Oct 2023
Event	2023 30th IEEE International Conference on Image Processing, ICIP 2023 - Kuala Lumpur, Malaysia Duration: 8 Oct 2023 → 11 Oct 2023 https://2023.ieeeicip.org/ (Conference website) https://ieeexplore.ieee.org/xpl/conhome/10221937/proceeding (Conference proceedings) https://cmsworkshops.com/ICIP2023/technical_program.php (Conference programme)

Publication series

Name	IEEE International Conference on Image Processing, ICIP
Publisher	IEEE

Conference

Conference	2023 30th IEEE International Conference on Image Processing, ICIP 2023
Country/Territory	Malaysia
City	Kuala Lumpur
Period	8/10/23 → 11/10/23
Internet address	https://2023.ieeeicip.org/ (Conference website) https://ieeexplore.ieee.org/xpl/conhome/10221937/proceeding (Conference proceedings) https://cmsworkshops.com/ICIP2023/technical_program.php (Conference programme)

Scopus Subject Areas

Software
Signal Processing
Computer Vision and Pattern Recognition

User-Defined Keywords

Low-light enhancement
computational photography
infrared photography

Access to Document

10.1109/ICIP49359.2023.10222583

Cite this

@inproceedings{43242e2123d140b8a3b96f97ceff009c,

title = "Enhancing Low-light Images using Infrared Encoded Images",

abstract = "Low-light image enhancement task is essential yet challenging as it is ill-posed intrinsically. Previous arts mainly focus on the low-light images captured in the visible spectrum using pixel-wise loss, which limits the capacity of recovering the brightness, contrast, and texture details due to the small number of income photons. In this work, we propose a novel approach to increase the visibility of images captured under low-light environments by removing the in-camera infrared (IR) cut-off filter, which allows for the capture of more photons and results in improved signal-to-noise ratio due to the inclusion of information from the IR spectrum. To verify the proposed strategy, we collect a paired dataset of low-light images captured without the IR cut-off filter, with corresponding long-exposure reference images with an external filter. The experimental results on the proposed dataset demonstrate the effectiveness of the proposed method, showing better performance quantitatively and qualitatively. The dataset and code are publicly available at https://wyf0912.github.io/ELIEI/",

keywords = "Low-light enhancement, computational photography, infrared photography",

author = "Shulin Tian and Yufei Wang and Renjie Wan and Wenhan Yang and Kot, {Alex C.} and Bihan Wen",

note = "This work was done at Rapid-Rich Object Search (ROSE) Lab, Nanyang Technological University. This research is supported in part by the NTU-PKU Joint Research Institute (a collaboration between the Nanyang Technological University and Peking University that is sponsored by a donation from the Ng Teng Fong Charitable Foundation), the Basic and Frontier Research Project of PCL, the Major Key Project of PCL, and the MOE AcRF Tier 1 (RG61/22) and Start-Up Grant. Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 30th IEEE International Conference on Image Processing, ICIP 2023 ; Conference date: 08-10-2023 Through 11-10-2023",

year = "2023",

month = oct,

day = "8",

doi = "10.1109/ICIP49359.2023.10222583",

language = "English",

isbn = "9781728198361",

series = "IEEE International Conference on Image Processing, ICIP",

publisher = "IEEE",

pages = "465--469",

booktitle = "2023 IEEE International Conference on Image Processing (ICIP)",

address = "United States",

url = "https://2023.ieeeicip.org/, https://ieeexplore.ieee.org/xpl/conhome/10221937/proceeding, https://cmsworkshops.com/ICIP2023/technical_program.php",

}

Tian, S, Wang, Y, Wan, R, Yang, W, Kot, AC & Wen, B 2023, Enhancing Low-light Images using Infrared Encoded Images. in 2023 IEEE International Conference on Image Processing (ICIP). IEEE International Conference on Image Processing, ICIP, IEEE, pp. 465-469, 2023 30th IEEE International Conference on Image Processing, ICIP 2023, Kuala Lumpur, Malaysia, 8/10/23. https://doi.org/10.1109/ICIP49359.2023.10222583

TY - GEN

T1 - Enhancing Low-light Images using Infrared Encoded Images

AU - Tian, Shulin

AU - Wang, Yufei

AU - Wan, Renjie

AU - Yang, Wenhan

AU - Kot, Alex C.

AU - Wen, Bihan

N1 - This work was done at Rapid-Rich Object Search (ROSE) Lab, Nanyang Technological University. This research is supported in part by the NTU-PKU Joint Research Institute (a collaboration between the Nanyang Technological University and Peking University that is sponsored by a donation from the Ng Teng Fong Charitable Foundation), the Basic and Frontier Research Project of PCL, the Major Key Project of PCL, and the MOE AcRF Tier 1 (RG61/22) and Start-Up Grant. Publisher Copyright: © 2023 IEEE.

PY - 2023/10/8

Y1 - 2023/10/8

N2 - Low-light image enhancement task is essential yet challenging as it is ill-posed intrinsically. Previous arts mainly focus on the low-light images captured in the visible spectrum using pixel-wise loss, which limits the capacity of recovering the brightness, contrast, and texture details due to the small number of income photons. In this work, we propose a novel approach to increase the visibility of images captured under low-light environments by removing the in-camera infrared (IR) cut-off filter, which allows for the capture of more photons and results in improved signal-to-noise ratio due to the inclusion of information from the IR spectrum. To verify the proposed strategy, we collect a paired dataset of low-light images captured without the IR cut-off filter, with corresponding long-exposure reference images with an external filter. The experimental results on the proposed dataset demonstrate the effectiveness of the proposed method, showing better performance quantitatively and qualitatively. The dataset and code are publicly available at https://wyf0912.github.io/ELIEI/

AB - Low-light image enhancement task is essential yet challenging as it is ill-posed intrinsically. Previous arts mainly focus on the low-light images captured in the visible spectrum using pixel-wise loss, which limits the capacity of recovering the brightness, contrast, and texture details due to the small number of income photons. In this work, we propose a novel approach to increase the visibility of images captured under low-light environments by removing the in-camera infrared (IR) cut-off filter, which allows for the capture of more photons and results in improved signal-to-noise ratio due to the inclusion of information from the IR spectrum. To verify the proposed strategy, we collect a paired dataset of low-light images captured without the IR cut-off filter, with corresponding long-exposure reference images with an external filter. The experimental results on the proposed dataset demonstrate the effectiveness of the proposed method, showing better performance quantitatively and qualitatively. The dataset and code are publicly available at https://wyf0912.github.io/ELIEI/

KW - Low-light enhancement

KW - computational photography

KW - infrared photography

UR - http://www.scopus.com/inward/record.url?scp=85180762694&partnerID=8YFLogxK

U2 - 10.1109/ICIP49359.2023.10222583

DO - 10.1109/ICIP49359.2023.10222583

M3 - Conference proceeding

SN - 9781728198361

T3 - IEEE International Conference on Image Processing, ICIP

SP - 465

EP - 469

BT - 2023 IEEE International Conference on Image Processing (ICIP)

PB - IEEE

T2 - 2023 30th IEEE International Conference on Image Processing, ICIP 2023

Y2 - 8 October 2023 through 11 October 2023

ER -

Enhancing Low-light Images using Infrared Encoded Images

Abstract

Publication series

Conference

Scopus Subject Areas

User-Defined Keywords

Access to Document

Other files and links

Fingerprint

Cite this