Facial-Centric Color Constancy Dataset to Improve Scenario-Specific White Balance Algorithms

Yuyang Liu; Minchen Wei

doi:10.2352/CIC.2025.33.1.15

Facial-Centric Color Constancy Dataset to Improve Scenario-Specific White Balance Algorithms

Yuyang Liu
, Minchen Wei

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

Abstract

Eliminating the color cast of the illuminant is a critical step in modern image processing systems, which has been addressed with a great number of illuminant estimation algorithms. The algorithms are found not effective for some specific contexts and applications, which leads to the development of scenarios-specific algorithms leveraging domain-specific cues. This paper investigated how facial cues help illuminant estimation. A total of 1299 images were captured under various dual-illuminant conditions, including real-world environments and lab settings. Modifications were made on existing methods by considering the facial information, which resulted in better performance.

Original language	English
Title of host publication	Final Program and Proceedings - IS and T/SID Color Imaging Conference
Publisher	Society for Imaging Science and Technology
Pages	75-79
Number of pages	5
Edition	1
ISBN (Electronic)	9780892083701
DOIs	https://doi.org/10.2352/CIC.2025.33.1.15
Publication status	Published - Oct 2025
Event	33rd Color and Imaging Conference Final Program and Proceedings, CIC 2025 - Hong Kong, Hong Kong Duration: 27 Oct 2025 → 31 Oct 2025

Publication series

Name	Final Program and Proceedings - IS and T/SID Color Imaging Conference
Number	1
Volume	33
ISSN (Print)	2166-9635
ISSN (Electronic)	2169-2629

Conference

Conference	33rd Color and Imaging Conference Final Program and Proceedings, CIC 2025
Country/Territory	Hong Kong
City	Hong Kong
Period	27/10/25 → 31/10/25

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Atomic and Molecular Physics, and Optics
Computer Vision and Pattern Recognition

More information

10.2352/CIC.2025.33.1.15

Cite this

Liu, Y., & Wei, M. (2025). Facial-Centric Color Constancy Dataset to Improve Scenario-Specific White Balance Algorithms. In Final Program and Proceedings - IS and T/SID Color Imaging Conference (1 ed., pp. 75-79). (Final Program and Proceedings - IS and T/SID Color Imaging Conference; Vol. 33, No. 1). Society for Imaging Science and Technology. https://doi.org/10.2352/CIC.2025.33.1.15

@inproceedings{2839b7b7f9a447ac861d5c73503ec172,

title = "Facial-Centric Color Constancy Dataset to Improve Scenario-Specific White Balance Algorithms",

abstract = "Eliminating the color cast of the illuminant is a critical step in modern image processing systems, which has been addressed with a great number of illuminant estimation algorithms. The algorithms are found not effective for some specific contexts and applications, which leads to the development of scenarios-specific algorithms leveraging domain-specific cues. This paper investigated how facial cues help illuminant estimation. A total of 1299 images were captured under various dual-illuminant conditions, including real-world environments and lab settings. Modifications were made on existing methods by considering the facial information, which resulted in better performance.",

author = "Yuyang Liu and Minchen Wei",

note = "Publisher Copyright: {\textcopyright}2025 Society for Imaging Science and Technology.; 33rd Color and Imaging Conference Final Program and Proceedings, CIC 2025 ; Conference date: 27-10-2025 Through 31-10-2025",

year = "2025",

month = oct,

doi = "10.2352/CIC.2025.33.1.15",

language = "English",

series = "Final Program and Proceedings - IS and T/SID Color Imaging Conference",

publisher = "Society for Imaging Science and Technology",

number = "1",

pages = "75--79",

booktitle = "Final Program and Proceedings - IS and T/SID Color Imaging Conference",

address = "United States",

edition = "1",

}

Liu, Y & Wei, M 2025, Facial-Centric Color Constancy Dataset to Improve Scenario-Specific White Balance Algorithms. in Final Program and Proceedings - IS and T/SID Color Imaging Conference. 1 edn, Final Program and Proceedings - IS and T/SID Color Imaging Conference, no. 1, vol. 33, Society for Imaging Science and Technology, pp. 75-79, 33rd Color and Imaging Conference Final Program and Proceedings, CIC 2025, Hong Kong, Hong Kong, 27/10/25. https://doi.org/10.2352/CIC.2025.33.1.15

Facial-Centric Color Constancy Dataset to Improve Scenario-Specific White Balance Algorithms. / Liu, Yuyang; Wei, Minchen.
Final Program and Proceedings - IS and T/SID Color Imaging Conference. 1. ed. Society for Imaging Science and Technology, 2025. p. 75-79 (Final Program and Proceedings - IS and T/SID Color Imaging Conference; Vol. 33, No. 1).

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Facial-Centric Color Constancy Dataset to Improve Scenario-Specific White Balance Algorithms

AU - Liu, Yuyang

AU - Wei, Minchen

PY - 2025/10

Y1 - 2025/10

N2 - Eliminating the color cast of the illuminant is a critical step in modern image processing systems, which has been addressed with a great number of illuminant estimation algorithms. The algorithms are found not effective for some specific contexts and applications, which leads to the development of scenarios-specific algorithms leveraging domain-specific cues. This paper investigated how facial cues help illuminant estimation. A total of 1299 images were captured under various dual-illuminant conditions, including real-world environments and lab settings. Modifications were made on existing methods by considering the facial information, which resulted in better performance.

AB - Eliminating the color cast of the illuminant is a critical step in modern image processing systems, which has been addressed with a great number of illuminant estimation algorithms. The algorithms are found not effective for some specific contexts and applications, which leads to the development of scenarios-specific algorithms leveraging domain-specific cues. This paper investigated how facial cues help illuminant estimation. A total of 1299 images were captured under various dual-illuminant conditions, including real-world environments and lab settings. Modifications were made on existing methods by considering the facial information, which resulted in better performance.

UR - https://www.scopus.com/pages/publications/105039183569

U2 - 10.2352/CIC.2025.33.1.15

DO - 10.2352/CIC.2025.33.1.15

M3 - Conference article published in proceeding or book

AN - SCOPUS:105039183569

T3 - Final Program and Proceedings - IS and T/SID Color Imaging Conference

SP - 75

EP - 79

BT - Final Program and Proceedings - IS and T/SID Color Imaging Conference

PB - Society for Imaging Science and Technology

T2 - 33rd Color and Imaging Conference Final Program and Proceedings, CIC 2025

Y2 - 27 October 2025 through 31 October 2025

ER -

Facial-Centric Color Constancy Dataset to Improve Scenario-Specific White Balance Algorithms

Abstract

Publication series

Conference

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this