2022
DOI: 10.3389/fnbot.2022.841426
|View full text |Cite
|
Sign up to set email alerts
|

Color Constancy via Multi-Scale Region-Weighed Network Guided by Semantics

Abstract: In obtaining color constancy, estimating the illumination of a scene is the most important task. However, due to unknown light sources and the influence of the external imaging environment, the estimated illumination is prone to color ambiguity. In this article, a learning-based multi-scale region-weighed network guided by semantic features is proposed to estimate the illuminated color of the light source in a scene. Cued by the human brain's processing of color constancy, we use image semantics and scale info… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
5
1

Relationship

1
5

Authors

Journals

citations
Cited by 7 publications
(2 citation statements)
references
References 57 publications
0
2
0
Order By: Relevance
“…A quantitative comparison of the seven fusion results was chosen to avoid the interference of subjective human factors [ 35 , 36 , 37 ]. All fused images are based on publicly available code, and all data in the tables are from our own measurements of the fused images.…”
Section: Experimental Results and Analysismentioning
confidence: 99%
“…A quantitative comparison of the seven fusion results was chosen to avoid the interference of subjective human factors [ 35 , 36 , 37 ]. All fused images are based on publicly available code, and all data in the tables are from our own measurements of the fused images.…”
Section: Experimental Results and Analysismentioning
confidence: 99%
“…In recent years, deep learning-based AWB algorithms 4 , 11 15 have made significant improvements to address this issue. For example, FC4 11 can generate final illuminant estimation results by establishing confidence maps for each color patch in the scene.…”
Section: Introductionmentioning
confidence: 99%