.png){kind=icon}
返回
Uncertainty estimation in color constancy
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2024.111175.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Computational color constancy is an under-determined problem. As such, a key objective is to assign a level of uncertainty to the output illuminant estimations, which can significantly impact the reliability of the corrected images for downstream computer vision tasks. In this paper we present a formalization of uncertainty estimation in color constancy, and we define three forms of uncertainty that require at most one inference run to be estimated. The defined uncertainty estimators are applied to five different categories of color constancy algorithms. The experimental results on two standard datasets show a strong correlation between the estimated uncertainty and the illuminant estimation error. Furthermore, we show how color constancy algorithms can be cascaded leveraging the estimated uncertainty to provide more accurate illuminant estimates.
Keyword:
Uncertainty estimation
Color constancy
Automatic white balance
Illuminant estimation
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Impact of signalling traffic for mobility management in an IN based PCS environment.png)
Proceedings of ICUPC '95 - 4th IEEE International Conference on Universal Personal Communications
Proceedings of ICUPC '95 - 4th IEEE International Conference on Universal Personal CommunicationsIF0
PREAI
分享收藏Approaching the computational color constancy as a classification problem through deep learningPATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏
An Emulated Test Framework for Service Discovery and MANET Research Based on ns-3基于ns-3的服务发现和MANET研究的仿真测试框架
PREAI
分享收藏
查看更多内容