DB-GAN: A Low Contrast Image Enhancer Based on NIR-RGB Fusion

Linruize Tang, Longbin Yan, Jie Chen

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

RGB images captured under haze or over-/under-exposure conditions frequently have low contrast and lack of detail. Due to the limited information in the original image, the majority of enhancement techniques that rely solely on visible information fail to restore the original image satisfactorily. This emphasizes the need for information beyond the visible spectrum. In this paper, we formulate the low contrast image enhancement problem based on near-infrared (NIR)-RGB fusion. A Dual-Branch Generative Adversarial Network (DB-GAN) is designed based on the specific characteristics of NIR-RGB fusion problem. To be specific, with the guidance of the two discriminators that respectively extract information from RGB and NIR images, a U-net based generator generates informative, high-quality fused images. In addition, we create an NIR-RGB dataset with over 1300 aligned image pairs for training the network. Quantitative and qualitative experimental results show the superior performance of our proposed framework.

源语言英语
主期刊名2022 IEEE 32nd International Workshop on Machine Learning for Signal Processing, MLSP 2022
出版商IEEE Computer Society
ISBN(电子版)9781665485470
DOI
出版状态已出版 - 2022
活动32nd IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2022 - Xi'an, 中国
期限: 22 8月 202225 8月 2022

出版系列

姓名IEEE International Workshop on Machine Learning for Signal Processing, MLSP
2022-August
ISSN(印刷版)2161-0363
ISSN(电子版)2161-0371

会议

会议32nd IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2022
国家/地区中国
Xi'an
时期22/08/2225/08/22

指纹

探究 'DB-GAN: A Low Contrast Image Enhancer Based on NIR-RGB Fusion' 的科研主题。它们共同构成独一无二的指纹。

引用此