Illumination-aware divide-and-conquer network for improperly-exposed image enhancement

分而治之算法 计算机科学 图像(数学) 人工智能 模式识别(心理学) 计算机视觉 算法
作者
Fenggang Han,Kan Chang,Guiqing Li,Mingyang Ling,Mengyuan Huang,Zan Gao
出处
期刊:Neural Networks [Elsevier BV]
卷期号:: 106733-106733
标识
DOI:10.1016/j.neunet.2024.106733
摘要

Improperly-exposed images often have unsatisfactory visual characteristics like inadequate illumination, low contrast, and the loss of small structures and details. The mapping relationship from an improperly-exposed condition to a well-exposed one may vary significantly due to the presence of multiple exposure conditions. Consequently, the enhancement methods that do not pay specific attention to this issue tend to yield inconsistent results when applied to the same scene under different exposure conditions. In order to obtain consistent enhancement results for various exposures while restoring rich details, we propose an illumination-aware divide-and-conquer network (IDNet). Specifically, to address the challenge of directly learning a sophisticated nonlinear mapping from an improperly-exposed condition to a well-exposed one, we utilize the discrete wavelet transform (DWT) to decompose the image into the low-frequency (LF) component, which primarily captures brightness and contrast, and the high-frequency (HF) components that depict fine-scale structures. To mitigate the inconsistency in correction across various exposures, we extract a conditional feature from the input that represents illumination-related global information. This feature is then utilized to modulate the dynamic convolution weights, enabling precise correction of the LF component. Furthermore, as the co-located positions of LF and HF components are highly correlated, we create a mask to distill useful knowledge from the corrected LF component, and integrate it into the HF component to support the restoration of fine-scale details. Extensive experimental results demonstrate that the proposed IDNet is superior to several state-of-the-art enhancement methods on two datasets with multiple exposures.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
Vincy完成签到 ,获得积分10
刚刚
美丽的雪珍完成签到,获得积分10
刚刚
gf完成签到,获得积分10
刚刚
Queen完成签到,获得积分10
刚刚
羊羊发布了新的文献求助10
刚刚
刚刚
HouKk完成签到,获得积分20
刚刚
刚刚
zhang完成签到 ,获得积分10
1秒前
1秒前
小马发布了新的文献求助10
2秒前
2秒前
2秒前
fvsjbc完成签到,获得积分10
3秒前
太阳完成签到,获得积分10
3秒前
小马甲的应助被轩逸采纳,获得10
4秒前
和光同尘完成签到,获得积分10
4秒前
黄橙橙完成签到 ,获得积分10
4秒前
黑米粥发布了新的文献求助200
5秒前
5秒前
研友_Lpa2On完成签到,获得积分10
5秒前
ZD发布了新的文献求助10
5秒前
5秒前
gxiaxia发布了新的文献求助10
5秒前
半梦发布了新的文献求助10
5秒前
科研通AI6.2的应助被Tracy采纳,获得10
6秒前
Tammm完成签到,获得积分10
6秒前
null的应助被心系天下采纳,获得10
6秒前
v0id的应助被凤凰院凶真采纳,获得10
6秒前
酷酷酷完成签到,获得积分10
6秒前
orixero的应助被gouerde采纳,获得10
6秒前
7秒前
背后的谷南完成签到,获得积分10
7秒前
DDDDn完成签到 ,获得积分10
7秒前
zzzrrr完成签到,获得积分10
7秒前
无辜小花卷完成签到,获得积分10
8秒前
一一发布了新的文献求助10
8秒前
MYH发布了新的文献求助10
8秒前
史书发布了新的文献求助10
8秒前
8秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1500
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology)求助 1000
Encyclopedia of Modern Artificial Intelligence 1000
John McDowells Bildungstheorie 800
Analyses de reconnaissances de dettes passées devant les échevins d'Ypres (1249-1291) 600
Synthesis, Application and Future Perspectives of Smart Nano-materials - Part 1 400
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8152794
求助须知:如何正确求助?哪些是违规求助? 9549444
关于积分的说明 21693226
捐赠科研通 7741107
什么是DOI,文献DOI怎么找? 3425348
关于科研通互助平台的介绍 2550424
邀请新用户注册赠送积分活动 2468928