Benchmarking Low-Light Image Enhancement and Beyond

人工智能 计算机科学 计算机视觉 标杆管理 面子(社会学概念) 目标检测 人脸检测 机器视觉 面部识别系统 透视图(图形) 模式识别(心理学) 营销 业务 社会科学 社会学
作者
Jiaying Liu,Dejia Xu,Wenhan Yang,Minhao Fan,Haofeng Huang
出处
期刊:International Journal of Computer Vision [Springer Science+Business Media]
卷期号:129 (4): 1153-1184 被引量:111
标识
DOI:10.1007/s11263-020-01418-8
摘要

In this paper, we present a systematic review and evaluation of existing single-image low-light enhancement algorithms. Besides the commonly used low-level vision oriented evaluations, we additionally consider measuring machine vision performance in the low-light condition via face detection task to explore the potential of joint optimization of high-level and low-level vision enhancement. To this end, we first propose a large-scale low-light image dataset serving both low/high-level vision with diversified scenes and contents as well as complex degradation in real scenarios, called Vision Enhancement in the LOw-Light condition (VE-LOL). Beyond paired low/normal-light images without annotations, we additionally include the analysis resource related to human, i.e. face images in the low-light condition with annotated face bounding boxes. Then, efforts are made on benchmarking from the perspective of both human and machine visions. A rich variety of criteria is used for the low-level vision evaluation, including full-reference, no-reference, and semantic similarity metrics. We also measure the effects of the low-light enhancement on face detection in the low-light condition. State-of-the-art face detection methods are used in the evaluation. Furthermore, with the rich material of VE-LOL, we explore the novel problem of joint low-light enhancement and face detection. We develop an enhanced face detector to apply low-light enhancement and face detection jointly. The features extracted by the enhancement module are fed to the successive layer with the same resolution of the detection module. Thus, these features are intertwined together to unitedly learn useful information across two phases, i.e. enhancement and detection. Experiments on VE-LOL provide a comparison of state-of-the-art low-light enhancement algorithms, point out their limitations, and suggest promising future directions. Our dataset has supported the Track “Face Detection in Low Light Conditions” of CVPR UG2+ Challenge (2019–2020) ( http://cvpr2020.ug2challenge.org/ ).
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

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
Geodada完成签到,获得积分10
刚刚
小马甲应助和谐的玉米采纳,获得10
1秒前
顺顺顺完成签到,获得积分10
1秒前
鹿书雪发布了新的文献求助10
1秒前
2秒前
3秒前
Orange应助好运采纳,获得10
3秒前
4秒前
Orange应助张必雨采纳,获得30
5秒前
Ava应助TANG采纳,获得10
6秒前
6秒前
歆琉发布了新的文献求助10
7秒前
8秒前
冬虫草发布了新的文献求助20
8秒前
8秒前
量子星尘发布了新的文献求助10
8秒前
9秒前
清秀凉面完成签到 ,获得积分10
9秒前
丁丁很顺利完成签到,获得积分10
10秒前
10秒前
wying发布了新的文献求助30
10秒前
英俊的铭应助犹豫书瑶采纳,获得10
10秒前
10秒前
鱼叔发布了新的文献求助10
11秒前
11秒前
上官若男应助太叔凡儿采纳,获得10
11秒前
研友_08ozgZ完成签到,获得积分10
12秒前
G1997完成签到 ,获得积分10
12秒前
我没那么郝完成签到,获得积分10
13秒前
14秒前
倪小呆发布了新的文献求助10
14秒前
相信发布了新的文献求助10
14秒前
希望天下0贩的0应助CC采纳,获得10
15秒前
15秒前
16秒前
情怀应助壮观不斜采纳,获得10
16秒前
a怪完成签到,获得积分10
17秒前
唐诗蕾完成签到,获得积分10
17秒前
LLLLL关注了科研通微信公众号
17秒前
张必雨完成签到,获得积分10
17秒前
高分求助中
【提示信息,请勿应助】关于scihub 10000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Social Research Methods (4th Edition) by Maggie Walter (2019) 2390
A new approach to the extrapolation of accelerated life test data 1000
北师大毕业论文 基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 390
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
Robot-supported joining of reinforcement textiles with one-sided sewing heads 360
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 4009979
求助须知:如何正确求助?哪些是违规求助? 3550041
关于积分的说明 11304472
捐赠科研通 3284482
什么是DOI,文献DOI怎么找? 1810684
邀请新用户注册赠送积分活动 886503
科研通“疑难数据库(出版商)”最低求助积分说明 811412