Multi-Branch and Progressive Network for Low-Light Image Enhancement

计算机科学 人工智能 像素 计算机视觉 水准点(测量) 卷积神经网络 亮度 过程(计算) 模式识别(心理学) 光学 物理 大地测量学 地理 操作系统
作者
Kaibing Zhang,Cheng Yuan,Jie Li,Xinbo Gao,Minqi Li
出处
期刊:IEEE transactions on image processing [Institute of Electrical and Electronics Engineers]
卷期号:32: 2295-2308 被引量:18
标识
DOI:10.1109/tip.2023.3266171
摘要

Low-light images incur several complicated degradation factors such as poor brightness, low contrast, color degradation, and noise. Most previous deep learning-based approaches, however, only learn the mapping relationship of single channel between the input low-light images and the expected normal-light images, which is insufficient enough to deal with low-light images captured under uncertain imaging environment. Moreover, too deeper network architecture is not conducive to recover low-light images due to extremely low values in pixels. To surmount aforementioned issues, in this paper we propose a novel multi-branch and progressive network (MBPNet) for low-light image enhancement. To be more specific, the proposed MBPNet is comprised of four different branches which build the mapping relationship at different scales. The followed fusion is performed on the outputs obtained from four different branches for the final enhanced image. Furthermore, to better handle the difficulty of delivering structural information of low-light images with low values in pixels, a progressive enhancement strategy is applied in the proposed method, where four convolutional long short-term memory networks (LSTM) are embedded in four branches and an recurrent network architecture is developed to iteratively perform the enhancement process. In addition, a joint loss function consisting of the pixel loss, the multi-scale perceptual loss, the adversarial loss, the gradient loss, and the color loss is framed to optimize the model parameters. To evaluate the effectiveness of proposed MBPNet, three popularly used benchmark databases are used for both quantitative and qualitative assessments. The experimental results confirm that the proposed MBPNet obviously outperforms other state-of-the-art approaches in terms of quantitative and qualitative results. The code will be available at https://github.com/kbzhang0505/MBPNet.
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
大幅提高文件上传限制,最高150M (2024-4-1)

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
明亮的涵山完成签到,获得积分10
刚刚
科研通AI2S应助zhuzhihao采纳,获得10
1秒前
有余发布了新的文献求助20
1秒前
和和完成签到,获得积分10
1秒前
3秒前
冰淇淋完成签到,获得积分10
3秒前
4秒前
4秒前
喝水长肉的小胖子完成签到 ,获得积分20
5秒前
鱼鱼发布了新的文献求助30
5秒前
5秒前
平常的可乐完成签到 ,获得积分10
6秒前
10秒前
玖梦发布了新的文献求助10
10秒前
善学以致用应助东方既白采纳,获得10
10秒前
家湘完成签到,获得积分20
11秒前
12秒前
符雁完成签到,获得积分20
12秒前
Frank完成签到,获得积分10
14秒前
15秒前
16秒前
znchick发布了新的文献求助10
16秒前
顺利的耶完成签到 ,获得积分10
17秒前
符雁发布了新的文献求助10
17秒前
17秒前
若有光完成签到,获得积分20
18秒前
烟花应助若楼兰不死采纳,获得10
18秒前
123发布了新的文献求助10
18秒前
若有光发布了新的文献求助10
20秒前
21秒前
22秒前
Elena发布了新的文献求助10
22秒前
22秒前
22秒前
hhhhhhh完成签到,获得积分10
22秒前
NexusExplorer应助Lily采纳,获得10
23秒前
啥也搞不懂完成签到 ,获得积分10
24秒前
科研通AI2S应助科研小白采纳,获得10
24秒前
华仔应助chenlihuan采纳,获得10
24秒前
Nn完成签到,获得积分10
25秒前
高分求助中
The Young builders of New china : the visit of the delegation of the WFDY to the Chinese People's Republic 1000
юрские динозавры восточного забайкалья 800
English Wealden Fossils 700
Chen Hansheng: China’s Last Romantic Revolutionary 500
COSMETIC DERMATOLOGY & SKINCARE PRACTICE 388
Case Research: The Case Writing Process 300
Global Geological Record of Lake Basins 300
热门求助领域 (近24小时)
化学 医学 生物 材料科学 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 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3141883
求助须知:如何正确求助?哪些是违规求助? 2792846
关于积分的说明 7804392
捐赠科研通 2449137
什么是DOI,文献DOI怎么找? 1303086
科研通“疑难数据库(出版商)”最低求助积分说明 626769
版权声明 601265