An Optimization-Driven Network With Knowledge Prior Injection for HSI Denoising

计算机科学 可解释性 增采样 高斯噪声 人工智能 降噪 噪音(视频) 脉冲噪声 稳健性(进化) 卷积神经网络 噪声测量 模式识别(心理学) 计算机视觉 图像(数学) 生物化学 基因 像素 化学
作者
Yajie Li,Jie Li,Jiang He,Xinxin Liu,Qiangqiang Yuan
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing [Institute of Electrical and Electronics Engineers]
卷期号:61: 1-17 被引量:6
标识
DOI:10.1109/tgrs.2023.3329887
摘要

Due to the limitations of sensor hardware devices, the hyperspectral image (HSI) often suffers from various types of noise, such as Gaussian noise, impulse noise, stripe noise, and deadlines, which can significantly degrade their quality. Although many data-driven methods have been proposed to deal with complex noise, few of them consider the structural characteristics of noise. This not only leads to a lack of interpretability but also results in poor performance when dealing with structural noise in practical applications. To address this issue, this article proposes KPInet, a convolutional neural network (CNN) driven by the structural knowledge of noise for HSI denoising. First and foremost, the knowledge optimization-driven module (KODM) utilizes the deep unrolling method to unfold a total variation (TV) algorithm that considers the structural characteristics of noise. This approach improves the network’s interpretability and results in better performance on structural noise, while maintaining the effect of removing Gaussian noise. Second, the statistical feature injection module (SFIM) extracts more features by utilizing spectral gradients, medians, and means of the HSI. Third, the multiscale degradation guidance module (MDGM) utilizes a dual-stream decoder with a low-resolution upsampling guidance branch to better distinguish the real structure and noise structure in the HSI. Experimental results on simulated and real datasets indicate that the approach achieves favorable denoising performance, as evidenced by both quantitative evaluation metrics and visual results. Furthermore, it also demonstrates the robustness and generalization capacity of the proposed KPInet.
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
汉堡包应助啦啦啦啦啦采纳,获得10
1秒前
ice7完成签到,获得积分10
1秒前
if完成签到 ,获得积分10
1秒前
彭于彦祖应助阿黎采纳,获得30
1秒前
孤独的珩发布了新的文献求助10
2秒前
好运来发布了新的文献求助10
2秒前
大模型应助謓言采纳,获得10
2秒前
3秒前
bkagyin应助niu采纳,获得10
3秒前
温柔的沉鱼完成签到,获得积分10
3秒前
小白发布了新的文献求助10
4秒前
4秒前
NexusExplorer应助自然香旋采纳,获得30
4秒前
anna1992完成签到,获得积分10
5秒前
满意溪流发布了新的文献求助10
5秒前
6秒前
研友_VZGvVn完成签到,获得积分10
6秒前
Jasper应助zhengmin采纳,获得10
6秒前
KBYer完成签到,获得积分10
6秒前
可耐的老虎完成签到,获得积分20
6秒前
7秒前
zwy完成签到,获得积分10
7秒前
吱吱吱完成签到 ,获得积分10
7秒前
8秒前
anna1992发布了新的文献求助10
8秒前
捞鱼完成签到,获得积分10
8秒前
8秒前
8秒前
土狗完成签到,获得积分10
9秒前
零零零零完成签到,获得积分10
9秒前
REBACK完成签到,获得积分20
9秒前
9秒前
9秒前
发飙的牛发布了新的文献求助10
9秒前
9秒前
水木应助Ilan采纳,获得10
10秒前
10秒前
11秒前
英吉利25发布了新的文献求助10
11秒前
飞云发布了新的文献求助10
11秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
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 3969335
求助须知:如何正确求助?哪些是违规求助? 3514162
关于积分的说明 11172430
捐赠科研通 3249456
什么是DOI,文献DOI怎么找? 1794853
邀请新用户注册赠送积分活动 875437
科研通“疑难数据库(出版商)”最低求助积分说明 804809