Learning-based high-quality image recovery from 1D signals obtained by single-pixel imaging

计算机科学 人工智能 采样(信号处理) 像素 计算机视觉 图像质量 迭代重建 生成对抗网络 压缩传感 过采样 模式识别(心理学)
作者
Xiaogang Wang,Angang Zhu,Shanshan Lin,Bijun Xu
出处
期刊:Optics Communications [Elsevier BV]
卷期号:: 128571-128571
标识
DOI:10.1016/j.optcom.2022.128571
摘要

As an innovative and computational imaging technique, it is critical for single-pixel imaging (SPI) to achieve a high reconstruction quality. However, the reconstruction image quality in conventional SPI is heavily dependent on the sampling rate. In this work, we present a learning-based SPI approach for high-quality image reconstruction under a low sampling rate. A bucket detector included in our optical setup is used to collect the one-dimensional (1D) signals reflected from a two-dimensional (2D) object and an end-to-end generative adversarial network (EGAN) which is pre-trained with simulated data is utilized to implement the reconstruction of the object. The results show that the proposed approach is able to produce high quality approximations of 2D images from optically collected 1D bucket signals at a very low sampling ratio. It can also be shown a better performance can be achieved by compared with previous studies on the same dataset, such as conventional SPI, compressive-sensing ghost imaging (CSGI) and U-net-based SPI approaches. • A learning-based single-pixel imaging (SPI) for high-quality image reconstruction under a very low sampling rate is proposed. • The implementation of efficient image reconstruction is performed by an end-to-end generative adversarial network. • The performance of the proposed SPI is demonstrated under different sampling rate conditions using both simulated and optical experiments. • Compared with other techniques, the pre-trained EGAN can output higher quality approximations of object images.
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
林钟完成签到,获得积分10
刚刚
在水一方应助会飞的鱼采纳,获得10
刚刚
zzqblue发布了新的文献求助10
3秒前
4秒前
zjy完成签到,获得积分10
5秒前
科研通AI5应助xn201120采纳,获得10
5秒前
量子星尘发布了新的文献求助10
6秒前
7秒前
zommen驳回了dodo应助
7秒前
快乐的青柏完成签到,获得积分10
8秒前
peiter发布了新的文献求助10
8秒前
lzb完成签到,获得积分10
10秒前
落寞依玉完成签到,获得积分20
11秒前
研友_VZG7GZ应助深海敢敢采纳,获得10
12秒前
烟花应助zzqblue采纳,获得10
12秒前
科研通AI5应助QQ采纳,获得10
13秒前
会飞的鱼发布了新的文献求助10
13秒前
14秒前
18秒前
睿123456完成签到,获得积分10
19秒前
23秒前
诚心仙人掌完成签到,获得积分10
24秒前
顺利秋灵完成签到,获得积分10
24秒前
7t完成签到 ,获得积分10
27秒前
27秒前
27秒前
田様应助渡川采纳,获得10
29秒前
会飞的鱼完成签到,获得积分10
29秒前
善学以致用应助二丙采纳,获得10
30秒前
31秒前
松鼠桂鱼发布了新的文献求助10
31秒前
32秒前
33秒前
ChatGPT发布了新的文献求助10
34秒前
dramarama720发布了新的文献求助10
35秒前
35秒前
37秒前
学术蟑螂完成签到,获得积分10
38秒前
38秒前
39秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 700
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
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 3976267
求助须知:如何正确求助?哪些是违规求助? 3520472
关于积分的说明 11203425
捐赠科研通 3257089
什么是DOI,文献DOI怎么找? 1798589
邀请新用户注册赠送积分活动 877785
科研通“疑难数据库(出版商)”最低求助积分说明 806523