Deep Learning Reconstruction for Single Pixel Imaging with Generative Adversarial Networks

鉴别器 计算机科学 人工智能 像素 深度学习 迭代重建 生成对抗网络 模式识别(心理学) 图像分辨率 灵敏度(控制系统) 计算机视觉 探测器 电子工程 电信 工程类
作者
Baturalp Güven,Alper Güngör,M. Umut Bahçeci,Tolga Çukur
标识
DOI:10.1109/icip49359.2023.10223149
摘要

Single pixel imaging (SPI) enables high-resolution imaging through multiple coded measurements based on low-resolution snapshots. An inverse problem can then be solved to reconstruct a high-resolution image given the coded measurements. There has been recent interest in adoption of deep neural networks in SPI reconstruction. However, existing methods are commonly trained with pixel-wise loss terms such as the ℓ 1 -norm loss, which can result in spatial blurring and poor sensitivity to structural details. In this study, we propose a novel approach for deep SPI reconstruction based on an unrolled conditional generative adversarial network (cGAN) model. The generator estimates the high-resolution image using coded low-resolution measurements by iterating across a cascade of denoising and data-consistency modules. Meanwhile, the discriminator distinguishes real versus synthesized high-resolution images. The architecture is trained end-to-end via a combined pixel-wise and adversarial loss to enhance sensitivity to structural details. The proposed method is demonstrated against existing SPI reconstruction methods, and ablation studies are performed to demonstrate the individual model components. The proposed method outperforms competing methods in terms of both quantitative metrics and visual quality.
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
刚刚
1秒前
香蕉觅云应助吴大打采纳,获得10
1秒前
1秒前
1秒前
风语完成签到,获得积分10
1秒前
笨笨善若发布了新的文献求助10
2秒前
2秒前
汉堡包应助musejie采纳,获得10
2秒前
1337003319发布了新的文献求助30
2秒前
dild发布了新的文献求助10
3秒前
4秒前
爆米花应助wang123采纳,获得10
4秒前
abcdefg发布了新的文献求助10
4秒前
5秒前
瘦瘦的草丛完成签到,获得积分10
5秒前
GQC发布了新的文献求助30
5秒前
5秒前
风语发布了新的文献求助20
6秒前
桔梗发布了新的文献求助10
6秒前
7秒前
我是老大应助艾妮吗采纳,获得10
7秒前
直率雨柏完成签到,获得积分20
7秒前
7秒前
热心市民小红花应助su采纳,获得10
7秒前
韶雁开发布了新的文献求助10
8秒前
8秒前
吃狼的羊发布了新的文献求助30
8秒前
白白白发布了新的文献求助20
8秒前
pluto应助Wwt采纳,获得10
8秒前
莫默发布了新的文献求助10
9秒前
9秒前
对方正在输入完成签到,获得积分10
10秒前
Rick发布了新的文献求助10
11秒前
11秒前
12秒前
12秒前
豆子发布了新的文献求助50
13秒前
13秒前
13秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 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
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 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 3971277
求助须知:如何正确求助?哪些是违规求助? 3515939
关于积分的说明 11180280
捐赠科研通 3251061
什么是DOI,文献DOI怎么找? 1795664
邀请新用户注册赠送积分活动 875937
科研通“疑难数据库(出版商)”最低求助积分说明 805209