1 重庆大学 光电技术与系统教育部重点实验室,重庆4033
2 北京空间机电研究所,北京100094
现有大多遥感图像超分辨率方法,无法充分挖掘图像中混合尺度的自相似性信息和跨尺度区域间的关联信息,且忽略了频率域对感知图像高频信息的能力。针对这一问题,本文提出了一种空间自适应及频率融合网络(Spatial Adaptation and Frequency Fusion Network, SAF2Net)。SAF2Net首先引入一种混合尺度空间自适应特征调制模块,采用类似于特征金字塔的方式获取不同尺度下的判别特征,丰富多尺度特征的表达能力。随后,设计了一个全局多尺度感受野选择块,挖掘跨尺度区域间的关联特征。在此基础上,引入空间自适应选择块和频率分离选择块,融合空间-频率互补信息以增强局部特征,提高模型对图像高频内容的建模能力。在两个公开遥感图像数据集上进行多组实验,SAF2Net获得的定量评价指标结果均优于其他对比方法。以UCMerced数据集3倍超分辨率为例,本文方法相较于次优方法HAUNet,PSNR和SSIM分别提升了0.11 dB和0.003 3;在主观视觉质量方面,SAF2Net能够恢复出更多清晰的纹理细节。实验结果表明,本文所提出的SAF2Net能够从两个不同的角度挖掘混合尺度全局信息,并有效融合空间-频率互补特征,在遥感图像超分辨率任务中表现出具有竞争力的重建性能。
遥感图像 超分辨率 混合尺度特征 空频互补信息 remote sensing image super resolution hybrid-scale features space-frequency complementary information
1 越秀(中国)交通基建投资有限公司,广东 广州 510000
2 交通运输部科学研究院,北京 100029
3 越秀(湖北)高速公路有限公司,湖北 武汉 430000
4 北京中交国通智能交通系统技术有限公司产品事业部,北京 100088
在夜间驾驶场景中,光照不足和雾气使得图像质量急剧下降,给驾驶员和自动驾驶系统带来了严峻挑战。针对这一问题,提出了一种面向夜间驾驶场景的新颖图像去雾算法。该算法不依赖于传统的先验理论,而是从重建的角度出发,将夜间雾图像视为雾层和背景层的叠加,并提出一种无须借助物理成像模型的轻量级超分辨率重建去雾网络。通过引入基于空洞卷积的雾特征提取网络和以雾特征图为监督信息的注意力机制模块,去雾网络能够在保留图像细节的同时有效地去除雾层,生成清晰、对比度高的图像。在两个夜间雾图数据集上,与其他5种先进去雾方法进行了比较实验。实验表明,超分辨率重建去雾网络的去雾结果与其他夜间去雾模型相比均更优。消融实验结果证明了基于雾特征监督的注意力模块可以显著提升网络的去雾能力。研究为解决夜间驾驶场景下的图像质量问题提供了新的思路和方法,对提高驾驶安全性和自动驾驶系统的可靠性具有重要意义。
夜间驾驶 夜间图像去雾 超分辨率重建 空洞卷积 雾特征图 注意力机制 激光与光电子学进展
2025, 62(12): 1237007
1 长春理工大学空间光电技术研究所,吉林 长春 130022
2 长春理工大学光电工程学院,吉林 长春 130022
针对基于数字微镜器件(DMD)的红外超分辨率系统的简化设计和成像质量提升问题,深入研究了基于DMD的红外超分辨率成像理论,提出系统简化设计思路,并获取了简化后系统所对应的点扩散函数。在此基础上,构建了基于T-L(TVAL3-Lucy Richardson)的分块超分辨率复原像质优化模型,开发了一种结合超分辨率重建、图像去模糊复原以及图像去噪的像质优化算法。对于简化设计后系统拍摄的降质图像,使用该算法成功实现了图像分辨率与清晰度的协同提升,有效改善了成像质量。对于简化设计系统,相较于传统的图像复原算法,采用基于T-L的分块超分辨率复原算法实现了2倍超分辨率成像。在仿真成像中,峰值信噪比(PSNR)的平均提升幅度为78.0%,结构相似度(SSIM)的平均提升幅度为71.0%;在室内成像实验中,PSNR提升了58.5%,SSIM提升了57.1%。在室外场景成像实验中,与简化设计系统拍摄的退化图像相比,所提算法实现了有效的细节复现。基于光学系统简化设计的红外超分辨率成像方法能够有效校正由光学像差引起的图像退化,同时提升图像的分辨率和清晰度,这不仅减少了光学元件的数量,降低了系统的制造成本,还提高了能量透过率并增强了系统的成像性能。此外,简化后的系统结构更加紧凑,便于集成和部署,这对于设备轻便性和成本有严格要求的应用场景尤为重要,如便携式安防监控、空间遥感、野外探测等。
数字微镜器件 红外成像 简化设计 超分辨率复原 光学学报
2025, 45(11): 1111002
Author Affiliations
Abstract
1 Wuhan Forth Hospital, Wuhan, Hubei 430030, P. R. China
2 Britton Chance Center for Biomedical Photonics-MoE Key Laboratory for Biomedical Photonics, Advanced Biomedical Imaging Facility-Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan, Hubei 430074, P. R. China
3 Wuhan Jinyintan Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei 430023, P. R. China
The rapid development of super-resolution microscopy has made it possible to observe subcellular structures and dynamic behaviors in living cells with nanoscale spatial resolution, greatly advancing progress in life sciences. As hardware technology continues to evolve, the availability of new fluorescent probes with superior performance is becoming increasingly important. In recent years, fluorescent nanoprobes (FNPs) have emerged as highly promising fluorescent probes for bioimaging due to their high brightness and excellent photostability. This paper focuses on the development and applications of FNPs as probes for live-cell super-resolution imaging. It provides an overview of different super-resolution methods, discusses the performance requirements for FNPs in these methods, and reviews the latest applications of FNPs in the super-resolution imaging of living cells. Finally, it addresses the challenges and future outlook in this field.
Super-resolution imaging fluorescent nanoprobe live-cell imaging Journal of Innovative Optical Health Sciences
2025, 18(3): 2530001
Author Affiliations
Abstract
Guangdong Provincial Key Laboratory of Advanced Biomaterials, Department of Biomedical Engineering, Southern University of Science and Technology, Shenzhen 518055, Guangdong, P. R. China
Self-labeling protein (SLP) tags, such as HaloTag, have gained considerable interest as advanced tools for live cell labeling. However, the chloroalkane-based substrates that can be directly used for protein labeling are limited. Here, we report two bioorthogonal small molecule linkers, chloroalkane-tetrazine (CA-Tz) and chloroalkane-azide (CA-N3), which can penetrate cell membranes and facilitate click chemistry-based labeling in live cells. We compare their labeling capability using two clickable silicon rhodamine dyes (SiR-PEG3-TCO and SiR-PEG4-DBCO). Confocal imaging results demonstrate that using CA-Tz and SiR-PEG3-TCO dye exhibits superior intracellular labeling with low nonspecific signals. We subsequently compared the photostability of SiR dyes with that of green fluorescent proteins (mEmerald). Total internal reflection fluorescence (TIRF) imaging indicates that SiR dyes exhibit superior photostability under identical excitation conditions, making them suitable for long-term cell imaging. Furthermore, SiR dyes labeling also shows high structure retention for the fourth-order super-resolution optical fluctuation imaging (SOFI) compared to fluorescent proteins. This study presents clickable HaloTag linkers as effective tools for live cell labeling and imaging, highlighting the high-quality labeling of chloroalkane linkers and clickable dyes for live cell imaging.
Small molecular linkers live cell labeling super-resolution imaging Journal of Innovative Optical Health Sciences
2025, 18(3): 2441003
重庆邮电大学通信与信息工程学院,重庆 400065
针对遥感图像分辨率低于传统图像且受到复杂退化过程的影响,传统生成对抗网络会生成不真实的特征,导致出现伪影和大量虚假、尖锐的边缘等问题。提出了一种基于边缘提取和增强的遥感图像超分辨率网络EEEGAN。该网络首先采用了边缘提取算法TEED以提取图像边缘。其次设计了双重注意力机制TAM以获取图像丰富的空间和通道信息。同时提出了一种基本块RRDJB以扩大模型的处理能力,并引入下采样网络SPD进一步减少细节损失。在RSOD数据集的基础上,根据退化模型对数据集进行了不同的数据退化处理。结果表明文中所提出的模型,在不同的退化条件下,与目前的主流图像超分辨率模型相比,指标均有所提升。文中的方法相对于真实增强图像超分辨率对抗网络在退化条件I的样本上SSIM提升了0.034,PSNR提升了1.329 8 dB。图像在重建后,边缘细节的视觉效果更好。并且,在DIOR和HRSC2016数据集上均取得了良好的泛化效果。
超分辨率 遥感图像 边缘提取 注意力机制 生成对抗网络 super resolution remote sensing image edge extraction attention mechanism generative adversarial network

1 嘉兴大学信息科学与工程学院,浙江 嘉兴 314000
2 浙江工业大学计算机科学与技术学院,浙江 杭州 310000
3 宁波大学信息科学与工程学院,浙江 宁波 315000
Experimental results demonstrate that ADAN significantly outperforms state-of-the-art algorithms on multiple public remote sensing datasets in terms of quantitative metrics (e.g., PSNR and SSIM) and visual quality, validating its effectiveness and superiority. The main contributions are as follows: 1) Proposing a novel method, ADAN, tailored for remote sensing image super-resolution tasks; 2) Designing parallel channel and spatial feature extraction modules along with a gated convolution module to comprehensively explore features across channel, spatial, and convolutional dimensions; 3) Introducing a multi-scale feed-forward network (MSFFN) to effectively explore potential scale relationships and enhance global representation capabilities; 4) Experimentally validating the superior performance of ADAN in remote sensing image super-resolution reconstruction. This research provides new insights and technical pathways for remote sensing image super-resolution reconstruction.
双域注意力 Transformer 注意力机制 遥感图像 超分辨率 dual-domain attention transformer attention mechanism remote sensing images super-resolution
1 西南科技大学制造科学与工程学院,四川 绵阳 621010
2 西南科技大学信息工程学院,四川 绵阳 621010
3 西南科技大学极端条件物性联合实验室,四川 绵阳 621010
双焦点器件在高分辨率显微镜成像、激光切割等领域中有着广泛的应用。现有双焦点器件存在结构复杂、加工难度大等问题。提出了一种基于空间光调制器的远场超分辨双焦点聚焦光场构建方法。基于光学超振荡原理,结合二进制粒子群优化算法和角谱衍射理论,设计了两个具有不同焦距的单焦点聚焦二值相位超振荡掩模。通过布尔逻辑“与”运算,得到双焦点聚焦二值相位超振荡掩模。采用该方法,针对波长λ=632.8 nm的圆偏振光,设计了焦距分别为280000λ(177184 μm)和300000λ(189840 μm)的双焦点聚焦超振荡掩模。实验中,将超振荡掩模载入空间光调制器,成功实现了远场超分辨双焦点聚焦。实验结果与理论计算结果高度一致:两个聚焦焦斑的横向峰值半峰全宽分别为20.333 μm和20.353 μm,均低于对应的衍射极限,同时保持了较低的旁瓣。该方法具有易于实现、设计焦距可控等优点,在光通信、生物医学成像等领域中具有广阔的应用前景。
远场超分辨 双焦点聚焦 光学超振荡 空间光调制器 角谱衍射 中国激光
2025, 52(11): 1101005

Author Affiliations
Abstract
University of Kassel, Faculty of Electrical Engineering and Computer Science, Measurement Technology Group, Kassel, Germany
Microsphere and microcylinder-assisted microscopy (MAM) has grown steadily over the last decade and is still an intensively studied optical far-field imaging technique that promises to overcome the fundamental lateral resolution limit of microscopy. However, the physical effects leading to resolution enhancement are still frequently debated. In addition, various configurations of MAM operating in transmission mode as well as reflection mode are examined, and the results are sometimes generalized. We present a rigorous simulation model of MAM and introduce a way to quantify the resolution enhancement. The lateral resolution is compared for microscope arrangements in reflection and transmission modes. Furthermore, we discuss different physical effects with respect to their contribution to resolution enhancement. The results indicate that the effects impacting the resolution in MAM strongly depend on the arrangement of the microscope and the measurement object. As a highlight, we outline that evanescent waves in combination with whispering gallery modes also improve the imaging capabilities, enabling super-resolution under certain circumstances. This result is contrary to the conclusions drawn from previous studies, where phase objects have been analyzed, and thus further emphasizes the complexity of the physical mechanisms underlying MAM.
microsphere-assisted microscopy resolution enhancement resolution limit electromagnetic modeling super-resolution whispering gallery mode Advanced Photonics Nexus
2025, 4(4): 046003
大连民族大学 计算机科学与工程学院,辽宁 大连 116000
光场(LF)图像是一种能够记录光线方向和强度的图像,它可以提供丰富的视觉信息。近期,众多基于卷积神经网络(CNN)或Transformer的网络结构在光场图像处理任务中展现了巨大潜力。然而,由于光场图像在空间与角度之间的角度采样稀疏性,充分提取特征信息并挖掘其空间角度相关性成为实现光场图像超分辨率的重要挑战。针对这个问题,提出一种新的网络架构,以更好地重建高分辨率光场图像:经过浅特征提取部分逐渐提取视角内的特征;设计了具有通道注意力的多尺度特征提取模块,以有效融合在光场子空间上学到的特征;通过极平面图像(EPI)表示,将4D空间角度相关性投影到多个2D EPI平面上,通过全局注意力机制进一步学习和捕捉空间角度之间的复杂关联。这些操作能够更好地整合不同角度视图信息,充分挖掘光场子空间中的特征,并实现全局感受野。研究在5个公开的光场数据集上对所提出的方法进行了全面验证,结果表明,提出的方法在光场图像超分辨率任务中取得了更高的PSNR、SSIM值,生成的高分辨率光场图像具有更高的细节保真度和清晰度。
光场 视差 全局注意力 超分辨率 light field parallax error global attention super resolution