检索结果-内蒙古大学图书馆

Image reconstruction with transformer for mask-based lensless imaging

OPTICS LETTERS 2022年第7期47卷 1843-1846页

作者： Pan, Xiuxi Chen, Xiao Takeyama, Saori Yamaguchi, Masahiro Tokyo Inst Technol Sch Engn Midori Ku 4259-G2-28 Nagatsuta Yokohama Kanagawa 2268502 Japan

A mask-based lensless camera optically encodes the scene with a thin mask and reconstructs the image afterward. The improvement of image reconstruction is one of the most important subjects in lensless imaging. Conventional model-based reconstruction approaches, which leverage knowledge of the physical system, are susceptible to imperfect system modeling. reconstruction with a pure data-driven deep neural network (DNN) avoids this limitation, thereby having potential to provide a better reconstruction quality. However, existing pure DNN reconstruction approaches for lensless imaging do not provide a better result than model-based approaches. We reveal that the multiplexing property in lensless optics makes global features essential in understanding the optically encoded pattern. Additionally, all existing DNN reconstruction approaches apply fully convolutional networks (FCNs) which are not efficient in global feature reasoning. With this analysis, for the first time to the best of our knowledge, a fully connected neural network with a transformer for image reconstruction is proposed. The proposed architecture is better in global feature reasoning, and hence enhances the reconstruction. The superiority of the proposed architecture is verified by comparing with the model-based and FCN-based approaches in an optical experiment. (C) 2022 Optica Publishing Group

关键词： Fresnel zones Image quality Image reconstruction Image sensors Neural networks reconstruction algorithms

来源：评论

学校读者我要写书评

暂无评论

Iterative Approach to Reconstructing Neural Disparity Fields From Light-Field Data

IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING

引用

IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING 2025年 11卷 410-420页

作者： Shi, Ligen Liu, Chang Zhao, Xing Qiu, Jun Capital Normal Univ Sch Math Sci Beijing 100048 Peoples R China Beijing Informat Sci & Technol Univ Coll Comp Sci Beijing 100101 Peoples R China

This study proposes a neural disparity field (NDF) that establishes an implicit, continuous representation of scene disparity based on a neural field and an iterative approach to address the inverse problem of NDF reconstruction from light-field (LF) data. NDF enables seamless and precise characterization of disparity variations in three-dimensional scenes and can discretize disparity at any arbitrary resolution, overcoming the limitations of traditional disparity maps that are prone to sampling errors and interpolation inaccuracies. The proposed NDF network architecture utilizes hash encoding combined with multilayer perceptrons (MLPs) to capture detailed disparities in texture levels, thereby enhancing its ability to represent the geometric information of complex scenes. By leveraging the spatial-angular consistency inherent in the LF data, a differentiable forward model to generate a central view image from the LF data is developed. Based on the forward model, an optimization scheme for the inverse problem of NDF reconstruction using differentiable propagation operators is established. Furthermore, an iterative solution method is adopted to reconstruct the NDF in the optimization scheme, which does not require training datasets and applies to LF data captured by various acquisition methods. Experimental results demonstrate that the proposed method can reconstruct high-quality NDF from LF data. The high-resolution disparity can be effectively recovered by NDF, demonstrating its capability for the implicit, continuous representation of scene disparities.

关键词： Image reconstruction Imaging Depth measurement Estimation Iterative methods Inverse problems Cameras Training reconstruction algorithms Image resolution Neural disparity field disparity estimation light-field

来源：评论

学校读者我要写书评

暂无评论

A Position Sensorless Control Strategy for PMSM Drives With Single-Phase Current Sensor

引用

IEEE TRANSACTIONS ON TRANSPORTATION ELECTRIFICATION 2024年第3期10卷 4678-4688页

作者： Xu, Guanda Xiao, Fei Lian, Chuanqiang Naval Univ Engn Natl Key Lab Electromagnet Energy Wuhan 430033 Peoples R China

This article aims to provide a more credible control scheme or a fault-tolerant control strategy for permanent magnet synchronous motor (PMSM) drives without a position sensor. Considering that, a position sensorless control strategy is proposed using only one phase current sensor. First, the mathematical model of full-order sliding mode observer (FSMO) is established in the stationary reference frame. Second, the coordinate transformation and notch filter (NF) are carried out for the only measurable phase current to calculate the current error information, which is needed by the FSMO. Third, a phase-locked loop (PLL) is employed to estimate the position. The motor parameter variation effect on the position estimation is evaluated. The observer's stability and parameter design method are analyzed through the Lyapunov theory. The proposed method utilizes a single current sensor to reconstruct the three-phase current and position signals, which improves the economy of inverters and provides the possibility of fault-tolerant control with few sensors. Compared with existing methods, it is simpler to implement and does not require changing the power unit structure. Finally, experiments have shown that the proposed method is comparable to the full-current-sensor method in terms of position estimation and control performance. Compared to the traditional method, the proposed method has higher accuracy of position estimation and better dynamic and steady-state control performance.

关键词： Sensorless control Observers Estimation reconstruction algorithms Mathematical models Inverters Synchronous motors Full-order sliding mode observer (FSMO) permanent magnet synchronous motor (PMSM) position sensor sensorless control single-phase current sensor

来源：评论

学校读者我要写书评

暂无评论

PACformer: A Multi-Stage Heterogeneous Convolutional-Vision Transformer for Sparse-View Photoacoustic Tomography Restoration

IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING

引用

IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING 2025年 11卷 377-388页

作者： He, Li Chen, Ruitao Liu, Xiangyu Cao, Xu Zhu, Shouping Wang, Yihan Xidian Univ Sch Life Sci & Technol Engn Res Ctr Mol & NeuroImaging Minist Educ Xian 710126 Peoples R China Xidian Univ Xian Key Lab Intelligent Sensing & Regulat Transsc Guangzhou 510555 Peoples R China Xidian Univ Int Joint Res Ctr Adv Med Imaging & Intelligent Di Guangzhou 510555 Peoples R China Xidian Univ Guangzhou Inst Technol Innovat Ctr Adv Med Imaging & Intelligent Med Guangzhou 510555 Peoples R China

Sparse sampling of photoacoustic (PA) signals is a crucial strategy for enhancing the feasibility of photoacoustic tomography (PAT) in clinical settings by reducing system complexity and costs. However, this approach often faces significant artifacts resulting from traditional reconstruction algorithms, underscoring the urgent need for effective solutions. To address the critical challenge of balancing computational efficiency with imaging quality, we introduce PACformer-a novel hybrid model that integrates convolutional neural networks (CNNs) with multi-head self-attentions (MSAs) to improve the reconstruction of sparse-view PAT images. While conventional CNNs excel at local feature extraction, they often struggle to capture long-range dependencies inherent in continuous structures and the diverse artifact patterns present in PAT images. PACformer tackles these limitations through a dual architecture that seamlessly combines MSAs with heterogeneous convolutional layers. Since feature representations differ in size and semantics at various stages of the deep model, PACformer employs specialized blocks for shallow and deep stages. Specifically, it utilizes efficient local convolutions and windowed MSAs for high-resolution feature maps, conditional convolutions (CondConv) integrated with MSAs for advanced feature representation in deeper stages, and Scale-Modulated Convolution combined with CondConv for the bottleneck stage. Experimental results on open-source datasets demonstrate PACformer's superior performance compared to traditional and state-of-the-art networks, validated through ablation studies and attention map visualizations. By effectively modeling both local and global artifacts, PACformer establishes itself as a robust solution for sparse-view PAT reconstruction.

关键词： Visualization Convolution Computational modeling Semantics reconstruction algorithms Transformers Feature extraction Image restoration Image reconstruction Faces Deep learning image restoration photoacoustic tomography reconstruction algorithms sparse-view

来源：评论

学校读者我要写书评

暂无评论

Recovering Fine Details for Neural Implicit Surface reconstruction 23

Recovering Fine Details for Neural Implicit Surface Reconstr...

引用

23rd IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

作者： Chen, Decai Zhang, Peng Feldmann, Ingo Schreer, Oliver Eisert, Peter Fraunhofer HHI Berlin Germany TU Berlin Berlin Germany HU Berlin Berlin Germany

ISBN: (纸本)9781665493468

Recent works on implicit neural representations have made significant strides. Learning implicit neural surfaces using volume rendering has gained popularity in multiview reconstruction without 3D supervision. However, accurately recovering fine details is still challenging, due to the underlying ambiguity of geometry and appearance representation. In this paper, we present D-NeuS, a volume rendering-base neural implicit surface reconstruction method capable to recover fine geometry details, which extends NeuS by two additional loss functions targeting enhanced reconstruction quality. First, we encourage the rendered surface points from alpha compositing to have zero signed distance values, alleviating the geometry bias arising from transforming SDF to density for volume rendering. Second, we impose multi-view feature consistency on the surface points, derived by interpolating SDF zerocrossings from sampled points along rays. Extensive quantitative and qualitative results demonstrate that our method reconstructs high-accuracy surfaces with details, and outperforms the state of the art.(1)

关键词： Geometry Surface reconstruction Interpolation Computer vision Three-dimensional displays reconstruction algorithms Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

SimGlim: Simplifying glimpse based active visual reconstruction 23

SimGlim: Simplifying glimpse based active visual reconstruct...

引用

23rd IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

作者： Jha, Abhishek Seifi, Soroush Tuytelaars, Tinne Katholieke Univ Leuven ESAT PSI Leuven Belgium

ISBN: (纸本)9781665493468

In active visual exploration, an agent with a limited field of view needs to sample the most informative local observations of an environment in order to model the global context. Current works train this selection strategy by defining a complex architecture built upon features learned through convolutional encoders. In this paper, we first discuss why vision transformers are better suited than CNNs for such an agent. Next, we propose a simple transformer-based active visual sampling model, called "SimGlim", which utilises transformer's inherent self-attention architecture to sequentially predict the best next location based on the current observable environment. We show the efficacy of our proposed method on the task of image reconstruction in the partial observable setting and compare our model against existing state-of-the-art active visual reconstruction methods. Finally, we provide ablations for the parameters of our design choice to understand their importance in the overall architecture.

关键词： Visualization Computer vision reconstruction algorithms Predictive models Transformers Data models Task analysis

来源：评论

学校读者我要写书评

暂无评论

SIM reconstruction framework for high-speed multi-dimensional super-resolution imaging

引用

OPTICS EXPRESS 2022年第7期30卷 10877-10898页

作者： Zeng, Hui Liu, Guoxuan Zhao, Rong Tsinghua Univ Opt Memory Natl Engn Res Ctr Ctr Brain Inspired Comp Res CBICR Dept Precis Instruments Beijing 100084 Peoples R China Tsinghua Univ Beijing Innovat Ctr Future Chip Beijing 100084 Peoples R China Tsinghua Univ Dept Precis Instrument State Key Lab Precis Measurement Technol & Instru Beijing 100084 Peoples R China

Structured illumination microscopy (SIM) holds great promise for live cell imaging applications due to its potential to obtain multidimensional information such as intensity, spectrum and polarization (I, lambda, p) at high spatial-temporal resolution, enabling the observation of more complex dynamic interactions between subcellular structures. However, the reconstruction results of polarized samples are prone to artifacts because all current SIM reconstruction frameworks use incomplete imaging models which neglect polarization modulation. Such polarization-related artifacts are especially prevalent for SIM reconstruction using a reduced number of raw images (RSIM) and severely undermine the ability of SIM to capture multi-dimensional information. Here, we report a new SIM reconstruction framework (PRSIM) that can recover multi-dimensional information (I, lambda, p) using a reduced number of raw images. PRSIM adopts a complete imaging model that is versatile for normal and polarized samples and uses a frequency-domain iterative reconstruction algorithm for artifact-free super-resolution (SR) reconstruction. It can simultaneously obtain the SR spatial structure and polarization orientation of polarized samples using 6 raw SIM images and can perform SR reconstruction using 4 SIM images for normal samples. In addition, PRSIM has less spatial computational complexity and achieves reconstruction speeds tens of times higher than that of the state-of-the-art non-iterative RSIM, making it more suitable for large field-of-view imaging. Thus, PRSIM is expected to facilitate the development of SIM into an ultra-high-speed and multi-dimensional SR imaging tool. (C) 2022 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement

关键词： Green fluorescent protein Hyperspectral imaging Imaging techniques Live cell imaging reconstruction algorithms Temporal resolution

来源：评论

学校读者我要写书评

暂无评论

Fast reconstruction of Three-Quarter Sampling Measurements Using Recurrent Local Joint Sparse Deconvolution and Extrapolation

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS 2022年第5期69卷 2398-2402页

作者： Grosche, Simon Regensky, Andy Sinn, Alexander Seiler, Jurgen Kaup, Andre Friedrich Alexander Univ Erlangen Nurnberg Multimedia Commun & Signal Proc D-91058 Erlangen Germany

Recently, non-regular three-quarter sampling has shown to deliver an increased image quality of image sensors by using differently oriented L-shaped pixels compared to the same number of square pixels. A three-quarter sampling sensor can be understood as a conventional low-resolution sensor where one quadrant of each square pixel is opaque. Subsequent to the measurement, the data can be reconstructed on a regular grid with twice the resolution in both spatial dimensions using an appropriate reconstruction algorithm. For this reconstruction, local joint sparse deconvolution and extrapolation (L-JSDE) has shown to perform very well. As a disadvantage, L-JSDE requires long computation times of several dozen minutes per megapixel. In this paper, we propose a faster version of L-JSDE called recurrent L-JSDE (RL-JSDE) which is a reformulation of L-JSDE. For reasonable recurrent measurement patterns, RL-JSDE provides significant speedups on both CPU and GPU without sacrificing image quality. Compared to L-JSDE, 20-fold and 733-fold speedups are achieved on CPU and GPU, respectively.

关键词： Image reconstruction Image resolution Windows Image quality Extrapolation reconstruction algorithms Mathematical models Image reconstruction image processing compressed sensing nonuniform sampling image sampling

来源：评论

学校读者我要写书评

暂无评论

High-Quality RGB-D reconstruction via Multi-View Uncalibrated Photometric Stereo and Gradient-SDF 23

High-Quality RGB-D Reconstruction via Multi-View Uncalibrate...

引用

23rd IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

作者： Sang, Lu Haefner, Bjoern Zuo, Xingxing Cremers, Daniel Tech Univ Munich Munich Germany Munich Ctr Machine Learning Munich Germany

ISBN: (纸本)9781665493468

Fine-detailed reconstructions are in high demand in many applications. However, most of the existing R-GBD reconstruction methods rely on pre-calculated accurate camera poses to recover the detailed surface geometry, where the representation of a surface needs to be adapted when optimizing different quantities. In this paper, we present a novel multi-view RGB-D based reconstruction method that tackles camera pose, lighting, albedo, and surface normal estimation via the utilization of a gradient signed distance field (gradient-SDF). The proposed method formulates the image rendering process using specific physically-based model(s) and optimizes the surface's quantities on the actual surface using its volumetric representation, as opposed to other works which estimate surface quantities only near the actual surface. To validate our method, we investigate two physically-based image formation models for natural light and point light source applications. The experimental results on synthetic and real-world datasets demonstrate that the proposed method can recover high-quality geometry of the surface more faithfully than the state-of-the-art and further improves the accuracy of estimated camera poses(1).

关键词： Geometry Surface reconstruction Lighting Estimation reconstruction algorithms Cameras Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

Numerical algorithms for recovering a fractional Sturm-Liouville operator based on trace formulae

引用

NUMERICAL algorithms 2024年 1-26页

作者： Li, Xiaowen Jiang, Xiaoying Xu, Xiang Zhejiang Univ Sch Math Sci Hangzhou Zhejiang Peoples R China Zhejiang A&F Univ Hangzhou Peoples R China

This paper explores numerical methods for recovering a density term in a fractional Sturm-Liouville problem using a set of spectra. By applying Lidskii's theorem, a sequence of trace formulae are derived to elucidate the connections between the unknown coefficients and the complex eigenvalues of a fractional spectra problem. Two efficient algorithms are proposed based on these trace formulae, and their effectiveness is demonstrated through numerical experiments.

关键词： Inverse spectra problem Trace formula Fractional Sturm-Liouville problem reconstruction algorithms

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：