检索结果-内蒙古大学图书馆

conference on Adaptive Optics Systems viii Part of SPIE Astronomical Telescopes and Instrumentation conference

作者： Smith, Jeffrey Cranney, Jesse Gretton, Charles Gratadour, Damien Australian Natl Univ Sch Comp Canberra Australia Australian Natl Univ Adv Instrumentat Technol Ctr Res Sch Astron & Astrophys Canberra Australia Univ Paris Univ PSL Sorbonne Univ CNRSLESIAObserv Paris 5 Pl Jules Janssen F-92195 Meudon France

ISBN: (纸本)9781510653528;9781510653511

We develop and evaluate a new approach to phase estimation for observational astronomy that can be used for accurate point spread function reconstruction. Phase estimation is required where a terrestrial observatory uses an Adaptive Optics (AO) system to assist astronomers in acquiring sharp, high-contrast images of faint and distant objects. Our approach is to train a conditional adversarial artificial neural network architecture to predict phase using the wavefront sensor data from a closed-loop AO system. We present a detailed simulation study under different turbulent conditions, using the retrieved residual phase to obtain the point spread function of the simulated instrument. Compared to the state-of-the-art model-based approach in astronomy, our approach is not explicitly limited by modelling assumptions e.g. independence between terms, such as bandwidth and anisoplanatism and is conceptually simple and flexible. We use the open source COMPASS tool for end-to-end simulations. On key quality metrics, specifically the Strehl ratio and Halo distribution in our application domain, our approach achieves results better than the model-based baseline.

关键词： Generative Adversarial Networks GANs Convolutional Neural Network Wavefront Estimation PSF reconstruction Adaptive Optics

来源：评论

学校读者我要写书评

暂无评论

Towards virtual access of adaptive optics telemetry data 8

Towards virtual access of adaptive optics telemetry data

引用

conference on Adaptive Optics Systems viii Part of SPIE Astronomical Telescopes and Instrumentation conference

作者： Gomes, Tiago Correia, Carlos Bardou, Lisa Beltramo-Martin, Olivier Fusco, Thierry Kulcsar, Caroline Morris, Timothy Morujao, Nuno Neichel, Benoit Osborn, James Garcia, Paulo Univ Porto Fac Engn Rua Dr Roberto Frias S-N P-4200465 Porto Portugal Space ODT Opt Deblurring Technol Porto Portugal Aix Marseille Univ CNRS CNES LAM Marseille France Univ Paris Saclay DOTA ONERA F-91123 Palaiseau France Univ Durham Durham England Inst Super Tecn Ctr Astrophys & Gravitat Rovisco Pais 1 P-1049001 Lisbon Portugal Univ Paris Saclay CNRS Inst Opt Grad Sch Lab Charles Fabry F-91127 Palaiseau France Univ Porto Dept Fis Astron Fac Ciencias Rua Campo Alegre S-N P-4169007 Porto Portugal

ISBN: (纸本)9781510653528;9781510653511

Large amounts of Adaptive-Optics (AO) control loop data and telemetry are currently inaccessible to end-users. Broadening access to those data has the potential to change the AO landscape on many fronts, addressing several use-cases such as derivation of the system's PSF, turbulence characterisation and optimisation of system control. We address one of the biggest obstacles to sharing these data: the lack of standardisation, which hinders access. We propose an object-oriented Python package for AO telemetry, whose data model abstracts the user from an underlining archive-ready data exchange standard based on the Flexible image Transport System (FITS). Its design supports data from a wide range of existing and future AO systems, either in raw format or abstracted from actual instrument details. We exemplify its usage with data from active AO systems on 10m-class observatories, of which two are currently supported (AOF and Keck), with plans for more.

关键词： Adaptive Optics Telemetry data Exchange Standard data Model PSF reconstruction FITS Object Oriented Python

来源：评论

学校读者我要写书评

暂无评论

Multispectral image reconstruction of Faint Circumstellar Environments from High Contrast Angular Spectral Differential Imaging (ASDI) data 8

Multispectral Image Reconstruction of Faint Circumstellar En...

引用

conference on Adaptive Optics Systems viii Part of SPIE Astronomical Telescopes and Instrumentation conference

作者： Flasseur, Olivier The, Samuel Denis, Loiec Thiebaut, Eric Langlois, Maud Univ Paris Diderot Sorbonne Univ Univ PSL Observ ParisLab Etud Spatiales & Instrumentat As Paris France Univ Claude Bernard Lyon 1 Univ Lyon CNRS Ctr Rech Astrophys LyonENS Lyon Lyon France Univ Lyon UJM St Etienne CNRS Inst Opt Grad SchLab Hubert Curien St Etienne France

ISBN: (纸本)9781510653528;9781510653511

We recently proposed REXPACO,(1) an algorithm for imaging circumstellar environments from high-contrast angular differential imaging (ADI) data. In the context of high-contrast imaging where the signal of interest is largely dominated by a nuisance term due to the stellar light leakages and the noise, our algorithm amounts to jointly estimating the object of interest and the statistics (mean and covariance matrix) of the nuisance component. In this contribution, we first extend the REXPACO algorithm by refining the statistical model of the nuisance component it embeds. Capitalizing on the improved robustness of this new method named robust REXPACO, we then show how it can be modified to deal with angular plus spectral differential imaging (ASDI) datasets. We apply our methods on several ADI and ASDI datasets from the IRDIS and IFS imagers of the VLT/SPHERE instrument and we show that the proposed algorithms significantly reduce the typical artifacts produced by state-of-the-art algorithms. By also taking into account the instrumental point spread function (PSF), our algorithms yield a deblurred estimate of the object of interest without the artifacts observed with other methods.

关键词： High-contrast imaging angular and spectral differential imaging circumstellar environment reconstruction algorithm regularized inverse problems statistical method

来源：评论

学校读者我要写书评

暂无评论

Compressive Imaging reconstruction via Conditional Diffusion Model With Augmented Measurements

Compressive Imaging Reconstruction via Conditional Diffusion...

引用

International conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Emmanuel Martinez Leon Suarez Romario Gualdrón-Hurtado Roman Jacome Henry Arguello Department of Systems and Informatics Engineering Universidad Industrial de Santander Bucaramanga Colombia Department of Electrical Electronics and Telecommunications Engineering Universidad Industrial de Santander Bucaramanga Colombia

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Compressive imaging (CI) consists of reconstructing images from incomplete observed data. The reconstruction process involves solving an ill-posed inverse problem which is highly dependent on the number of real measurements, with a greater number of measurements typically leading to more accurate reconstructions. Due to their ability to learn data distributions, diffusion models (DM) have emerged as promising techniques for various inverse problems. Mainly, DMs solve inverse problems by conditioning the generation process to the acquired measurements. In this work, we introduce a new approach to improve this conditioning by exploiting synthetic measurements, which come from a synthetic sensing matrix. Synthetic measurements are estimated from real data via a neural network. The combined real and synthetic measurements form an augmented set, which is input into the conditional DM to enhance reconstruction capacity. Computational experiments demonstrate that augmenting measurements with the conditional DM improves performance compared to using only real measurements.

关键词： image coding Inverse problems Imaging Signal processing Diffusion models Robustness Sensors Noise measurement Speech processing image reconstruction

来源：评论

学校读者我要写书评

暂无评论

A Bottom-Up Sampling Strategy for Reconstructing Geospatial data from Ultra Sparse Inputs 9th

A Bottom-Up Sampling Strategy for Reconstructing Geospatial...

引用

19th International conference on Advanced data Mining and Applications, ADMA 2023

作者： Landt-Hayen, Marco Wölker, Yannick Rath, Willi Claus, Martin Christian-Albrechts-Universität zu Kiel Kiel Germany GEOMAR Helmholtz Centre for Ocean Research Kiel Germany

ISBN: (纸本)9783031466601

Working with observational data in the context of geophysics can be challenging, since we often have to deal with missing data. This requires imputation techniques in pre-processing to obtain data-mining-ready samples. Here, we present a convolutional neural network (CNN) approach from the domain of deep learning to reconstruct complete data from sparse inputs. CNN architectures are state-of-the-art for image processing. As data, we use two-dimensional fields of sea level pressure (SLP) and sea surface temperature (SST) anomalies. To have consistent data over a sufficiently long time span, we favor to work with output from control simulations of two Earth System Models (ESMs), namely the Flexible Ocean and Climate Infrastructure and the Community Earth System Model. Our networks can restore complete information from incomplete input samples with varying rates of missing data. Moreover, we present a technique to identify the most relevant grid points of our input samples. Choosing the optimal subset of grid points allows us to successfully reconstruct SLP and SST anomaly fields from ultra sparse inputs. As a proof of concept, the insights obtained from ESMs can be transferred to real world observations to improve reconstruction quality. As uncertainty measure, we compare several climate indices derived from reconstructed versus complete fields. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Earth system models

来源：评论

学校读者我要写书评

暂无评论

Single-Stage 3D Geometry-Preserving Depth Estimation Model Training on dataset Mixtures with Uncalibrated Stereo data

Single-Stage 3D Geometry-Preserving Depth Estimation Model T...

引用

IEEE/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Patakin, Nikolay Vorontsova, Anna Artemyev, Mikhail Konushin, Anton Samsung AI Ctr Moscow Russia Skolkovo Inst Sci & Technol Skoltech Moscow Russia

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Nowadays, robotics, AR, and 3D modeling applications attract considerable attention to single-view depth estimation (SVDE) as it allows estimating scene geometry from a single RGB image. Recent works have demonstrated that the accuracy of an SVDE method hugely depends on the diversity and volume of the training data. However, RGB-D datasets obtained via depth capturing or 3D reconstruction are typically small, synthetic datasets are not photorealistic enough, and all these datasets lack diversity. The large-scale and diverse data can be sourced from stereo images or stereo videos from the web. Typically being uncalibrated, stereo data provides disparities up to unknown shift (geometrically incomplete data), so stereo-trained SVDE methods cannot recover 3D geometry. It was recently shown that the distorted point clouds obtained with a stereo-trained SVDE method can be corrected with additional point cloud modules (PCM) separately trained on the geometrically complete data. On the contrary, we propose GP(2), General-Purpose and Geometry-Preserving training scheme, and show that conventional SVDE models can learn correct shifts themselves without any post-processing, benefiting from using stereo data even in the geometry-preserving setting. Through experiments on different dataset mixtures, we prove that GP(2)-trained models outperform methods relying on PCM in both accuracy and speed, and report the state-of-the-art results in the general-purpose geometry-preserving SVDE. Moreover, we show that SVDE models can learn to predict geometrically correct depth even when geometrically complete data comprises the minor part of the training set.

关键词： Training Point cloud compression Phase change materials Geometry Solid modeling Three-dimensional displays Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Advanced compressed sensing photoacoustic imaging techniques using iteratively enhanced L1 regularization

Advanced compressed sensing photoacoustic imaging techniques...

引用

2024 International conference on Computer Application and Information Security, ICCAIS 2024

作者： Wang, Lu Yao, Yaru Hao, Ziqi Hu, Xiaolong School of Mathematical Sciences Liaocheng University Shandong Liaocheng252000 China

ISBN: (纸本)9781510689312

Photoacoustic imaging (PAI) offers significant advantages but faces challenges in data processing and reconstruction. Sparse reconstruction techniques and compressed sensing theory have advanced its development. Regularization methods are commonly used to address the ill-posed problem of reconstructing PAI images from incomplete and noisy experimental data. While the L1-norm efficiently promotes sparsity in regularization methods, it often results in undesirable edge smoothing, which can degrade image quality. To address this limitation, this paper employs the Modified Iterative Reweighted L1 (MIRL1) regularization method, which aims to enhance sparsity while preserving critical image features such as edges. Experiments with simulated signals containing Gaussian noise show that MIRL1 outperforms traditional L1-norm-based SPGL1 and L0-norm-based SL0 algorithms in terms of image quality and noise robustness. MIRL1 enhances image clarity and maintains strong resistance to noise, providing superior image recovery results. This finding is significant for the development of sparse sampling PAI imaging algorithms. © The Authors.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Generative adversarial networks in medical image reconstruction: A systematic literature review

引用

Computers in Biology and Medicine 2025年 191卷 110094-110094页

作者： Hussain, Jabbar Båth, Magnus Ivarsson, Jonas Dept. of Applied IT University of Gothenburg Forskningsgången 6 417 56 Sweden Department of Medical Radiation Sciences University of Gothenburg Sweden

Purpose: Recent advancements in generative adversarial networks (GANs) have demonstrated substantial potential in medical image processing. Despite this progress, reconstructing images from incomplete data remains a challenge, impacting image quality. This systematic literature review explores the use of GANs in enhancing and reconstructing medical imaging data. Method: A document survey of computing literature was conducted using the ACM Digital Library to identify relevant articles from journals and conference proceedings using keyword combinations, such as "generative adversarial networks or generative adversarial network," "medical image or medical imaging," and "image reconstruction." Results: Across the reviewed articles, there were 122 datasets used in 175 instances, 89 top metrics employed 335 times, 10 different tasks with a total count of 173, 31 distinct organs featured in 119 instances, and 18 modalities utilized in 121 instances, collectively depicting significant utilization of GANs in medical imaging. The adaptability and efficacy of GANs were showcased across diverse medical tasks, organs, and modalities, utilizing top public as well as private/synthetic datasets for disease diagnosis, including the identification of conditions like cancer in different anatomical regions. The study emphasized GAN's increasing integration and adaptability in diverse radiology modalities, showcasing their transformative impact on diagnostic techniques, including cross-modality tasks. The intricate interplay between network size, batch size, and loss function refinement significantly impacts GAN's performance, although challenges in training persist. Conclusions: The study underscores GANs as dynamic tools shaping medical imaging, contributing significantly to image quality, training methodologies, and overall medical advancements, positioning them as substantial components driving medical advancements. © 2025 The Authors

关键词： Medical image processing

来源：评论

学校读者我要写书评

暂无评论

Shot-Gather reconstruction on 3D incomplete Surveys Using Deep Prior-Based Convolutional Neural Networks 4

Shot-Gather Reconstruction on 3D Incomplete Surveys Using De...

引用

4th HGS/EAGE conference on Latin America

作者： Rodríguez, L.M. León-López, K. Goyes-Peñafiel, P. Galvis, L. Arguello, H. Universidad Industrial de Santander Colombia

ISBN: (纸本)9789462824324

Seismic surveys are often affected by irregularity and coarse sampling resulting from limitations at the acquisition such as obstacles and environmental constraints. Thus, various processing algorithms have been developed to reconstruct these missing data, including interpolation based on transforms and deep learning-based reconstruction methods, where the latter allows the extraction of more complex structures from tons of data. Alternatively, deep-image-prior (DIP) methods mitigate the use of extensive training information by considering only the data under observation, showing promising results in recovering seismic traces. This work proposes a DIP-based convolutional neural network for recovering missing sources in a three-dimensional (3D) seismic survey which exploits as priors the data acquired and the structure of the 3D network. Additionally, considering the correlation across the source domain, an operator is employed for vertically shifting the set of traces to have the maximum data correlation in the network. Numerical experiments show that the proposed network recovers the complete set of traces in each shot-gather, where the information and events are preserved even though the source is not acquired. © 2022 HGS/*** rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Non-local Low Rank and Total Variation Approach for Depth image Estimation 15

A Non-local Low Rank and Total Variation Approach for Depth ...

引用

15th RIVF International conference on Computing and Communication Technologies (RIVF)

作者： Mau Uyen Nguyen Truong Giang Tong Tat Thang Hoa Dai Duong Ha Van Ha Tang Le Quy Don Tech Univ Fac Informat Technol Hanoi Vietnam

ISBN: (纸本)9781665404358

Accurate depth reconstruction is vital for numerous applications including autonomous vehicles, virtual reality, and robot perception. However, the depth imaging is challenging because of limited hardware operations, resource-constrained limitations, and incomplete data measurements. To address such shortcomings, this paper introduces an imaging model for efficient depth image estimation from incomplete depth pixels using non-local low-rank (NLLR) and total variation (TV) representations. The motivation is that NLLR is used to model global similar structure among depth patches, and the TV is incorporated to capture the correlations among local depth pixels. We reformulate the problem of depth reconstruction as a regularized least squares minimization problem with the non-local LR and TV regularizers. Furthermore, this paper proposes an iterative algorithm using the alternating direction method of multipliers (ADMM) to solve the optimization model, yielding an estimate of the depth map from far reduced data points. Experimental results on benchmark datasets validate the efficiency of the proposed approach.

关键词： Depth imaging RGB-D imaging sparse reconstruction low-rank approximation

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：