检索结果-内蒙古大学图书馆

The role of prior in image based 3D modeling： a survey

Frontiers of Computer Science 2017年第2期11卷 175-191页

作者： Hao ZHU Yongming NIE Tao YUE Xun CAO Lab for Computational Imaging Technology and Engineering School of Electronic Science and Engineering Nanjing University Nanjing 210023 China

The prior knowledge is the significant supple- ment to image-based 3D modeling algorithms for refining the fragile consistency-based stereo. In this paper, we review the image-based 3D modeling problem according to prior cate- gories, i.e., classical priors and specific priors. The classical priors including smoothness, silhouette and illumination are well studied for improving the accuracy and robustness of the 3D reconstruction. In recent years, various specific priors which take advantage of Manhattan rule, geometry template and trained category features have been proposed to enhance the modeling performance. The advantages and limitations of both kinds of priors are discussed and evaluated in the paper. Finally, we discuss the trend and challenges of the prior studies in the future.

关键词： prior information consistency-based stereo,smoothness illumination silhouette specific prior

来源：评论

学校读者我要写书评

暂无评论

Towards Fast and Light-Weight Restoration of Dark Images 31

Towards Fast and Light-Weight Restoration of Dark Images

引用

31st British Machine Vision Conference, BMVC 2020

作者： Lamba, Mohit Balaji, Atul Mitra, Kaushik Computational Imaging Lab Dept. of Electrical Engineering Indian Institute of Technology Madras Chennai India

The ability to capture good quality images in the dark and near-zero lux conditions has been a long-standing pursuit of the computer vision community. The seminal work by Chen et al. [5] has especially caused renewed interest in this area, resulting in methods that build on top of their work in a bid to improve the reconstruction. However, for practical utility and deployment of low-light enhancement algorithms on edge devices such as embedded systems, surveillance cameras, autonomous robots and smartphones, the solution must respect additional constraints such as limited GPU memory and processing power. With this in mind, we propose a deep neural network architecture that aims to strike a balance between the network latency, memory utilization, model parameters, and reconstruction quality. The key idea is to forbid computations in the High-Resolution (HR) space and limit them to a Low-Resolution (LR) space. However, doing the bulk of computations in the LR space causes artifacts in the restored image. We thus propose Pack and UnPack operations, which allow us to effectively transit between the HR and LR spaces without incurring much artifacts in the restored image. State-of-the-art algorithms on dark image enhancement need to pre-amplify the image before processing it. However, they generally use ground truth information to find the amplification factor even during inference, restricting their applicability for unknown scenes. In contrast, we propose a simple yet effective light-weight mechanism for automatically determining the amplification factor from the input image. We show that we can enhance a full resolution, 2848 × 4256, extremely dark single-image in the ballpark of 3 seconds even on a CPU. We achieve this with 2 − 7× fewer model parameters, 2 − 3× lower memory utilization, 5 − 20× speed up and yet maintain a competitive image reconstruction quality compared to the state-of-the-art algorithms. © 2020. The copyright of this document resides with its author

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Radiomics-enhanced prediction of Constant-Murley scores following ultrasound-guided percutaneous irrigation of calcific tendinopathy

European Journal of Radiology Artificial Intelligence

引用

European Journal of Radiology Artificial Intelligence 2025年 2卷 100019-100019页

作者： Matthaios Triantafyllou Evangelia E. Vassalou Alexia Maria Goulianou Theodoros H. Tosounidis Kostas Marias Apostolos H. Karantanas Michail E. Klontzas Artificial Intelligence and Translational Imaging (ATI) Lab Department of Radiology School of Medicine University of Crete Voutes Campus Heraklion Greece Department of Medical Imaging University Hospital of Heraklion Heraklion Crete Greece Department of Orthopaedic Surgery University Hospital Heraklion Heraklion Crete 71500 Greece Computational BioMedicine Laboratory Institute of Computer Science Foundation for Research and Technology (FORTH) Heraklion Crete Greece Department of Electrical and Computer Engineering Hellenic Mediterranean University Heraklion Crete Greece Division of Radiology Department for Clinical Science Intervention and Technology (CLINTEC) Karolinska Institutet Stockholm Sweden

Objective Calcific tendinopathy of the rotator cuff presents challenges in symptom management and functional recovery with image-guided treatment. This study aimed to develop a regression model integrating radiomic and clinical features to predict 1-year Constant-Murley Score (CMS) improvement following ultrasound-guided percutaneous irrigation of calcific tendinopathy (US-PICT). Materials and Methods This retrospective study included 84 patients undergoing US-PICT between 2017 and 2019. Advanced Contrast Limited Adaptive Histogram Equilization (CLAHE) preprocessing was applied to US images for radiomic feature extraction. Manual segmentation of calcifications yielded 849 features, later refined to 6 predictive features through inter-rater ICC analysis, correlation filtering, and Recursive Feature Elimination (RFE). Clinical variables, including age, calcification type, and maximum diameter, were integrated. Model performance was evaluated using R 2 , MAE, RMSE, calibration curves, and SHAP analysis, while decision curve analysis assessed clinical utility. Results The regression model achieved an R 2 of 0.66 (95 % CI: 0.52–0.76) with an RMSE of 8.26. Younger age, larger calcifications, and fluid-like consistency correlated with greater CMS improvement (p < 0.001). SHAP analysis identified calcification type, age, and radiomic features as key predictors. Calibration curves demonstrated reasonable alignment between predictions and observed outcomes, while decision curve analysis highlighted the model’s clinical utility. Conclusion Radiomics combined with clinical features provides robust predictions of 1-year functional improvement after US-PICT. Further validation in larger cohorts is warranted to refine and generalize these findings.

关键词： Radiomics Calcific Tendinopathy/(US-PICT) Machine Learning Artificial Intelligence Shoulder

来源：评论

学校读者我要写书评

暂无评论

GN-FR: Generalizable Neural Radiance Fields for Flare Removal

arXiv

引用

arXiv 2024年

作者： Matta, Gopi Raju Siddartha, Rahul Venkata Girish, Rongali Simhachala Sharma, Sumit Mitra, Kaushik Computational Imaging Lab Dept. of Electrical Engineering Indian Institute of Technology Madras Chennai India

Flare, an optical phenomenon resulting from unwanted scattering and reflections within a lens system, presents a significant challenge in imaging. The diverse patterns of flares—such as halos, streaks, color bleeding, and haze—complicate the flare removal process. Existing traditional and learning-based methods have exhibited limited efficacy due to their reliance on single-image approaches, where flare removal is highly ill-posed. We address this by framing flare removal as a multi-view image problem, taking advantage of the view-dependent nature of flare artifacts. This approach leverages information from neighboring views to recover details obscured by flare in individual images. Our proposed framework, GN-FR (Generalizable Neural Radiance Fields for Flare Removal), can render flare-free views from a sparse set of input images affected by lens flare and generalizes across different scenes in an unsupervised manner. GN-FR incorporates several modules within the Generalizable NeRF Transformer (GNT) framework: Flare-occupancy Mask Generation (FMG), View Sampler (VS), and Point Sampler (PS). To overcome the impracticality of capturing both flare-corrupted and flare-free data, we introduce a masking loss function that utilizes mask information in an unsupervised setting. Additionally, we present the first-of-its-kind 3D multi-view flare dataset, comprising 17 real flare scenes with 782 images, 80 real flare patterns, and their corresponding annotated flare-occupancy masks. To our knowledge, this is the first work to address flare removal within a Neural Radiance Fields (NeRF) framework. © 2024, CC BY.

关键词： Lenses

来源：评论

学校读者我要写书评

暂无评论

Towards fast and light-weight restoration of dark images 202

arXiv

引用

arXiv 2020年

作者： Lamba, Mohit Balaji, Atul Mitra, Kaushik Computational Imaging Lab Dept. of Electrical Engineering Indian Institute of Technology Madras Chennai India

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Anomalous Hall optical conductivity in tilted topological nodal-line semimetals

引用

Physical Review B 2021年第16期103卷 165104-165104页

作者： Chen Wang Wen-Hui Xu Chang-Yong Zhu Jin-Na Chen Yong-Long Zhou Ming-Xun Deng Hou-Jian Duan Rui-Qiang Wang Lab for Computational Imaging Technology and Engineering School of Electronic Science and Engineering Nanjing University Nanjing 210023 China Guangdong Provincial Key Laboratory of Quantum Engineering and Quantum Materials School of Physics and Telecommunication Engineering South China Normal University Guangzhou 510006 China

Nodal-line semimetals are typically characterized by a nodal ring, a closed line of Dirac points in the Brillouin zone, whose topology is characterized by a quantized Berry phase. The nodal loop is protected by the combined inversion and time-reversal (PT) symmetry in the absence of spin-orbit coupling, exhibiting the parity anomaly. Introduction of the PT-break mass term can lead to the transverse Hall response at each point in the nodal ring, but the net Hall current vanishes due to the existence of inversion-symmetry points that contribute to the transverse current with opposite signs. We show that the combination of an inversion-broken tilt term and finite Fermi energy can cause the nonzero anomalous Hall effect. We explore the DC and AC anomalous Hall conductivity in tilted nodal-line semimetals using Kubo formula and focus on the contribution of the free carriers to the Hall conductivity. We find that the interband transition of free carriers dominates the nonvanishing dynamic Hall conductivity over the filled band contribution. The resulting anomalous Hall conductivity exhibits the parity anomaly for the DC case, and rich characteristic frequencies for the AC case which is closely related to the change of the geometry of the Fermi surface. These features may serve as a diagnostic tool to characterize the topological property, tilting parameter, or the radius of the nodal line.

关键词： Electrical conductivity Optical conductivity Topological materials Node-line semimetals

来源：评论

学校读者我要写书评

暂无评论

High-spatial-resolution ultrafast framing imaging at 15 trillion frames per second by optical parametric amplification

引用

Advanced Photonics 2020年第5期2卷 53-63页

作者： Xuanke Zeng Shuiqin Zheng Yi Cai Qinggang Lin Jinyang Liang Xiaowei Lu Jingzhen Li Weixin Xie Shixiang Xu Shenzhen University College of Physics and Optoelectronic EngineeringShenzhen Key Lab of Micro-Nano Photonic Information TechnologyShenzhenChina Shenzhen University College of Electronic Information EngineeringShenzhenChina Institut National de la Recherche Scientifique CentreÉnergie Matériaux TélécommunicationsLaboratory of Applied Computational ImagingVarennesQuébecCanada

We report a framing imaging based on noncollinear optical parametric amplification(NCOPA),named FINCOPA,which applies NCOPA for the first time to single-shot ultrafast optical *** an experiment targeting a laser-induced air plasma grating,FINCOPA achieved 50 fs-resolved optical imaging with a spatial resolution of^83 lp∕mm and an effective frame rate of 10 trillion frames per second(Tfps).It has also successfully visualized an ultrafast rotating optical field with an effective frame rate of 15 *** has simultaneously a femtosecond-level temporal resolution and frame interval and a micrometer-level spatial *** outstanding spatial and temporal resolutions with an ultrahigh frame rate,FINCOPA will contribute to high-spatiotemporal resolution observations of ultrafast transient events,such as atomic or molecular dynamics in photonic materials,plasma physics,and laser inertial-confinement fusion.

关键词： ultrafast imaging spatiotemporal resolution frame rate noncollinear optical parametric amplification

来源：评论

学校读者我要写书评

暂无评论

Efficient reconstruction of cardiac LV surfaces using a 3D sparse ASM

Efficient reconstruction of cardiac LV surfaces using a 3D s...

引用

IEEE International Symposium on Biomedical imaging

作者： H.C. van Assen A.F. Frangi M.G. Danilouchkine S. Ordas J.J.M. Westenberg J.H.C. Reiber B.P.F. Lelieveldtt Biomedical Image Analysis Biomedical Engineering Technical University Eindhoven Eindhoven Netherlands Dep. Radiology Leiden Universtiy Medical Center Leiden Netherlands Department Technology Computational Imaging Laboratory Universitat Pompeu Fabra Barcelona Spain Dep. Technology Computational Imaging Lab. Barcelona Spain Department of Cardiology Erasmus MC-University Medical Center Rotterdam Rotterdam Netherlands

Cardiac magnetic resonance imaging (MRI) has demonstrated to be the most accurate and reproducible tool for assessment of the cardiovascular system. Traditional quantification methods require acquisition of densely sampled data sets, resulting in increased analysis time. This paper investigates whether comparable quantification accuracy can be achieved with a combination of sparsely sampled data and using an active shape model (ASM) of the left ventricle

关键词： Surface reconstruction Magnetic resonance imaging Shape Biomedical imaging Heart Image reconstruction Cardiology Image analysis Risk management Fuzzy systems

来源：评论

学校读者我要写书评

暂无评论

Photon-Induced Weyl Half-Metal Phase and Spin Filter Effect from Topological Dirac Semimetals

引用

Physical Review Letters 2019年第20期123卷 206601-206601页

作者： Xiao-Shi Li Chen Wang Ming-Xun Deng Hou-Jian Duan Pei-Hao Fu Rui-Qiang Wang L. Sheng D. Y. Xing Guangdong Provincial Key Laboratory of Quantum Engineering and Quantum Materials GPETR Center for Quantum Precision Measurement SPTE South China Normal University Guangzhou 510006 China Lab for Computational Imaging Technology and Engineering School of Electronic Science and Engineering Nanjing University Nanjing 210023 China National Laboratory of Solid State Microstructures and Department of Physics Nanjing University Nanjing 210093 China

Recently discovered Dirac semimetals (DSMs) with two Dirac nodes, such as Na3Bi and Cd2As3, are regarded as carrying the Z2 topological charge in addition to the chiral charge. We study the Floquet phase transition of Z2 topological DSMs subjected to a beam of circularly polarized light. Owing to the resulting interplay of the chiral and Z2 charges, the Weyl nodes are not only chirality dependent but also spin dependent, which constrains the behavior in creation and annihilation of the pair of Weyl nodes. Interestingly, we find a novel phase: One spin band is in the Weyl semimetal phase while the other is in the insulator phase, and we dub it the Weyl half-metal (WHM) phase. We further study the spin-dependent transport in a Dirac-Weyl semimetal junction and find a spin filter effect as a fingerprint of the existence of the WHM phase. The proposed spin filter effect, based on the WHM bulk band, is highly tunable in a broad parameter regime and robust against magnetic disorder, which is expected to overcome the shortcomings of the previously proposed spin filter based on the topological edge or surface states. Our results offer a unique opportunity to explore the potential applications of topological DSMs in spintronics.

关键词： Photoinduced effect Spintronics Topological materials Dirac semimetal

来源：评论

学校读者我要写书评

暂无评论

Functional imaging and Modeling of the Heart 1

引用

丛书名： Lecture Notes in Computer Science

1000年

作者： Alejandro F. Frangi Petia I. Radeva Andres Santos Monica Hernandez

ISBN: (数字)9783540320814

ISBN: (纸本)9783540261612

The1stand2ndInternationalConferencesonFunctionalimagingandModelling of the Heart (FIMH) were held in Helsinki, Finland, in November 2001, and in Lyon, France, in June 2003. These meetings were born through a fruitful sci- ti?c collaboration between France and Finland that outreached to other groups and led to the start of this biennial event. The FIMH conference was the ?rst attempt to agglutinate researchers from several complementary but often i- lated ?elds: cardiac imaging, signal and image processing, applied mathematics and physics, biomedical engineering and computer science, cardiology, radi- ogy, biology, and physiology. In the ?rst two editions, the conference received an enthusiastic acceptance by experts of all these communities. FIMH was ori- nally started as a European event and has increasingly attracted more and more people from the US and Asia. This edition of FIMH received the largest number of submissions so far with a result of 47 papers being accepted as either oral presentations or posters. There were a number of submissions from non-EU institutions which con?rms the growing interest in this series of meetings. All papers were reviewed by up to four reviewers. The accepted contributions were organized into 8 oral sessions and 3 poster sessions complemented by a number of invited talks. This year we tried to allocate as many papers as possible as oral presentations to facilitate more active participation and to stimulate multidisciplinary discussions.

关键词： Image Processing and Computer Vision Simulation and Modeling Artificial Intelligence Computer Appl. in Life Sciences imaging / Radiology Cardiology

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：