检索结果-内蒙古大学图书馆

An Efficient End-to-End 3D Voxel reconstruction based on Neural Architecture Search 26

An Efficient End-to-End 3D Voxel Reconstruction based on Neu...

26th International Conference on Pattern Recognition / 8th International Workshop on Image Mining - Theory and Applications (IMTA)

作者： Huang, Yongdong Li, Yuanzhan Cao, Xulong Zhang, Siyu Cai, Shen Lu, Ting Wang, Jie Liu, Yuqi Donghua Univ Visual & Geometr Percept Lab Shanghai 201620 Peoples R China Univ Manchester Manchester M13 9PL Lancs England Tongji Univ Sch Elect & Informat Engn Shanghai 201804 Peoples R China

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

Using neural networks to represent 3D objects has become popular. However, many previous works employ neural networks with fixed architecture and size to represent different 3D objects, which lead to excessive network parameters for simple objects and limited reconstruction accuracy for complex objects. For each 3D model, it is desirable to have an end-to-end neural network with as few parameters as possible to achieve high-fidelity reconstruction. In this paper, we propose an efficient voxel reconstruction method utilizing neural architecture search (NAS) and binary classification. Taking the number of layers, the number of nodes in each layer, and the activation function of each layer as the search space, a specific network architecture can be obtained based on reinforcement learning technology. Furthermore, to get rid of the traditional surface reconstruction algorithms (e.g., marching cube) used after network inference, we complete the end-to-end network by classifying binary voxels. Compared to other signed distance field (SDF) prediction or binary classification networks, our method achieves significantly higher reconstruction accuracy using fewer network parameters.

关键词： Surface reconstruction Solid modeling Three-dimensional displays Neural networks Reinforcement learning reconstruction algorithms Network architecture

来源：评论

学校读者我要写书评

暂无评论

PrideDiff: Physics-Regularized Generalized Diffusion Model for CT reconstruction

引用

IEEE TRANSACTIONS ON RADIATION AND PLASMA MEDICAL SCIENCES 2025年第2期9卷 157-168页

作者： Lu, Zexin Gao, Qi Wang, Tao Yang, Ziyuan Wang, Zhiwen Yu, Hui Chen, Hu Zhou, Jiliu Shan, Hongming Zhang, Yi Sichuan Univ Coll Comp Sci Chengdu 610065 Peoples R China Sichuan Univ Key Lab Data Protect & Intelligent Management Minist Educ Chengdu 610207 Peoples R China Fudan Univ Inst Sci & Technol Brain Inspired Intelligence Shanghai 200433 Peoples R China Sichuan Univ Sch Cyber Sci & Engn Chengdu 610065 Peoples R China Sichuan Univ Key Lab Data Protect & Intelligent Management Minist Educ Chengdu 610207 Peoples R China

Achieving a lower radiation dose and a faster imaging speed is a pivotal objective of computed tomography (CT) reconstruction. However, these often come at the cost of compromised reconstruction quality. With the advent of deep learning, numerous CT reconstruction methods rooted in this field have significantly improved the reconstruction performance. Recently, diffusion models have further enhanced training stability and imaging quality for CT. However, many of these methods only focus on CT image domain features, ignoring the intrinsic physical information of the imaging process. Although compressive sensing-based iterative reconstruction algorithms utilize physical prior information, their intricate iterative process poses challenges in training, subsequently influencing their efficiency. Motivated by these observations, we introduce a novel physics-regularized generalized diffusion model for CT reconstruction (PrideDiff). On the one hand, our method further improves the quality of reconstructed images by fusing physics-regularized iterative reconstruction methods with diffusion models. On the other hand, we propose a prior extraction module embedded with temporal features, which effectively improves the performance of the iteration process. Extensive experimental results demonstrate that PrideDiff outperforms several state-of-the-art methods in low-dose and sparse-view CT reconstruction tasks on different datasets, with faster reconstruction speed. We further discuss the effectiveness of relevant components in PrideDiff and validate the stability of the iterative reconstruction process, followed by detailed analysis of computational cost and inference time.

关键词： Image reconstruction Computed tomography Diffusion models Training Noise Feature extraction reconstruction algorithms Plasmas Image restoration Diffusion processes Deep learning (DL) diffusion models iterative reconstruction low-dose computed tomography (CT) sparse-view CT

来源：评论

学校读者我要写书评

暂无评论

SAR Image reconstruction Method for Target Detection Using Self-Attention CNN-Based Deep Prior Learning

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2024年 62卷

作者： Li, Min Huo, Weibo Wu, Junjie Yang, Jianyu Southwest Jiaotong Univ Sch Comp & Artificial Intelligence Chengdu 611756 Peoples R China Univ Elect Sci & Technol China Sch Informat & Commun Engn Chengdu 611731 Peoples R China

Due to its all-day and all-weather capability, synthetic aperture radar (SAR) plays an important role in many remote sensing and monitoring applications. However, conventional SAR image reconstruction methods generally perform undifferentiated imaging, complicating target detection. To address this challenge, we propose a SAR image reconstruction method based on self-attention deep prior learning for differentiated image reconstruction and target detection. The proposed method can separate the target from the clutter using their feature priors during image reconstruction, thus helping improve target detection performance. Specifically, a deep prior learning operation based on a self-attention convolutional neural network (SACNN) is proposed. SACNN can help enhance target and suppress clutter by learning both the local and global features. Finally, the proposed method is implemented through an unrolled deep network with a loss function designed to make the reconstructed image beneficial for target detection. Simulation experiments have been conducted to verify the efficacy of the proposed method.

关键词： Image reconstruction Radar polarimetry Feature extraction Clutter Object detection reconstruction algorithms Optimization Deep prior self-attention convolutional neural network (SACNN) synthetic aperture radar (SAR) image reconstruction target enhancement unrolling algorithm

来源：评论

学校读者我要写书评

暂无评论

Iterative reconstruction algorithm based on discriminant adaptive-weighted TV regularization for fibrous biological tissues using in-line X-ray phase-contrast imaging

引用

BIOMEDICAL OPTICS EXPRESS 2021年第4期12卷 2460-2483页

作者： Zheng, Mengting Zhao, Yuqing Han, Shuo Ji, Dongjiang Li, Yimin Lv, Wenjuan Xin, Xiaohong Zhao, Xinyan Hu, Chunhong Tianjin Med Univ Sch Biomed Engn & Technol Tianjin 300070 Peoples R China Tianjin Univ Technol & Educ Sch Sci Tianjin 300222 Peoples R China Capital Med Univ Beijing Friendship Hosp Liver Res Ctr Beijing 100050 Peoples R China

In-line X-ray phase-contrast computed tomography (IL-PCCT) can produce highcontrast and high-resolution images of biological samples, and it has a great advantage with regard to imaging the microstructures and morphologies of fibrous biological tissues (FBTs). Filtered back projection (FBP) is widely used in ILPCCT. However, it requires long scanning times and high radiation doses to produce high-quality CT images, and this restricts its applicability in biomedical and preclinical studies on FBTs. To solve this problem, a novel IL-PCCT reconstruction algorithm is proposed to decrease the radiation dose by reducing the number of projections and reconstruct high-quality CT images of FBTs. The proposed algorithm incorporates the FBP method into the iterative reconstruction framework. Considering the area types and anisotropic edge properties of FBTs, a discriminant adaptive-weighted total variation model is introduced to optimize the intermediate reconstructed images. A fibrous phantom simulation and real experiment were performed to assess the performance of the proposed algorithm. Simulation and experimental results demonstrated that the proposed algorithm is an effective IL-PCCT reconstruction method for FBTs with incomplete projection data, and it has a great ability to suppress artifacts and preserve the edges of fibrous structures.

关键词： Biological imaging Computed tomography Image quality Image reconstruction reconstruction algorithms X ray imaging

来源：评论

学校读者我要写书评

暂无评论

PPG Signal reconstruction Using Deep Convolutional Generative Adversarial Network 44

PPG Signal Reconstruction Using Deep Convolutional Generativ...

引用

44th Annual International Conference of the IEEE-Engineering-in-Medicine-and-Biology-Society (EMBC)

作者： Wang, Yuning Azimi, Iman Kazemi, Kianoosh Rahmani, Amir M. Liljeberg, Pasi Univ Turku Dept Comp Turku Finland Univ Calif Irvine Dept Elect Engn & Comp Sci Irvine CA USA Univ Calif Irvine Dept Comp Sci Irvine CA USA Univ Calif Irvine Sch Nursing Irvine CA USA

ISBN: (数字)9781728127828

ISBN: (纸本)9781728127828

Photoplethysmography (PPG) is a non-invasive technique used in wearable devices to collect various vital signs, including heart rate and heart rate variability. The signal is highly susceptible to motion artifacts, which is inevitable in health monitoring and may lead to inaccurate decision-making. Studies in the literature proposed time series analysis, signal decomposition, and machine learning methods to reconstruct PPG signals or reduce noise. However, they are limited to short-term noisy signals or to noise caused by certain physical activities. In this paper, we propose a deep convolutional generative adversarial network (GAN) method to reconstruct distorted PPG signals. Our method exploits the temporal information extracted from the corrupted signal and preceding data to perform PPG reconstruction. The model is trained and tested using data collected by smartwatches in a home-based health monitoring application. We evaluate the proposed GAN method in comparison to three state-of-the-art PPG reconstruction methods. The evaluation includes noisy PPG signals with different durations and SNR values. The proposed method outperforms the other methods by obtaining the least error rates. The results indicate that the proposed method is effective for improving PPG signal quality to produce reliable heart rate and heart rate variability.

关键词： reconstruction algorithms Generative adversarial networks Distortion Noise measurement Reliability Heart rate variability Signal resolution

来源：评论

学校读者我要写书评

暂无评论

Deep Hyperspectral-Depth reconstruction Using Single Color-Dot Projection

Deep Hyperspectral-Depth Reconstruction Using Single Color-D...

引用

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

作者： Li, Chunyu Monno, Yusuke Okutomi, Masatoshi Tokyo Inst Technol Tokyo Japan

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Depth reconstruction and hyperspectral reflectance reconstruction are two active research topics in computer vision and image processing. Conventionally, these two topics have been studied separately using independent imaging setups and there is no existing method which can acquire depth and spectral reflectance simultaneously in one shot without using special hardware. In this paper;we propose a novel single-shot hyperspectral-depth reconstruction method using an off-the-shelf RGB camera and projector. Our method is based on a single color-dot projection, which simultaneously acts as structured light for depth reconstruction and spatially-varying color illuminations for hyperspectral reflectance reconstruction. To jointly reconstruct the depth and the hyperspectral reflectance from a single color-dot image, we propose a novel end-to-end network architecture that effectively incorporates a geometric color-dot pattern loss and a photometric hyperspectral reflectance loss. Through the experiments, we demonstrate that our hyperspectral-depth reconstruction method outperforms the combination of an existing state-of-the-art single-shot hyperspectral reflectance reconstruction method and depth reconstruction method.

关键词： Reflectivity Training Computer vision Three-dimensional displays reconstruction algorithms Cameras Sensors

来源：评论

学校读者我要写书评

暂无评论

Neural Template: Topology-aware reconstruction and Disentangled Generation of 3D Meshes

Neural Template: Topology-aware Reconstruction and Disentang...

引用

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

作者： Hui, Ka-Hei Li, Ruihui Hu, Jingyu Fu, Chi-Wing Chinese Univ Hong Kong Hong Kong Peoples R China Hunan Univ Changsha Peoples R China

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

This paper introduces a novel framework called DTNet for 3D mesh reconstruction and generation via Disentangled Topology. Beyond previous works, we learn a topology-aware neural template specific to each input then deform the template to reconstruct a detailed mesh while preserving the learned topology. One key insight is to de couple the complex mesh reconstruction into two sub-tasks: topology formulation and shape deformation. Thanks to the decoupling, DT-Net implicitly learns a disentangled representation for the topology and shape in the latent space. Hence, it can enable novel disentangled controls for supporting various shape generation applications, e.g., remix the topologies of 3D objects, that are not achievable by previous reconstruction works. Extensive experimental results demonstrate that our method' is able to produce high quality meshes, particularly with diverse topologies, as compared with the state-of-the-art methods.

关键词： Three-dimensional displays Codes Shape Aerospace electronics reconstruction algorithms Topology Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

FvOR: Robust Joint Shape and Pose Optimization for Few-view Object reconstruction

FvOR: Robust Joint Shape and Pose Optimization for Few-view ...

引用

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

作者： Yang, Zhenpei Ren, Zhile Bautista, Miguel Angel Zhang, Zaiwei Shan, Qi Huang, Qixing Univ Texas Austin Austin TX 78712 USA Apple Cupertino CA USA

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Reconstructing an accurate 3D object model from a few image observations remains a challenging problem in computer vision. State-of-the-art approaches typically assume accurate camera poses as input, which could be difficult to obtain in realistic settings. In this paper, we present FvOR, a learning-based object reconstruction method that predicts accurate 3D models given a few images with noisy input poses. The core of our approach is a fast and robust multi-view reconstruction algorithm to jointly refine 3D geometry and camera pose estimation using learnable neural network modules. We provide a thorough benchmark of state-of-the-art approaches for this problem on ShapeNet. Our approach achieves best-in-class results. It is also two orders of magnitude faster than the recent optimization-based approach IDR[67].

关键词： Solid modeling Computer vision Three-dimensional displays Shape Computational modeling Pose estimation reconstruction algorithms

来源：评论

学校读者我要写书评

暂无评论

Shape reconstruction for Flexible Robot Using FBG Sensor

引用

IEEE INSTRUMENTATION & MEASUREMENT MAGAZINE 2025年第3期28卷 44-51页

作者： Jiang, Qi Wang, Feiwen Zhang, Yingxuan Shandong Univ Control Sci & Engn Dept Jinan Shandong Peoples R China

Flexible robots have shown great potential in medical applications. Highly accurate shape perception methods for flexible robots can effectively enhance their operability in complex environments. In this paper, an improved 3D shape reconstruction algorithm based on the Frenet-Serret formulas is proposed to reconstruct the robot curve. The complex 3D curve shape can be reconstructed by segmenting and stitching the curvature and torsion information collected by fiber Bragg grating sensor. The calibration experiments prove the reconstruction accuracy and calculation speed of the algorithm. The shape sensor for the flexible robot is fabricated, 2D and 3D shape sensing experiments are conducted. The average Euclidean errors of the reconstructed curve endpoints are 1.120 mm and 1.358 mm, and the average Frey interval distances are 1.922 mm and 2.533 mm, respectively. The experimental results showed that the designed shape sensor has high accuracy to meet the actual sensing requirements.

关键词： Surface reconstruction Optical fiber sensors Three-dimensional displays Accuracy reconstruction algorithms Robot sensing systems Fiber gratings Sensors Strain measurement Flexible structures

来源：评论

学校读者我要写书评

暂无评论

Nonlinear reconstruction of coded spectral X-ray CT based on material decomposition

引用

OPTICS EXPRESS 2021年第13期29卷 19319-19339页

作者： Zhang, Tong Zhao, Shengjie Ma, Xu Cuadros, Angela P. Zhao, Qile Arce, Gonzalo R. Tongji Univ Sch Software Engn Shanghai 201804 Peoples R China Beijing Inst Technol Sch Opt & Photon Minist Educ China Key Lab Photoelect Imaging Technol & Syst Beijing 100081 Peoples R China Univ Delaware Dept Elect & Comp Engn Newark DE 19716 USA

Coded spectral X-ray computed tomography (CT) based on K-edge filtered illumination is a cost-effective approach to acquire both 3-dimensional structure of objects and their material composition. This approach allows sets of incomplete rays from sparse views or sparse rays with both spatial and spectral encoding to effectively reduce the inspection duration or radiation dose, which is of significance in biological imaging and medical diagnostics. However, reconstruction of spectral CT images from compressed measurements is a nonlinear and ill-posed problem. This paper proposes a material-decomposition-based approach to directly solve the reconstruction problem, without estimating the energy-binned sinograms. This approach assumes that the linear attenuation coefficient map of objects can be decomposed into a few basis materials that are separable in the spectral and space domains. The nonlinear problem is then converted to the reconstruction of the mass density maps of the basis materials. The dimensionality of the optimization variables is thus effectively reduced to overcome the ill-posedness. An alternating minimization scheme is used to solve the reconstruction with regularizations of weighted nuclear norm and total variation. Compared to the state-of-the-art reconstruction method for coded spectral CT, the proposed method can significantly improve the reconstruction quality. It is also capable of reconstructing the spectral CT images at two additional energy bins from the same set of measurements, thus providing more spectral information of the object. (C) 2021 Optical Society of America under the terms of the OSA Open Access Publishing Agreement

关键词： Attenuation coefficient Biological imaging Image quality reconstruction algorithms Spectral imaging X ray computed tomography

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：