检索结果-内蒙古大学图书馆

A Non-Rigid Three-dimensional image Reconstruction Algorithm Based on deformable Shape Reliability

IEEE ACCESS 2024年 12卷 76995-77008页

作者： Chen, Haiying Moqurrab, Syed Atif Tianmen Vocat Coll Dept Publ Courses Tianmen 431700 Peoples R China Gachon Univ Sch Comp Seongnam Si 13120 South Korea

Most reconstruction algorithms for non-rigid three-dimensional (3d) images assume that non-rigidity can be represented as a linear combination of a fixed number of rigid bases. However, this assumption struggles to establish reliable shape functions and initial values for nonlinear and non-rigid motions, decreasing reconstruction reliability. This paper introduces an enhanced-reliability reconstruction algorithm for non-rigid 3d images. Our algorithm models the dynamic non-rigid shape basis as a low-rank matrix composed of image points and depth factors, improving the restoration of non-rigid shape base changes and providing accurate parameters for constructing objective functions. By leveraging manifold alignment and physical continuity constraints, our method optimizes the function structures. Assuming minimal reconstruction error and shape change, we solve for the motion structure parameters and select the key initial shape basis value by minimizing the objective function with the L-M nonlinear optimization method. Our experimental results on 3d image sequence reconstructions demonstrate significant error reduction, underscoring our model's credibility, robust reliability, and minimal re-projection error.

关键词： Shape mesaurement Three-dimensional displays image reconstruction Reliability Manifolds Matrix decomposition Linear programming Ranking (statistics) Rigidity Non-rigid 3d image reconstruction shape reliability low-rank matrix improved objective function

来源：评论

学校读者我要写书评

暂无评论

Leveraging Single-View images for Unsupervised 3d Point Cloud Completion

引用

IEEE TRANSACTIONS ON MULTIMEdIA 2025年 27卷 940-953页

作者： Wu, Lintai Zhang, Qijian Hou, Junhui Xu, Yong City Univ Hong Kong Dept Comp Sci Hong Kong Peoples R China Harbin Inst Technol Biocomp Res Ctr Shenzhen 518055 Guangdong Peoples R China Shenzhen Key Lab Visual Object Detect & Recognit Shenzhen 518055 Guangdong Peoples R China

Point clouds captured by scanning devices are often incomplete due to occlusion. To overcome this limitation, point cloud completion methods have been developed to predict the complete shape of an object based on its partial input. These methods can be broadly classified as supervised or unsupervised. However, both categories require a large number of 3d complete point clouds, which may be difficult to capture. In this paper, we propose Cross-PCC, an unsupervised point cloud completion method without requiring any 3d complete point clouds. We only utilize 2d images of the complete objects, which are easier to capture than 3d complete and clean point clouds. Specifically, to take advantage of the complementary information from 2d images, we use a single-view RGB image to extract 2d features and design a fusion module to fuse the 2d and 3d features extracted from the partial point cloud. To guide the shape of predicted point clouds, we project the predicted points of the object to the 2d plane and use the foreground pixels of its silhouette maps to constrain the position of the projected points. To reduce the outliers of the predicted point clouds, we propose a view calibrator to move the points projected to the background into the foreground by the single-view silhouette image. To the best of our knowledge, our approach is the first point cloud completion method that does not require any 3d supervision. The experimental results of our method are superior to those of the state-of-the-art unsupervised methods by a large margin. Moreover, our method even achieves comparable performance to some supervised methods.

关键词： Point cloud compression Three-dimensional displays Shape Feature extraction image reconstruction Training Fuses Cross-modality point cloud completion single-view image unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Implicit-Explicit Integrated Representations for Multi-View Video Compression

引用

IEEE TRANSACTIONS ON image processing 2025年 34卷 1106-1118页

作者： Zhu, Chen Lu, Guo He, Bing Xie, Rong Song, Li Shanghai Jiao Tong Univ Sch Elect Informat & Elect Engn Shanghai 200240 Peoples R China Shanghai Jiao Tong Univ AI Inst Key Lab Artificial Intelligence MoE Shanghai 200240 Peoples R China

With the increasing consumption of 3d displays and virtual reality, multi-view video has become a promising format. However, its high resolution and multi-camera shooting result in a substantial increase in data volume, making storage and transmission a challenging task. To tackle these difficulties, we propose an implicit-explicit integrated representation for multi-view video compression. Specifically, we first use the explicit representation-based 2d video codec to encode one of the source views. Subsequently, we propose employing the implicit neural representation (INR)-based codec to encode the remaining views. The implicit codec takes the time and view index of multi-view video as coordinate input and generates the corresponding implicit reconstruction frames. To enhance the compressibility, we introduce a multi-level feature grid embedding and a fully convolutional architecture into the implicit codec. These components facilitate coordinate-feature and feature-RGB mapping, respectively. To further enhance the reconstruction quality from the INR codec, we leverage the high-quality reconstructed frames from the explicit codec to achieve inter-view compensation. Finally, the compensated results are fused with the implicit reconstructions from the INR to obtain the final reconstructed frames. Our proposed framework combines the strengths of both implicit neural representation and explicit 2d codec. Extensive experiments conducted on public datasets demonstrate that the proposed framework can achieve comparable or even superior performance to the latest multi-view video compression standard MIV and other INR-based schemes in terms of view compression and scene modeling. The source code can be found at https://***/zc-lynen/MV-IERV.

关键词： image reconstruction image coding Codecs Video compression Standards Three-dimensional displays Cameras Video coding Indexes Transform coding Multi-view video compression implicit neural representation feature grid inter-view compensation

来源：评论

学校读者我要写书评

暂无评论

Real-time per-pixel predistortion for head-tracked light field displays

引用

JOURNAL OF THE SOCIETY FOR information dISPLAY 2025年

作者： Wu, Tianyu Jajoo, Anuraag Choi, Hee-Jin Watson, Benjamin North Carolina State Univ Visual Experience Lab Raleigh NC 27695 USA Sejong Univ Dept Phys Seoul South Korea

The latest light-field displays (LFds) have improved greatly with head tracking but continue to be based on the approximate pinhole model, meaning that cross-talk is often visible at large viewing angles and when virtual objects are distant from the display panel. To address these problems, our real-time LFd technique evaluates a full optical model for every frame and then displays an image predistorted during ray-traced rendering at the subpixel level to the current pixel-to-eye light flow, reducing cross-talk and increasing viewing angle. A comparison to imagery produced with the pinhole model shows clear advantages for our LFd technique, and in a user study with interactive, head-tracked display of several different scenes, viewers reported a significant preference for our novel LFd technique. Our unoptimized prototype implementation is already real time, and as GPUs improve in performance and ray tracing becomes increasingly common, we expect that our LFd technique will be easy to add to a variety of 3d applications, including games.

关键词： eye-tracking integral imaging light-field display real-time ray tracing

来源：评论

学校读者我要写书评

暂无评论

An Improved High Precision 3d Semantic Mapping of Indoor Scenes from RGB-d images

引用

Computer Modeling in Engineering & Sciences 2023年第12期137卷 2621-2640页

作者： Jing Xin Kenan du Jiale Feng Mao Shan Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi’an University of TechnologyXi’an710048China Australian Centre for Field Robotics The University of SydneySydney2006Australia

This paper proposes an improved high-precision 3d semantic mapping method for indoor scenes using RGB-d *** current semantic mapping algorithms suffer from low semantic annotation accuracy and insufficient real-time *** address these issues,we first adopt the Elastic Fusion algorithm to select key frames from indoor environment image sequences captured by the Kinect sensor and construct the indoor environment space ***,an indoor RGB-d image semantic segmentation network is proposed,which uses multi-scale feature fusion to quickly and accurately obtain object labeling information at the pixel level of the spatial point cloud ***,Bayesian updating is used to conduct incremental semantic label fusion on the established spatial point cloud *** also employ dense conditional random fields(CRF)to optimize the 3d semantic map model,resulting in a high-precision spatial semantic map of indoor *** results show that the proposed semantic mapping system can process image sequences collected by RGB-d sensors in real-time and output accurate semantic segmentation results of indoor scene images and the current local spatial semantic ***,it constructs a globally consistent high-precision indoor scenes 3d semantic map.

关键词： 3d semantic map online reconstruction RGB-d images semantic segmentation indoor mobile robot

来源：评论

学校读者我要写书评

暂无评论

Language guided 3d object detection in point clouds for MEP scenes

引用

IET COMPUTER VISION 2024年第4期18卷 526-539页

作者： Li, Junjie du, Shengli Liu, Jianfeng Chen, Weibiao Tang, Manfu Zheng, Lei Wang, Lianfa Ji, Chunle Yu, Xiao Yu, Wanli China Natl Coal Grp Co China Coal Shaanxi Yulin Energy & Chem Co Ltd Yulin Shanxi Peoples R China China Natl Coal Grp Co China Coal Elect Co Ltd Beijing Peoples R China China Univ Min & Technol IOT Percept Mine Res Ctr Xuzhou 221000 Jiangsu Peoples R China Univ Bremen Inst Electrodynam & Microelect Bremen Germany

In recent years, contrastive language-image pre-training (CLIP) has gained popularity for processing 2d data. However, the application of cross-modal transferable learning to 3d data remains a relatively unexplored area. In addition, high-quality, labelled point cloud data for Mechanical, Electrical, and Plumbing (MEP) scenarios are in short supply. To address this issue, the authors introduce a novel object detection system that employs 3d point clouds and 2d camera images, as well as text descriptions as input, using image-text matching knowledge to guide dense detection models for 3d point clouds in MEP environments. Specifically, the authors put forth the proposition of a language-guided point cloud modelling (PCM) module, which leverages the shared image weights inherent in the CLIP backbone. This is done with the aim of generating pertinent category information for the target, thereby augmenting the efficacy of 3d point cloud target detection. After sufficient experiments, the proposed point cloud detection system with the PCM module is proven to have a comparable performance with current state-of-the-art networks. The approach has 5.64% and 2.9% improvement in KITTI and SUN-RGBd, respectively. In addition, the same good detection results are obtained in their proposed MEP scene dataset. The authors proposed a language-guided 3d object detection in point clouds for MEP scenes. Specifically, the authors put forth the proposition of a language-guided point cloud modelling (PCM) module, which leverages the shared image weights inherent in the CLIP ***

关键词： computer vision object detection

来源：评论

学校读者我要写书评

暂无评论

design of 3d Mapping and Encryption Techniques in digital image processing

引用

International Journal of Network Security 2025年第2期27卷 378-389页

作者： Wang, Xiaofen Wang, Yanzhen Yu, Kaiyue School of Architecture and Art Shijiazhuang Tiedao University Shijiazhuang050043 China

digital images are the most widely used format for digital data and the protection of their information is critical in the current network environment. Chaotic systems have been widely implemented in image encryption;however, current digital image encryption technology struggles to meet high-efficiency standards for image information encryption and defend against complex external attacks. As a result, this work suggests using a public key cipher based on 3d logistic mapping to create an asymmetric picture encryption technique. Histogram analysis revealed that the suggested encryption algorithm could effectively counteract histogram attacks, lowering the average ciphertext image cardinality of the three digital images by 99.88% compared to the plaintext image. Compared to the traditional encryption method, the correlation of the ciphertext image was reduced by 96.05%, 75.26%, and 90.05%, respectively, in metrics like the level of the phase space. Furthermore, all three types of pictures’ ciphertext image correlation coefficients were nearly zero. information entropy analysis and the differential attack demonstrated that the suggested encryption methods from the study effectively enhanced information encryption in digital photographs. Furthermore, every differential attack indicator reached the theoretical maximum. The findings suggest that the suggested algorithm for encrypting digital images exhibits strong resilience against various types of attacks, such as those that include the use of differential methods, statistical studies, and histograms. Additionally, the algorithm exhibits superior encryption performance for image data. © (2025), (International Journal of Network Security). All rights reserved.

关键词： Chaotic systems

来源：评论

学校读者我要写书评

暂无评论

Laser: Efficient Language-Guided Segmentation in Neural Radiance Fields

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS ANd MACHINE INTELLIGENCE 2025年第5期47卷 3922-3934页

作者： Miao, Xingyu duan, Haoran Bai, Yang Shah, Tejal Song, Jun Long, Yang Ranjan, Rajiv Shao, Ling Univ Durham Dept Comp Sci Durham DH1 3LE England Newcastle Univ Sch Comp Newcastle Upon Tyne NE1 7RU England ASTAR Inst High Performance Comp IHPC Singapore 138632 Singapore China Univ Geosci Sch Comp Sci Wuhan 430074 Peoples R China Univ Chinese Acad Sci Terminus AI Lab UCAS Beijing 100049 Peoples R China

In this work, we propose a method that leverages CLIP feature distillation, achieving efficient 3d segmentation through language guidance. Unlike previous methods that rely on multi-scale CLIP features and are limited by processing speed and storage requirements, our approach aims to streamline the workflow by directly and effectively distilling dense CLIP features, thereby achieving precise segmentation of 3d scenes using text. To achieve this, we introduce an adapter module and mitigate the noise issue in the dense CLIP feature distillation process through a self-cross-training strategy. Moreover, to enhance the accuracy of segmentation edges, this work presents a low-rank transient query attention mechanism. To ensure the consistency of segmentation for similar colors under different viewpoints, we convert the segmentation task into a classification task through label volume, which significantly improves the consistency of segmentation in color-similar areas. We also propose a simplified text augmentation strategy to alleviate the issue of ambiguity in the correspondence between CLIP features and text. Extensive experimental results show that our method surpasses current state-of-the-art technologies in both training speed and performance.

关键词： Three-dimensional displays Neural radiance field image segmentation Semantics Feature extraction Training Rendering (computer graphics) Visualization Solid modeling Accuracy 3d segmentation CLIP NeRF

来源：评论

学校读者我要写书评

暂无评论

3d Reconstruction of Light Microscopic images and Its Significance for Better Clinical decisions: A Systematic Review Emphasizing Gastric Histopathology

引用

IEEE ACCESS 2024年 12卷 93957-93974页

作者： Roy, Bijoyeta Gupta, Mousumi Krishna Goswami, Bidyut Sikkim Manipal Univ Sikkim Manipal Inst Technol Dept Comp Sci & Engn Gangtok 737102 Sikkim India Sikkim Manipal Univ Sikkim Manipal Inst Technol Dept Comp Applicat Gangtok 737102 Sikkim India North Bengal Med Coll & Hosp Dept Pathol Siliguri 734012 W Bengal India

Histopathological findings depend on the distinction between normal and subtle changes in mucosal tissues. These distinctions are made based on the nature of the cell lining, nuclear hyperchromasia and cyto-architecture of glands. diagnosis is mostly based on the experience of the pathologists, which is a subjective procedure. This research focuses on automating the process through 3d reconstruction of gastric histopathology images enhancing quantitative diagnosis. It emphasizes the advantages of 3d reconstruction from light microscopic serial section gastric images over whole slide imaging for clinical decision-making. Comparative analysis shows that processing and analyzing WSI scans are more expensive than light microscopy. While 2d imaging with light microscopy faces challenges due to limited focal depth, especially for thin sections, the objective of this research is to highlight the importance of transforming 2d gastric images into 3d by layering sequential sections. It will offer insights into glandular texture and volume, aiding in distinguishing between malignant glands and benign mimickers. The paper presents a summary and comparative examination of the registration techniques necessary for reconstructing 3d histopathology images. Additionally, it discusses future directions in the field of 3d histopathology reconstruction and acknowledges its potential benefits for research scholars. This will hold potential interest for pathologists when grading gastric carcinoma.

关键词： Three-dimensional displays Histopathology Microscopy Glands image reconstruction Reviews Surveys Gastrointestinal tract gastric gland serial section registration 3d reconstruction

来源：评论

学校读者我要写书评

暂无评论

Enhanced Heart disease Classification Using dual Attention Mechanisms and 3d-Echo Fusion Algorithm in Echocardiogram Videos

引用

IEEE ACCESS 2025年 13卷 1609-1620页

作者： deepika, S. Jaisankar, N. Vellore Inst Technol Sch Comp Sci & Engn Vellore 632014 India

Heart disease remains a leading cause of mortality worldwide, making early detection and diagnosis crucial for preventing severe outcomes. Echocardiogram based classification of heart valve conditions is vital for effectively diagnosing and managing heart disease. In this paper, we present a novel hybrid deep learning framework that integrates convolutional neural networks (CNNs) with recurrent neural networks (RNNs) alongside a 3d-Echo Fusion approach and a dual Attention Model for heart valve disease classification using echocardiogram videos. Our method employs a CNN-based encoder to extract spatial features from individual video frames, which are then enhanced through a 3d-Echo Fusion technique to capture comprehensive volumetric information. An RNN models the temporal dynamics of heart valve motion, while the dual Attention Model refines the classification process by enabling the model to focus on the most relevant features. This integration results in a classification accuracy of 98.7% and an AUC score of 0.85, demonstrating the model's effectiveness in heart valve disease classification. The high accuracy and interpretability of the model provide potential clinical benefits by supporting decision-making and improving patient care. Furthermore, our proposed method addresses challenges related to the variability and complexity of cardiac data, aligning with current research that advocates for automated learning models in interpreting echocardiographic imagery. By leveraging advanced deep learning techniques, including 3d-Echo Fusion, our approach promises high classification accuracy while reducing reliance on manual annotations, thus enhancing scalability in cardiac diagnostics.

关键词： Feature extraction diseases Videos Convolutional neural networks Attention mechanisms Recurrent neural networks deep learning Three-dimensional displays Heart valves data models 3d-echo fusion dual attention mechanism heart valves CNN-RNN deep learning

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：