检索结果-内蒙古大学图书馆

Optimization Effect of Random Sample Consistency Algorithm in Immersive 3d Animation Splicing

IEEE ACCESS 2024年 12卷 193445-193458页

作者： duan, Tao dong, Wei Wang, Fei Yao, Yuxia Jilin Engn Normal Univ Sch Arts & Design Changchun 130000 Peoples R China Jilin Engn Normal Univ Inst Educ & Sci Changchun 130000 Peoples R China Jilin Agr Univ Coll Informat Technol Changchun 130000 Peoples R China

In order to provide viewers with a richer and more realistic visual experience and achieve the secondary utilization of 3d animation resources, an immersive 3d animation production image stitching model is designed based on Accelerated Kernelized-Adaptive-Zone-Extraction and Random Sample Consensus. The results showed that the image registration algorithm achieved the highest recall rate under changes in brightness, rotation angle, and flip angle, with values of 0.942, 0.971, and 0.831, respectively. The highest matching accuracy reached 94.17%. Meanwhile, the algorithm had the shortest execution time, with computation time for different datasets all within 400ms. The matching accuracy performed the best. The image quality processed by the designed image stitching algorithm was relatively high. The Brenner gradient function, Tenengrad gradient function, energy gradient function, and sum of modified differences 2 index simultaneously verified the clarity and detail quality of the image. Meanwhile, the peak signal-to-noise ratio exceeded the other three models, and the feature, multi-scale structure, and information content weighted similarity were all higher than 0.9. The mutual information, normalized mutual information, and normalized cross-correlation of spliced images performed the best. This study introduces new optimization strategies for the field of animation stitching, providing new ideas and methods for theoretical research in the immersive 3d animation field. This research has important practical significance for promoting the widespread application of immersive animation in film, television, gaming, and other fields.

关键词： Animation Three-dimensional displays image stitching Accuracy Production Solid modeling Libraries Optimization Industries Stereo image processing image registration image fusion depth image stitching random sampling consistency AKAZE algorithm

来源：评论

学校读者我要写书评

暂无评论

All Roads Lead to Rome: Achieving 3d Object Encryption Through 2d image Encryption Methods

引用

IEEE TRANSACTIONS ON image processing 2025年 34卷 1075-1089页

作者： Zhao, Ruoyu Zhang, Yushu Lan, Rushi Yi, Shuang Hua, Zhongyun Weng, Jian Jiangxi Univ Finance & Econ Sch Comp & Artificial Intelligence Nanchang 330013 Peoples R China Jiangxi Prov Key Lab Multimedia Intelligent Proc Nanchang 330013 Peoples R China Guilin Univ Elect Technol Guangxi Key Lab Image & Graph Intelligent Proc Guilin 541004 Peoples R China Southwest Univ Polit Sci & Law Criminal Invest Sch Chongqing 401120 Peoples R China Harbin Inst Technol Sch Comp Sci & Technol Shenzhen 518055 Guangdong Peoples R China Jinan Univ Coll Informat Sci & Technol Guangzhou 510632 Peoples R China

In this paper, we explore a new road for format-compatible 3d object encryption by proposing a novel mechanism of leveraging 2d image encryption methods. It alleviates the difficulty of designing 3d object encryption schemes coming from the intrinsic intricacy of the data structure, and implements the flexible and diverse 3d object encryption designs. First, turning complexity into simplicity, the vertex values, real numbers with continuous values, are converted into integers ranging from 0 to 255. The simplification result for a 3d object is a 2d numerical matrix. Second, six prototypes for three encryption patterns (permutation, diffusion, and permutation-diffusion) are designed as exemplifications to encrypt the 2d matrix. Third, the integer-valued elements in the encrypted numeric matrix are converted into real numbers complying with the syntax of the 3d object. In addition, some experiments are conducted to verify the effectiveness of the proposed mechanism.

关键词： Encryption Three-dimensional displays Matrix converters Roads Prototypes Standards distance measurement data structures Two-dimensional displays Electronic mail 3d object encryption image encryption multimedia security

来源：评论

学校读者我要写书评

暂无评论

Re-Introducing BN Into Transformers for Vision Tasks

引用

IEEE ACCESS 2023年 11卷 58462-58469页

作者： Tang, Xue-Song Xie, Xian-Lin Donghua Univ Coll Informat Sci & Technol Shanghai 201620 Peoples R China Minist Educ Engn Res Ctr Digitized Text Apparel Technol Shanghai 201620 Peoples R China

In recent years, Transformer-based models have exhibited significant advancements over previous models in natural language processing and vision tasks. This powerful methodology has also been extended to the 3d point cloud domain, where it can mitigate the inherent difficulties posed by the irregular and disorderly nature of the point clouds. However, the attention mechanism within the Transformer presents challenges for utilizing Batch Normalization (BN), as statistical information cannot be extracted efficiently from the data set. Thus, this study proposes a novel residual structure, ResBN, which can effectively handle 3d data. Additionally, to replace BN in the transformer for 2d image processing, we introduce the Patch Normalization (PN) technique. ResBN and PN are evaluated on 3d point cloud and 2d image datasets respectively through statistical experiments, demonstrating their efficacy in enhancing classification performance.

关键词： Three-dimensional displays Point cloud compression Feature extraction current transformers Transformers Convolutional neural networks Training data Point clouds normalization transformers 3d feature extraction

来源：评论

学校读者我要写书评

暂无评论

Visual perception of distance in 3d-augmented reality head-up displays

引用

JOURNAL OF THE SOCIETY FOR information dISPLAY 2024年第8期32卷 592-604页

作者： Lee, Tae Hee Jeong, Young Ju Sungkyunkwan Univ Comp Educ Seoul South Korea Sookmyung Womens Univ Software Cheongparo 47 gil 100 Seoul South Korea

A head-up display (HUd) is conveniently used to provide information on the display without changing the user's gaze. 3d HUds, capable of projecting three-dimensional information beyond the 2d HUds, enable the projection of augmented reality (AR) objects into the real world. research on the perception of 3d AR HUds is crucial for their efficient utilization and secure commercialization. In this study, we examined whether a 3d HUd is more comfortable than a 2d HUd in the context of viewing real-world environments and augmented reality objects together. Additionally, we analyzed participants' perception of distance and fatigue for AR objects at varying distances from the 3d HUd. The study found that using a 3d HUd in an AR environment resulted in less fatigue than using a 2d HUd, as determined by a Mann-Whitney statistical analysis. Participants were able to match the depth of AR objects in a 3d HUd within a range of 3 to 50 m, with similar diopter and parallax angular distance errors, regardless of the distance of the AR object. Visual fatigue increases with increasing distance from the virtual-image plane and can be modeled as a quadratic function in the domain of diopter and parallax angles. The present study aimed to analyze the perception of distance and fatigue for AR objects from the 3d HUd. Participants were able to match the depth of AR objects in a 3d HUd within a range of 3 to 50 m, with similar diopter and parallax angular distance errors, regardless of the distance of the AR object. image

关键词： 3d 3d perception augmented reality fatigue head-up display

来源：评论

学校读者我要写书评

暂无评论

Occlusion-Aware Amodal depth Estimation for Enhancing 3d Reconstruction From a Single image

引用

IEEE ACCESS 2024年 12卷 106524-106536页

作者： Jo, Seong-Uk Lee, du Yeol Rhee, Chae Eun Inha Univ Dept Elect & Comp Engn Incheon 22212 South Korea Hanyang Univ Dept Elect Engn Seoul 04763 South Korea

In various fields, such as robotics navigation, autonomous driving, and augmented reality, the demand for the reconstructing of three-dimensional (3d) scenes from two-dimensional (2d) images captured by a camera is growing. With advancements in deep learning, monocular depth prediction research has gained momentum, leading to the exploration of 3d reconstruction from a single image. While previous studies have attempted to restore occluded regions by training deep networks on high-resolution 3d data or with jointly learned 3d segmentation, achieving perfect restoration of occluded objects remains challenging. Such 3d mesh generation methods often result in unrealistic interactions with graphic objects, limiting their applicability. To address this, this paper introduces an amodal depth estimation approach to enhance the completeness of 3d reconstruction. By utilizing amodal masks that recover occluded regions, the method predicts the depths of obscured areas. Employing an iterative amodal depth estimation framework allows this approach to work even with scenes containing deep occlusions. Incorporating a spatially-adaptive normalization (SPAdE) fusion block within the amodal depth estimation model effectively combines amodal mask features and image features to improve the accuracy of depth estimation for occluded regions. The proposed system exhibits superior performance on occluded region depth estimation tasks compared to conventional depth inpainting networks. Unlike models that explicitly rely on multiple RGB or depth images to handle instances of occlusion, the proposed model implicitly extracts amodal depth information from a single image. Consequently, it significantly enhances the quality of 3d reconstruction even when single images serve as input. The code and data used in the paper are available at https://***/Seonguke/Occlusion-aware-Amodal-depth-Estimation-for-Enhancing-3d-Reconstruction-from-a-Single-image/ for further research and feedback.

关键词： Three-dimensional displays Estimation image reconstruction Transformers image restoration decoding Solid modeling Occlusion amodal segmentation depth estimation 3d-reconstruction

来源：评论

学校读者我要写书评

暂无评论

image quality enhancement for an integral imaging display using aperture array and revised pixel mapping method

引用

OPTICS EXPRESS 2025年第6期33卷 12615-12629页

作者： Li, Chao Ma, Haowen Li, Jingnan Wang, Yongtian Liu, Juan Beijing Inst Technol Beijing Engn Res Ctr Mixed Real & Adv Display Sch Opt & Photon MoE Key Lab Photoelect Imaging Technol & Syst Beijing 100081 Peoples R China

The limited space-bandwidth product constrains the performance of an integral imaging three-dimensional (3d) display, highlighting the need for optimization of system structure and display process. In this paper, we propose an image quality enhanced integral imaging 3d display system under a restricted information-capacity. An aperture array corresponding to the microlens array (MLA) is integrated into the system to improve display clarity and minimize crosstalk by controlling the beam diameter entering each microlens. To increase the ultimate information accuracy, a revised pixel mapping (RPM) method is designed to precisely manage the mapping from 3d scene voxels to pixels, which efficiently generates an element image array (EIA) without pseudoscopy or data loss. A prototype is developed, and the experimental results indicate that the Structural Similarity (SSIM) of reconstructed image improves by an average of 18%, with the improvement up to 40% at edge perspectives. This optimized system offers a promising solution for high-quality, real-time pickup and reconstruction in the naked-eye 3d display. (c) 2025 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement

关键词： diffractive optical elements Holographic displays Integral imaging Microlens arrays Systems design Three dimensional displays

来源：评论

学校读者我要写书评

暂无评论

Portrait stylized rendering for 3d light-field display based on radiation field and example guide

引用

OPTICS EXPRESS 2023年第18期31卷 29664-29675页

作者： Shen, Sheng Xing, Shujun Sang, Xinzhu Yan, Binbin Xie, Xinhui Fu, Bangshao Zhong, Chongli Zhang, Shuang Beijing Univ Posts & Telecommun State Key Lab Informat Photon & Opt Commun Beijing 100876 Peoples R China

With the development of three-dimensional (3d) light-field display technology, 3d scenes with correct location information and depth information can be perceived without wearing any external device. Only 2d stylized portrait images can be generated with traditional portrait stylization methods and it is difficult to produce high-quality stylized portrait content for 3d light-field displays. 3d light-field displays require the generation of content with accurate depth and spatial information, which is not achievable with 2d images alone. New and innovative portrait stylization techniques methods should be presented to meet the requirements of 3d light-field displays. A portrait stylization method for 3d light-field displays is proposed, which maintain the consistency of dense views in light-field display when the 3d stylized portrait is generated. Example-based portrait stylization method is used to migrate the designated style image to the portrait image, which can prevent the loss of contour information in 3d light-field portraits. To minimize the diversity in color information and further constrain the contour details of portraits, the Laplacian loss function is introduced in the pre-trained deep learning model. The three-dimensional representation of the stylized portrait scene is reconstructed, and the stylized 3d light field image of the portrait is generated the mask guide based light-field coding method. Experimental results demonstrate the effectiveness of the proposed method, which can use the real portrait photos to generate high quality 3d light-field portrait content.& COPY;2023 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement

关键词： image resolution Light fields Neural networks Synthesis methods Three dimensional displays Three dimensional imaging

来源：评论

学校读者我要写书评

暂无评论

image Understands Point Cloud: Weakly Supervised 3d Semantic Segmentation via Association Learning

引用

IEEE TRANSACTIONS ON image processing 2024年 33卷 1838-1852页

作者： Sun, Tianfang Zhang, Zhizhong Tan, Xin Qu, Yanyun Xie, Yuan East China Normal Univ Sch Comp Sci & Technol Shanghai 200060 Peoples R China East China Normal Univ Chongqing Inst Chongqing 401333 Peoples R China Xiamen Univ Sch Informat Dept Comp Sci & Technol Xiamen 361005 Fujian Peoples R China

Weakly supervised point cloud semantic segmentation methods that require 1% or fewer labels with the aim of realizing almost the same performance as fully supervised approaches have recently attracted extensive research attention. A typical solution in this framework is to use self-training or pseudo-labeling to mine the supervision from the point cloud itself while ignoring the critical information from images. In fact, cameras widely exist in LidAR scenarios, and this complementary information seems to be highly important for 3d applications. In this paper, we propose a novel cross-modality weakly supervised method for 3d segmentation that incorporates complementary information from unlabeled images. We design a dual-branch network equipped with an active labeling strategy to maximize the power of tiny parts of labels and to directly realize 2d-to-3d knowledge transfer. Afterward, we establish a cross-modal self-training framework, which iterates between parameter updating and pseudolabel estimation. In the training phase, we propose cross-modal association learning to mine complementary supervision from images by reinforcing the cycle consistency between 3d points and 2d superpixels. In the pseudolabel estimation phase, a pseudolabel self-rectification mechanism is derived to filter noisy labels, thus providing more accurate labels for the networks to be fully trained. The extensive experimental results demonstrate that our method even outperforms the state-of-the-art fully supervised competitors with less than 1% actively selected annotations.

关键词： Point cloud compression Three-dimensional displays Labeling Laser radar Annotations Training Semantic segmentation Multimodal weakly supervised point cloud semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

dual-stream spectral-spatial convolutional neural network for hyperspectral image classification and optimal band selection

引用

AdVANCES IN SPACE research 2024年第5期74卷 2025-2041页

作者： Atik, Saziye Ozge Istanbul Tech Univ Fac Civil Engn Dept Geomat Engn TR-34469 Istanbul Turkiye

Along with the high spectral rich information it provides, one of the difficulties in processing a hyperspectral image is the need for expert knowledge and high-spec hardware to process very high-dimensional data. 3d convolutional neural network (3d CNN), which uses spectral and spatial features together, enables a powerful solution for HSI classification. This study proposes an efficient dual-stream 3d CNN for accurate HSI classification. The proposed method offers effective classification using spectral-spatial features without relying on pre-processing or post-processing. A comparative study of how CNN classification performance is affected by hyperspectral band selection based on deep reinforcement learning (dRL) is presented. Using the most relevant bands in the hyperspectral image is decisive in deep CNN networks without losing information and accuracy. The proposed method was compared with 3d CNN, 3d + 1d CNN, Multiscale 3d deep convolutional neural network (M3d-dCNN), and InceptionV3 algorithms using Indian Pines (IP), Salinas, Pavia Center (PaviaC), Houston 2013 and QUH-Tangdaowan datasets. It achieved 92.43 % overall accuracy (OA) in IP, 95.06 % OA in Salinas dataset, 99.00 % OA in PaviaC dataset, 91.25 % OA in Houston 2013 and 94.87 % OA in QUH-Tangdaowan. Codes are released at: https://***/lapistlazuli/dS-3dCNN. (c) 2024 COSPAR. Published by Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.

关键词： Hyperspectral image Classification deep Learning dual-Stream Band Selection deep Reinforcement Learning 3d CNN

来源：评论

学校读者我要写书评

暂无评论

Multi-View 3d Scene Abstraction From drone-Captured RGB images

引用

IEEE ACCESS 2025年 13卷 27641-27656页

作者： Jeong, Wooseong Kim, Jihun Kweon, Hyeokjun Yoon, Kuk-Jin Korea Adv Inst Sci & Technol KAIST Dept Mech Engn Daejeon 34141 South Korea

3d map reconstruction plays a critical role in fields such as autonomous driving, urban planning, and virtual reality. Using 2d images from real-world settings, multi-view image-based 3d map reconstruction offers a practical solution across these sectors. Specifically, generating 3d maps from realistic drone-view images has broad applicability. However, direct reconstruction from drone-view images is challenging due to extreme viewing angles and unstable image conditions like motion blur or varying light. Additionally, simultaneously generating and utilizing 3d maps from drone-captured images presents significant challenges, including fragmented sub-tasks such as 3d point cloud reconstruction, surface reconstruction, and shape fitting. To address these challenges, we introduce the 3d Scene Abstraction, which seamlessly integrates image matching, 3d reconstruction, 3d semantic segmentation, clustering, and shape fitting to produce 3d maps from RGB images. Our approach enhances the robustness of 3d map generation by merging 2d semantic information with 3d point clouds, ensuring reliable results under diverse drone-captured image conditions. For efficient data representation, we employ multiple primitives based on prior knowledge of various building shapes, improving both map formation performance and computational efficiency. Our approach not only enhances the effectiveness of 3d map reconstruction but also reduces the amount of data required to represent the scene, thereby improving overall efficiency and practical usability. These contributions address practical challenges in the field and lay the foundation for future advancements in 3d map reconstruction technologies.

关键词： Three-dimensional displays image reconstruction Point cloud compression Shape image color analysis Surface reconstruction Feature extraction Fitting Surface treatment Surface fitting 3d map reconstruction multi-view image-based reconstruction drone-view images 3d scene abstraction clustering shape fitting data efficiency primitives

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：